# classification

Published articles for classification.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Clairic Hit 98% Accuracy on 72.8% of Questions via Confidence Scores

DevFeed: [Clairic Hit 98% Accuracy on 72.8% of Questions via Confidence Scores](<https://devfeed.tech/articles/clairic-hit-98-accuracy-on-72-8-of-questions-via-confidence-scores-146441.md>)

Original publisher: [Read original article](<https://towardsdatascience.com/clairic-hit-98-accuracy-on-728-of-questions-via-confidence-scores/>)

Author: Mariya Mansurova

Published: 2026-11-20T15:00:00Z

Content type: tutorial

Language: en

Sources: [Towards Data Science](<https://devfeed.tech/sources/towards-data-science.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Data Science](<https://devfeed.tech/topics/data-science.md>), [ai-experiments](<https://devfeed.tech/topics/ai-experiments.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>)

Tags: [analysts](<https://devfeed.tech/tags/analysts.md>), [arithmetic](<https://devfeed.tech/tags/arithmetic.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [autocomplete](<https://devfeed.tech/tags/autocomplete.md>), [based](<https://devfeed.tech/tags/based.md>), [bike](<https://devfeed.tech/tags/bike.md>), [charts](<https://devfeed.tech/tags/charts.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cloudflare](<https://devfeed.tech/tags/cloudflare.md>), [complex](<https://devfeed.tech/tags/complex.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [confidence-interval](<https://devfeed.tech/tags/confidence-interval.md>), [control](<https://devfeed.tech/tags/control.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [easy](<https://devfeed.tech/tags/easy.md>), [editor-s-picks](<https://devfeed.tech/tags/editor-s-picks.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [jev](<https://devfeed.tech/tags/jev.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-applications](<https://devfeed.tech/tags/llm-applications.md>), [luna](<https://devfeed.tech/tags/luna.md>), [model](<https://devfeed.tech/tags/model.md>), [science](<https://devfeed.tech/tags/science.md>), [system-one](<https://devfeed.tech/tags/system-one.md>)

### AI overview

Clairic is a fast, low-cost extraction model that accepts text and images and can return typed values with confidence scores. In tests against Luna, Clairic was faster but less accurate overall, especially on calculations; examples also included confidently incorrect extractions. It handled some chart-based extraction and returned null for missing revenue. On 1,360 questions across four languages, a 0.9 confidence cutoff yielded 98% accuracy while Clairic answered 72.8% of questions. The author suggests using it for high-confidence extraction and routing the rest to a larger model, with validation because confidence is imperfect. The tests did not establish a reason to prefer it for forecasting over traditional methods.

### Source excerpt

With a 0.9 confidence cutoff, Cloudflare's System One model handles the easy cases and routes the rest to a bigger, slower LLM like Luna. The post Clairic Hit 98% Accuracy on 72.8% of Questions via Confidence Scores appeared first on Towards Data Science.

## When Safety Rationales Hallucinate: Diagnosing and Grounding Multimodal Safety Guards

DevFeed: [When Safety Rationales Hallucinate: Diagnosing and Grounding Multimodal Safety Guards](<https://devfeed.tech/articles/when-safety-rationales-hallucinate-diagnosing-and-grounding-multimodal-safety-guards-145588.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25793>)

Author: Yingshuo Wang, Weixiang Zhao, Guancheng Li, Jiahe Guo, Yu Zhang, Yanyan Zhao

Published: 2026-11-20T05:00:00Z

Content type: news

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [attribution](<https://devfeed.tech/tags/attribution.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classification-accuracy](<https://devfeed.tech/tags/classification-accuracy.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [fine](<https://devfeed.tech/tags/fine.md>), [focus](<https://devfeed.tech/tags/focus.md>), [generation](<https://devfeed.tech/tags/generation.md>), [grounded](<https://devfeed.tech/tags/grounded.md>), [grounding](<https://devfeed.tech/tags/grounding.md>), [guards](<https://devfeed.tech/tags/guards.md>), [learning](<https://devfeed.tech/tags/learning.md>), [model](<https://devfeed.tech/tags/model.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [safety](<https://devfeed.tech/tags/safety.md>), [scale](<https://devfeed.tech/tags/scale.md>)

### AI overview

The study finds that multimodal safety guards often produce unreliable rationales: they may state unsupported visual facts or assign incorrect safety meanings to grounded content. This persists across the examined methods, vision-language backbones, and datasets, and does not consistently improve with higher prediction accuracy or model scale. In Think-with-Image analysis, errors cluster around fine-grained attributes and relations; visual tools are often used infrequently or without enough spatial focus. The proposed Tool-Contrastive Grounding Reinforcement Learning (TCG-RL) rewards tool use only when it improves grounding relative to a tool-free reference. The abstract reports substantially fewer rationale hallucinations while maintaining competitive safety prediction performance, highlighting that prediction correctness alone does not establish rationale reliability.

### Source excerpt

arXiv:2611.25793v1 Announce Type: new Abstract: Multimodal safety guards increasingly generate rationales alongside safety predictions, yet whether these rationales are reliable remains largely unexplored. We systematically study *rationale hallucination* from two perspectives: visual rationale hallucination, where rationales contain unsupported visual facts, and safety attribution hallucination, where grounded content is assigned an incorrect safety interpretation. Across rationale-generation methods, multiple vision-language backbones, and safety datasets, we find that rationale hallucination is widespread and does not consistently diminish with higher classification accuracy or increased model scale. Further analysis of the Think-with-Image paradigm shows that hallucination is concentrated in fine-grained attributes and relations, while visual tools are often invoked infrequently or without sufficient spatial focus. Based on these findings, we propose *Tool-Contrastive Grounding Reinforcement Learning* (TCG-RL), which rewards tool use only when it improves rationale grounding over a tool-free reference. TCG-RL substantially reduces rationale hallucination while maintaining competitive safety prediction performance. By revealing the gap between prediction correctness and rationale reliability, our study motivates a shift in multimodal safety guarding from outcome-only evaluation toward safety decisions that are both accurate and verifiably grounded.

## Achieving Near-Zero-Overhead Multi-Model Hierarchical Classification in Real-Time Detection Pipelines

DevFeed: [Achieving Near-Zero-Overhead Multi-Model Hierarchical Classification in Real-Time Detection Pipelines](<https://devfeed.tech/articles/achieving-near-zero-overhead-multi-model-hierarchical-classification-in-real-time-detection-pipelines-144919.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.11770>)

Author: Vaishnav Raju

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [quantization](<https://devfeed.tech/topics/quantization.md>), [Jetson Orin](<https://devfeed.tech/topics/jetson-orin.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [real-time](<https://devfeed.tech/topics/real-time.md>)

Tags: [accelerators](<https://devfeed.tech/tags/accelerators.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-vehicles](<https://devfeed.tech/tags/autonomous-vehicles.md>), [bottleneck](<https://devfeed.tech/tags/bottleneck.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classifier](<https://devfeed.tech/tags/classifier.md>), [classifiers](<https://devfeed.tech/tags/classifiers.md>), [compilation](<https://devfeed.tech/tags/compilation.md>), [concurrent](<https://devfeed.tech/tags/concurrent.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [custom](<https://devfeed.tech/tags/custom.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [detection](<https://devfeed.tech/tags/detection.md>), [drone](<https://devfeed.tech/tags/drone.md>), [edge](<https://devfeed.tech/tags/edge.md>), [overhead](<https://devfeed.tech/tags/overhead.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [real-time](<https://devfeed.tech/tags/real-time.md>)

### AI overview

The paper reports that a GPU detector paired with DLA classification on a Jetson Orin NX ran at 12.5 FPS at 1080p, compared with 13.3 FPS for the detector alone. Its five-step deployment method covers adapting classification architectures, repairing TensorRT implicit quantization ranges for pipeline validation (raising reported accuracy from 75% to 94%), quantization-aware training, ONNX graph surgery, and concurrent GPU/DLA inference. The authors also describe nine engineering constraints and report dual-DLA scaling without additional cost. Evidence here is limited to the abstract.

### Source excerpt

arXiv:2608.11770v2 Announce Type: replace-cross Abstract: Edge-deployed vision systems in target recognition, surveillance, autonomous vehicles, and drone domains require hierarchical inference pipelines where a detection model identifies objects of interest and downstream classifiers provide fine-grained attribute analysis. Running all models on the GPU creates a serial bottleneck that limits real-time throughput as pipeline stages grow. Modern edge SoCs pair GPUs with dedicated neural accelerators (NPUs, DLAs) capable of concurrent execution, yet deploying custom models on these accelerators remains impractical due to strict operator constraints, quantization incompatibilities, and an undocumented end-to-end pipeline. We target NVIDIA Jetson DLA cores as the representative platform. We present a five-step methodology for zero GPU fallback DLA INT8 deployment of classification backbones, comprising architecture adaptation, manual dynamic range workaround to rescue TensorRT's implicit quantization (recovering 94.0% accuracy from implicit quantization's 75%) for rapid pipeline validation before explicit quantization, quantization-aware training, ONNX graph surgery for DLA compilation, and a concurrent GPU-detection/DLA-classification inference pipeline. We document nine engineering constraints with root-cause analysis and generalizable solutions. Validation on a dual-head person attribute classifier running on DLA alongside a GPU object detector on a Jetson Orin NX demonstrates near-zero pipeline overhead (12.5 vs. 13.3~FPS detector-only at 1080p), with dual-DLA scaling at no additional cost. The methodology is backbone-agnostic and generalizes to any detection-classification edge pipeline.

## Stop Removing Stopwords: How an Inherited Preprocessing Default Distorts Legal Text-as-Data

DevFeed: [Stop Removing Stopwords: How an Inherited Preprocessing Default Distorts Legal Text-as-Data](<https://devfeed.tech/articles/stop-removing-stopwords-how-an-inherited-preprocessing-default-distorts-legal-text-as-data-144926.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.19153>)

Author: Gregory M. Dickinson

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Data science and engineering](<https://devfeed.tech/topics/data-science-and-engineering.md>)

Tags: [ablation](<https://devfeed.tech/tags/ablation.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classifiers](<https://devfeed.tech/tags/classifiers.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [database](<https://devfeed.tech/tags/database.md>), [f1](<https://devfeed.tech/tags/f1.md>), [information-retrieval](<https://devfeed.tech/tags/information-retrieval.md>), [law](<https://devfeed.tech/tags/law.md>), [legal](<https://devfeed.tech/tags/legal.md>), [stop](<https://devfeed.tech/tags/stop.md>), [text](<https://devfeed.tech/tags/text.md>), [tf-idf](<https://devfeed.tech/tags/tf-idf.md>)

### AI overview

An exhaustive single-word ablation found no detectable benefit from stopword removal in two Supreme Court opinion classification tasks: ideological direction (7,668 opinions; baseline F1 about 0.68) and constitutional versus non-constitutional law type (7,001; about 0.92). The study tested roughly 18,500 words per task. Generic stoplists fell below the no-removal baseline in all twelve held-out tests; task-specific stoplists changed held-out F1 by only +0.0023 for ideology (95% CI −0.0124 to +0.0170) and +0.0001 for law type (−0.0082 to +0.0085). The authors argue that, in interpretable legal text-as-data pipelines, inherited preprocessing choices should be evaluated against the downstream objective because reshaping available features may alter the signal researchers aim to recover.

### Source excerpt

arXiv:2609.19153v3 Announce Type: replace-cross Abstract: Empirical legal scholarship increasingly treats judicial text as data, and much of it still runs on sparse, interpretable pipelines -- TF-IDF features and linear classifiers -- because the textual feature is often the object of study rather than a means to prediction. Yet these pipelines inherit preprocessing defaults from mid-century information retrieval that were never validated against classification accuracy. The most entrenched of these is stopword removal. This study introduces an exhaustive single word ablation that measures the effect of a preprocessing step directly against the downstream objective, and applies it to stopword removal as the hardest case to dislodge. Matching Supreme Court Database labels to Caselaw Access Project opinion texts, the study examines two binary tasks that bracket F1 headroom, ideological direction (no-removal baseline F1 ~0.68) and constitutional versus non-constitutional law type (~0.92), across 7,668 and 7,001 opinions. For each task, the ablation removes each of about 18,500 candidate words in turn, and a task-specific stoplist is built from the measurements. Common generic stoplists fall below the no-removal baseline in all twelve held-out tests. The task-specific stoplists move held-out F1 by +0.0023 (95% CI [-0.0124, +0.0170]) on ideology and by +0.0001 ([-0.0082, +0.0085]) on law type. Neither task shows a detectable benefit from removal, and supplemental analysis finds that word-level statistics predict removal effects poorly, because true removal effects differ by less than the measurement can register, leaving little to predict. The method generalizes to any inherited preprocessing default; the result is a caution specific to interpretable legal text-as-data, where a step that reshapes which features a model sees can distort the doctrinal and ideological signal the research is meant to recover. The burden of proof sits with removal.

## Revealing Pathway Interactions in Network Computations with Complete Path Contribution

DevFeed: [Revealing Pathway Interactions in Network Computations with Complete Path Contribution](<https://devfeed.tech/articles/revealing-pathway-interactions-in-network-computations-with-complete-path-contribution-145142.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26101>)

Author: Shenghua Liu, Youssef Faragalla, Surya Ganguli, Stephen A. Baccus

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [model architecture](<https://devfeed.tech/topics/model-architecture.md>), [Tool](<https://devfeed.tech/topics/tool.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [circuit](<https://devfeed.tech/tags/circuit.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [interaction](<https://devfeed.tech/tags/interaction.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mouse](<https://devfeed.tech/tags/mouse.md>), [network](<https://devfeed.tech/tags/network.md>), [q-bio-nc](<https://devfeed.tech/tags/q-bio-nc.md>)

### AI overview

Complete Path Contribution decomposes a network's output into mathematically complete contributions from individual input-to-output paths, enabling direct study of higher-order pathway interactions. Summing path contributions also defines complete contributions for circuits at different levels of granularity. An algorithm finds the k strongest paths without enumerating them all; its runtime was empirically linear in k rather than exponential in network depth. The authors apply the method to benchmark image classifiers to quantify excitatory and inhibitory interactions, and to an interpretable mouse-retina model, where it reveals pathway interaction motifs associated with dynamic receptive fields under time-varying natural stimuli.

### Source excerpt

arXiv:2611.26101v1 Announce Type: new Abstract: Networks pass signals through many layers of interconnected units, so explaining what they compute means tracing how information travels from input to output and how pathways interact. Most existing approaches analyze only pairwise interactions between components such as units, layers or attention heads. Even when these measurements are combined post hoc into a circuit, they do not capture higher-order interactions along full causal chains (paths) from input to output, and so cannot address how exponentially many paths interact to construct network computation. This leaves a large set of mechanistic questions unanswerable, for example whether inhibitory pathways veto excitatory ones, and how the two combine to yield network decisions. To address this gap, we introduce Complete Path Contribution, a method to decompose the network output into mathematically complete contributions of individual paths to study path-level interactions directly and at scale. Partial summation then induces definitions of contributions for any circuit at any granularity level, with completeness guaranteed at every level. We further present an efficient algorithm that identifies the $k$ strongest paths without examining all of them, with runtime empirically linear in $k$ rather than exponential in depth. By applying Path Contribution to benchmark image classification networks, we quantify excitatory-inhibitory interactions and show how they collectively construct network decisions at a level of detail previously unmeasurable. Furthermore, in an interpretable model of the mouse retina, it reveals how dynamic receptive fields emerge from excitatory-inhibitory interaction motifs among pathways between different cell types in response to time-varying natural stimuli. Overall, Path Contribution reveals how a network's causal pathways interact at scale to transform input to output.

## TabPFN: One Model to Rule Them All?

DevFeed: [TabPFN: One Model to Rule Them All?](<https://devfeed.tech/articles/tabpfn-one-model-to-rule-them-all-144854.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2505.20003>)

Author: Qiong Zhang, Yan Shuo Tan, Qinglong Tian, Pengfei Li

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Data science and engineering](<https://devfeed.tech/topics/data-science-and-engineering.md>), [model architecture](<https://devfeed.tech/topics/model-architecture.md>)

Tags: [application](<https://devfeed.tech/tags/application.md>), [bayesian-inference](<https://devfeed.tech/tags/bayesian-inference.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [foundation-model](<https://devfeed.tech/tags/foundation-model.md>), [learning](<https://devfeed.tech/tags/learning.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [stat-me](<https://devfeed.tech/tags/stat-me.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>), [tabpfn](<https://devfeed.tech/tags/tabpfn.md>), [tabular-data](<https://devfeed.tech/tags/tabular-data.md>)

### AI overview

The paper interprets TabPFN, a transformer for tabular regression and classification, as approximate Bayesian inference and examines its potential relevance to statistics. The authors report that out-of-the-box TabPFN sometimes outperforms specialized state-of-the-art methods in semi-supervised parameter estimation, prediction under covariate shift, and heterogeneous treatment effect estimation. They suggest one explanation is its ability to adapt to both nonparametric and parametric structure; in some experiments, it outperforms LASSO even when LASSO's assumptions are correctly specified. The evidence provided is an abstract, so it does not detail experimental setups or results.

### Source excerpt

arXiv:2505.20003v3 Announce Type: replace Abstract: Hollmann et al. (Nature 637 (2025) 319-326) recently introduced TabPFN, a transformer-based deep learning model for regression and classification on tabular data, which they claim "outperforms all previous methods on datasets with up to 10,000 samples by a wide margin, using substantially less training time." Furthermore, they have called TabPFN a "foundation model" for tabular data, as it can support "data generation, density estimation, learning reusable embeddings and fine-tuning". In this paper, we provide a tailored explanation of how TabPFN works for a statistics audience, by emphasizing its interpretation as approximate Bayesian inference. We then explore the significance of TabPFN to the field of statistics: We show that an out-of-the-box application of TabPFN can sometimes outperform specialized state-of-the-art methods for semi-supervised parameter estimation, prediction under covariate shift, and heterogeneous treatment effect estimation. As a partial explanation for the predictive effectiveness of TabPFN, we show that it can simultaneously adapt to both nonparametric structure and parametric structure, for instance, sometimes outperforming LASSO even when assumptions are correctly specified. All experiments can be reproduced using the code provided at https://github.com/qinglong-tian/tabpfn_study (https://github.com/qinglong-tian/tabpfn_study).

## VoxForge: A Unified Foundation Model for Dense 3D Features Across MRI, CT and PET

DevFeed: [VoxForge: A Unified Foundation Model for Dense 3D Features Across MRI, CT and PET](<https://devfeed.tech/articles/voxforge-a-unified-foundation-model-for-dense-3d-features-across-mri-ct-and-pet-145039.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25309>)

Author: Rushil Anirudh, Jayaraman J. Thiagarajan

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [Feature Engineering](<https://devfeed.tech/topics/feature-engineering.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [article](<https://devfeed.tech/tags/article.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [distillation](<https://devfeed.tech/tags/distillation.md>), [encoder](<https://devfeed.tech/tags/encoder.md>), [features](<https://devfeed.tech/tags/features.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [foundation-model](<https://devfeed.tech/tags/foundation-model.md>), [generalist](<https://devfeed.tech/tags/generalist.md>), [global](<https://devfeed.tech/tags/global.md>), [matching](<https://devfeed.tech/tags/matching.md>), [medical](<https://devfeed.tech/tags/medical.md>), [models](<https://devfeed.tech/tags/models.md>), [pet](<https://devfeed.tech/tags/pet.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [test](<https://devfeed.tech/tags/test.md>), [top](<https://devfeed.tech/tags/top.md>), [volumes](<https://devfeed.tech/tags/volumes.md>), [wide](<https://devfeed.tech/tags/wide.md>)

### AI overview

VoxForge is a single 3D encoder trained on permissively licensed MRI and CT volumes using 3D architecture advances, self-distillation, and cross-modal curricula. Evaluated with its features frozen, it achieves the best or tied-best average rank in every task group across segmentation, classification, and registration, including on PET, a modality absent from training. The abstract reports performance on localized and global tasks at the level of state-of-the-art specialists and says it matches top-performing models on TotalSegmentator CT using one tenth as many labels. The supplied text is an abstract, so it does not provide implementation details or per-task results.

### Source excerpt

arXiv:2611.25309v1 Announce Type: cross Abstract: A unified 3D medical foundation model promises reusable, frozen features that serve a wide variety of tasks such as segmentation, classification and registration on MRI, CT and PET as well as specialist models do. Generalist models still need separate backbones for localized and global tasks, specialist models are confined to a single modality, with the concern that spanning modalities under-emphasizes fine anatomy, and both typically rely on end-to-end fine-tuning to be competitive. We present VoxForge, a single encoder that integrates recent advances in 3D architecture, self-distillation and cross-modal curricula to learn transferable features from permissively licensed MRI and CT volumes. We evaluate it strictly frozen, the test a reusable foundation model must pass, against state-of-the-art generalist and specialist models on segmentation, classification and registration across MRI and CT, and on PET, which it never sees. VoxForge has the best or tied-best average rank in every task group, serves localized and global tasks across modalities at the level of state-of-the-art specialists, and is extremely label-efficient, matching top-performing models on TotalSegmentator CT with a tenth of the labels.

## LLMs Are Already Confidence-Aware Zero-Shot Classifiers

DevFeed: [LLMs Are Already Confidence-Aware Zero-Shot Classifiers](<https://devfeed.tech/articles/llms-are-already-confidence-aware-zero-shot-classifiers-145035.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25289>)

Author: Owen Cook, Xingyi Song

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [Uncertainty quantification LLMs](<https://devfeed.tech/topics/uncertainty-quantification-llms.md>), [Calibrated uncertainty](<https://devfeed.tech/topics/calibrated-uncertainty.md>)

Tags: [black-box](<https://devfeed.tech/tags/black-box.md>), [brier-score](<https://devfeed.tech/tags/brier-score.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classifier](<https://devfeed.tech/tags/classifier.md>), [classifiers](<https://devfeed.tech/tags/classifiers.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decode](<https://devfeed.tech/tags/decode.md>), [discrimination](<https://devfeed.tech/tags/discrimination.md>), [f1](<https://devfeed.tech/tags/f1.md>), [gemma](<https://devfeed.tech/tags/gemma.md>), [gemma-4](<https://devfeed.tech/tags/gemma-4.md>), [gemma-4-31b](<https://devfeed.tech/tags/gemma-4-31b.md>), [generation](<https://devfeed.tech/tags/generation.md>), [jev](<https://devfeed.tech/tags/jev.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [llms](<https://devfeed.tech/tags/llms.md>), [zero-shot](<https://devfeed.tech/tags/zero-shot.md>)

### AI overview

Across eleven open-weight LLMs and five classification datasets, confidence method choice rarely changed accuracy significantly, but token-probability logit scoring discriminated correct from incorrect predictions better than verbalised confidence or sampling (AUROC 0.74-0.77 vs. 0.57-0.66). Replacing labels with single-token identifiers preserved discrimination but reduced accuracy by 3-6 points on average. Decision-only scoring, which scores only positions where labels diverge in a prefix trie, cut decode steps by 88-96% on the three largest label sets while performing comparably to full-label scoring. The best tested open-weight configurations, Gemma 4 31B and Qwen 3.5 9B, were reported as competitive with Jev 1.13.0. These findings are from the supplied abstract.

### Source excerpt

arXiv:2611.25289v1 Announce Type: cross Abstract: Zero-shot large language models (LLMs) are increasingly used as text classifiers, but their labels are only useful when we know to what extent we can trust them. We compare black-box methods (verbalised confidence and sampling) with white-box methods that read token probabilities (P(True), and multiple logit-scoring methods using constrained generation). We evaluate eleven open-weight LLMs (1B-32B parameters) on five classification datasets with 3 to 151 labels, measuring classification performance (accuracy, F1-macro), discrimination (AUROC), and calibration (ECE and Brier score). The choice of confidence method rarely impacts accuracy significantly, but logit-based scoring methods lead to much better discrimination (AUROC 0.74-0.77) than black-box methods (AUROC 0.57-0.66). Replacing labels with single-token identifiers preserves discrimination but costs 3-6 accuracy points on average. We also introduce decision-only scoring, which only scores positions where labels diverge in the prefix tree (trie). It reduces decode steps by 88-96% on the three largest label sets and performs comparably to full-label scoring. The best open-weight model-method configurations (Gemma 4 31B and Qwen 3.5 9B) are competitive with the commercial Jev 1.13.0 classifier.

## Bio-PM-Guided Synthetic IMU Generation

DevFeed: [Bio-PM-Guided Synthetic IMU Generation](<https://devfeed.tech/articles/bio-pm-guided-synthetic-imu-generation-145200.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26607>)

Author: Deepali Singh, Deepesh Parpani, Aviral Gupta

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Feature Engineering](<https://devfeed.tech/topics/feature-engineering.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Occam's razor machine learning](<https://devfeed.tech/topics/occam-s-razor-machine-learning.md>)

Tags: [autoregressive](<https://devfeed.tech/tags/autoregressive.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classifier](<https://devfeed.tech/tags/classifier.md>), [conditional](<https://devfeed.tech/tags/conditional.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [decoder](<https://devfeed.tech/tags/decoder.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [encoder](<https://devfeed.tech/tags/encoder.md>), [f1](<https://devfeed.tech/tags/f1.md>), [feature](<https://devfeed.tech/tags/feature.md>), [generation](<https://devfeed.tech/tags/generation.md>), [gravity](<https://devfeed.tech/tags/gravity.md>), [imu](<https://devfeed.tech/tags/imu.md>), [measurement](<https://devfeed.tech/tags/measurement.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [models](<https://devfeed.tech/tags/models.md>), [raw](<https://devfeed.tech/tags/raw.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>)

### AI overview

The study generates synthetic IMU data in Bio-PM's representation space rather than directly as raw signals. It encodes 10-second windows with a frozen Bio-PM encoder and trains class-conditional autoregressive transformer and diffusion decoders; a PatchDecoder provides approximate waveform reconstruction. The diffusion model reaches 0.68 macro-F1 when trained on synthetic tokens and tested on real data. On WISDM across 51 subjects, combining synthetic-token augmentation with a 320-dimensional gravity-aware representation raises leave-one-subject-out macro-F1 from 0.729 to 0.809, with statistically significant gains concentrated in the hardest activity classes.

### Source excerpt

arXiv:2611.26607v1 Announce Type: new Abstract: Collecting and labeling inertial measurement unit (IMU) data for human activity recognition (HAR) is expensive, and models trained on one group of subjects often fail to generalize to unseen individuals. Even with balanced data, classifiers struggle to distinguish dynamically similar activity classes and benefit from targeted augmentation. We explore whether synthetic IMU data generated in the representation space of a pretrained biosignal encoder, Bio-PM \cite{b1}, can serve as a practical augmentation source. Rather than synthesizing raw signals, we leverage Bio-PM's frozen encoder to convert 10-second IMU windows into token embedding sequences and train class-conditional decoders in this space: (1) an autoregressive transformer decoder that predicts tokens sequentially, and (2) a diffusion decoder that learns the token distribution through a denoising objective. We analyze generation realism through distributional metrics and embedding-space visualizations, evaluate downstream utility through leave-one-subject-out HAR classification, and present a PatchDecoder for approximate raw waveform reconstruction. Our diffusion decoder achieves a Train-on-Synthetic-Test-on-Real (TSTR) macro-F1 of 0.68, demonstrating that generated tokens are realistic enough to train a classifier that transfers to real data. Combining synthetic-token augmentation with a 320-dimensional gravity-aware feature representation raises LOSO macro-F1 from 0.729 to 0.809 over a real-only baseline across 51 subjects on the WISDM benchmark, with statistically significant gains concentrated in the most challenging activity classes. These results demonstrate that high-fidelity generation in a pretrained encoder's representation space is achievable and practically useful for cross-subject HAR augmentation.

## ProtoSeam: Lifting Classifier Training with Latent Gaussian Mixture Models

DevFeed: [ProtoSeam: Lifting Classifier Training with Latent Gaussian Mixture Models](<https://devfeed.tech/articles/protoseam-lifting-classifier-training-with-latent-gaussian-mixture-models-144939.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.35174>)

Author: Robert Lampel, Timon Klein, Sebastian Sager

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [cifar-10](<https://devfeed.tech/topics/cifar-10.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classifier](<https://devfeed.tech/tags/classifier.md>), [consensus](<https://devfeed.tech/tags/consensus.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [inference](<https://devfeed.tech/tags/inference.md>), [interface](<https://devfeed.tech/tags/interface.md>), [models](<https://devfeed.tech/tags/models.md>), [network](<https://devfeed.tech/tags/network.md>), [prototype](<https://devfeed.tech/tags/prototype.md>), [resnet](<https://devfeed.tech/tags/resnet.md>), [test](<https://devfeed.tech/tags/test.md>), [theoretical](<https://devfeed.tech/tags/theoretical.md>), [training](<https://devfeed.tech/tags/training.md>), [transformer](<https://devfeed.tech/tags/transformer.md>)

### AI overview

ProtoSeam trains a classifier by splitting the network at a semantic interface and inserting one learnable prototype per class. A quadratic consensus penalty pulls each sample's representation toward its class prototype, while a classification loss trains the downstream network on samples drawn around the prototypes; gradients do not cross the interface. At inference, the prototypes are removed and the original network is used. On CIFAR-10, CIFAR-100, and TinyImageNet with ResNet and vision transformer backbones, the authors report test accuracy gains of up to six percentage points over variants without lifting under a shared tuning protocol. The abstract also says the results have theoretical justification.

### Source excerpt

arXiv:2609.35174v2 Announce Type: replace Abstract: We propose a lifted reformulation of supervised classification that improves the final accuracy of standard classifiers without changing the architecture at inference time. A network $N=N_2\circ N_1$ is split at a single semantic interface and one learnable prototype per class is inserted there. Training combines a quadratic consensus penalty that pulls $N_1(x)$ toward the prototype of its class with a classification loss of $N_2$ evaluated on samples drawn around the prototypes, while no gradient crosses the interface. At inference the prototypes are discarded and the unmodified network $N_2\circ N_1$ is used. Across CIFAR-10, CIFAR-100, and TinyImageNet with ResNet and vision transformer backbones, lifted training improves test accuracy by up to six percentage points over variants without lifting under a shared tuning protocol. Moreover, we provide theoretical justification of those results.

## ICARE: cross-domain text classification with incremental class-aware representation and distillation learning

DevFeed: [ICARE: cross-domain text classification with incremental class-aware representation and distillation learning](<https://devfeed.tech/articles/icare-cross-domain-text-classification-with-incremental-class-aware-representation-and-distillation-learning-144992.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24959>)

Author: Son Duong, Truong X. Tran, Hai-Anh Tran

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [text-classification](<https://devfeed.tech/topics/text-classification.md>), [Multitask learning](<https://devfeed.tech/topics/multitask-learning.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Post-training optimization](<https://devfeed.tech/topics/post-training-optimization.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [distillation](<https://devfeed.tech/tags/distillation.md>), [domain](<https://devfeed.tech/tags/domain.md>), [framework](<https://devfeed.tech/tags/framework.md>), [incremental](<https://devfeed.tech/tags/incremental.md>), [inference](<https://devfeed.tech/tags/inference.md>), [knowledge-transfer](<https://devfeed.tech/tags/knowledge-transfer.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [learning](<https://devfeed.tech/tags/learning.md>), [llms](<https://devfeed.tech/tags/llms.md>), [news](<https://devfeed.tech/tags/news.md>), [overfitting](<https://devfeed.tech/tags/overfitting.md>), [pruning](<https://devfeed.tech/tags/pruning.md>), [representation-learning](<https://devfeed.tech/tags/representation-learning.md>), [sentiment-analysis](<https://devfeed.tech/tags/sentiment-analysis.md>), [text-classification](<https://devfeed.tech/tags/text-classification.md>)

### AI overview

ICARE aims to reduce catastrophic forgetting in continual text classification by combining representation-based instance selection with knowledge distillation across tasks. Its distillation transfers feature-level and logit-level knowledge using pruning techniques and optimized objectives. The abstract reports improved target accuracy and a lower forgetting metric on benchmark text classification datasets, but provides no dataset names, numerical results, or detailed comparison baselines.

### Source excerpt

arXiv:2611.24959v1 Announce Type: cross Abstract: The rise of powerful, fine-tuned large language models (LLMs) necessitates robust natural language inference (NLI) systems. These NLI systems ideally train across various tasks, encompassing diverse concepts like sentiment analysis, news classification, and coreference resolution. However, this continual, multi-tasking approach can lead to catastrophic forgetting, where previously learned tasks are lost, especially in domains lacking specific labels. Rehearsing past examples with labels can further exacerbate this issue by causing overfitting, hindering the system's ability to classify new categories. To tackle these challenges, this research proposes ICARE, a novel framework with two key components: an instance selection module and a knowledge distillation method. The former is based on representation learning, which meticulously selects training examples to present to the NLI system. The latter, knowledge distillation with feature and logit-level transfer, facilitates knowledge transfer between tasks. This leverages pruning techniques and optimized objective functions to transfer both essential feature-level and decision-making (logit-level) knowledge, mitigating catastrophic forgetting while adapting to new patterns. Extensive evaluations on benchmark text classification datasets have demonstrated ICARE's effectiveness. The framework achieves a significant improvement in target accuracy and reduction in the ``forgetting metric''. These results solidify ICARE's ability to preserve and leverage learned knowledge across diverse tasks, ultimately enhancing the adaptability and performance of NLI systems. The source code is available at https://github.com/CongSon01/ICARE_NLP.git

## Provable Compliance: A Protocol for Runtime Compliance Evidence and Transaction-Specific Decisioning

DevFeed: [Provable Compliance: A Protocol for Runtime Compliance Evidence and Transaction-Specific Decisioning](<https://devfeed.tech/articles/provable-compliance-a-protocol-for-runtime-compliance-evidence-and-transaction-specific-decisioning-146010.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.22913>)

Author: Jeremy Blackburn, Tim Hines, Matthew Koepp, Russell Lessard, Jason Patrick

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [audit](<https://devfeed.tech/topics/audit.md>), [business logic](<https://devfeed.tech/topics/business-logic.md>), [rule-engine](<https://devfeed.tech/topics/rule-engine.md>), [Protocol (disambiguation)](<https://devfeed.tech/topics/protocol.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [agents](<https://devfeed.tech/tags/agents.md>), [aml](<https://devfeed.tech/tags/aml.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [atomic](<https://devfeed.tech/tags/atomic.md>), [background](<https://devfeed.tech/tags/background.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [business](<https://devfeed.tech/tags/business.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [changes](<https://devfeed.tech/tags/changes.md>), [classification](<https://devfeed.tech/tags/classification.md>), [commit](<https://devfeed.tech/tags/commit.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [transaction](<https://devfeed.tech/tags/transaction.md>)

### AI overview

ChainIT Provable Compliance packages transaction-specific compliance evidence into an attributable decision for a single reliance event. Separate Evidence Assertion VDTs record each fact's provenance, freshness, confidence, permitted purpose, and privacy classification; a versioned policy profile selects rules, a business rules engine returns deterministic reason-coded results, and the configured workflow engine composes them into a signed, time-bounded Compliance Decision VDT. That decision supplies one predicate to session eligibility and transaction policy. It does not authorize payment: value can be committed only with a final Allow, an exact transaction digest, an atomic capacity reservation, and a single-use execution credential. The abstract also identifies freshness at reliance, scoped updates when evidence changes, privacy controls, evidence domains, and residual risks; it does not provide their full specifications.

### Source excerpt

arXiv:2610.22913v2 Announce Type: replace Abstract: Regulated institutions already perform onboarding, screening, monitoring, and review, but compliance evidence ages, and whether it supports a decision depends on the institution, product, subject, counterparty, transaction, jurisdiction, risk tier, and purpose. A relying party therefore often cannot obtain compact, attributable proof of which evidence, policy, authority, and transaction context were current when a decision was made, a gap that grows as authority is delegated to software agents and scheduled workflows. We describe ChainIT Provable Compliance, the compliance-side layer of the ChainIT Authority Protocol. Each sourced or institution-generated fact is represented as a separate Evidence Assertion VDT with provenance, freshness, confidence, permitted purpose, and privacy classification; a versioned Compliance Policy Profile selects the applicable rules; a Business Rules Engine returns deterministic, reason-coded predicate results; and the organization's configured Workflow Engine composes them into a signed, time-bounded Compliance Decision VDT for one reliance event. The decision contributes a single predicate, Compliance Decision Permits, to session-eligibility and transaction-policy decisions. It never independently authorizes payment: only a final Allow together with an exact transaction digest, atomic capacity reservation, and a single-use execution credential can commit value. The paper specifies point-of-reliance freshness, scoped propagation of evidence changes, decision states, evidence domains (AML, sanctions, PEP, background, identity, and licensing), the U.S. and FATF regulatory context as of August 2026, privacy and disclosure controls, and residual risks.

## Multi-institutional grading of Barrett's esophagus dysplasia without stain normalization using a pathology foundation model and multiple instance learning

DevFeed: [Multi-institutional grading of Barrett's esophagus dysplasia without stain normalization using a pathology foundation model and multiple instance learning](<https://devfeed.tech/articles/multi-institutional-grading-of-barrett-s-esophagus-dysplasia-without-stain-normalization-using-a-pathology-foundation-model-and-multiple-instance-learning-145686.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26562>)

Author: Amirali Khosravi, Jaidip M. Jagtap, D. Chamil Codipilly, Catherine E. Hagen, Jason T. Lewis, Rickey E. Carter, Shahriar Faghani, Vani J. A. Konda, Fouad Otaki, Shajan Peter, Nicholas Shaheen, Sachin W

Published: 2026-11-20T05:00:00Z

Content type: news

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Model Development](<https://devfeed.tech/topics/model-development.md>)

Tags: [based](<https://devfeed.tech/tags/based.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classifiers](<https://devfeed.tech/tags/classifiers.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [diagnostic](<https://devfeed.tech/tags/diagnostic.md>), [foundation-model](<https://devfeed.tech/tags/foundation-model.md>), [institutions](<https://devfeed.tech/tags/institutions.md>), [learning](<https://devfeed.tech/tags/learning.md>), [patch](<https://devfeed.tech/tags/patch.md>), [performance](<https://devfeed.tech/tags/performance.md>), [study](<https://devfeed.tech/tags/study.md>)

### AI overview

In a retrospective study of 969 H&E whole-slide images from four institutions, a foundation-model system graded Barrett's esophagus as non-dysplastic, low-grade, or high-grade dysplasia. Expert-annotated patch classifiers first identified relevant regions; attribute-aware multiple instance learning then produced slide-level classifications. On a held-out set of 130 slides, macro-averaged AUC was 0.96 (95% CI 0.93-0.98). For binary dysplasia detection, sensitivity was 98% and specificity 81%; no high-grade case was labeled non-dysplastic. Performance was consistent across institutions without stain normalization, suggesting the approach may reduce site-specific preprocessing needs. These are retrospective diagnostic-accuracy results, not evidence of clinical outcome benefit.

### Source excerpt

arXiv:2611.26562v1 Announce Type: cross Abstract: Barrett's esophagus dysplasia grading suffers substantial inter-observer variability, particularly for low-grade dysplasia, complicating clinical decision-making. We conducted a retrospective multi-institutional diagnostic accuracy study of a foundation model-based deep learning system for dysplasia grading, using 969 H\&E-stained whole slide images from four institutions. Patch-level classifiers trained on expert annotations identified diagnostically relevant regions, followed by attribute-aware multiple instance learning for slide-level classification as non-dysplastic Barrett's esophagus (NDBE), low-grade dysplasia, or high-grade dysplasia. On a held-out test set (n = 130), macro-averaged AUC was 0.96 (95\% CI 0.93--0.98). For binary dysplasia detection, sensitivity was 98\% (80/82) and specificity 81\% (39/48), with a negative likelihood ratio of 0.030 and quadratic-weighted \kap{} of 0.83 against expert consensus. No high-grade dysplasia case was misclassified as NDBE. Performance was consistent across institutions without stain normalization, indicating that stain-robust foundation-model representations may remove the site-specific preprocessing that has constrained prior systems to institution-specific deployment.

## C-LiTE: A Lightweight Foundation Model for Cellular feature learning in Histopathology

DevFeed: [C-LiTE: A Lightweight Foundation Model for Cellular feature learning in Histopathology](<https://devfeed.tech/articles/c-lite-a-lightweight-foundation-model-for-cellular-feature-learning-in-histopathology-145653.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26316>)

Author: Esha Sadia Nasir, Jiaqi Lv, Gozde N. Gunesli, Shan E Ahmed Raza

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Training AI Models](<https://devfeed.tech/topics/training-ai-models.md>), [Dataset development](<https://devfeed.tech/topics/dataset-development.md>), [image recognition](<https://devfeed.tech/topics/image-recognition.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>)

Tags: [cellular](<https://devfeed.tech/tags/cellular.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [f1](<https://devfeed.tech/tags/f1.md>), [features](<https://devfeed.tech/tags/features.md>), [fewer](<https://devfeed.tech/tags/fewer.md>), [figure](<https://devfeed.tech/tags/figure.md>), [foundation-model](<https://devfeed.tech/tags/foundation-model.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [native](<https://devfeed.tech/tags/native.md>), [public](<https://devfeed.tech/tags/public.md>), [representation-learning](<https://devfeed.tech/tags/representation-learning.md>), [token](<https://devfeed.tech/tags/token.md>), [training-dataset](<https://devfeed.tech/tags/training-dataset.md>), [transformation](<https://devfeed.tech/tags/transformation.md>), [type](<https://devfeed.tech/tags/type.md>), [vit](<https://devfeed.tech/tags/vit.md>)

### AI overview

C-LiTE is a 22-million-parameter model for learning cellular features from H&E histopathology images. It processes 64x64-pixel cell-centred crops at native resolution, using 4x4-pixel patches to form a 16x16 token grid without upsampling; its patch embedding is initialized by adapting weights from a pre-trained ViT-5-S with a pseudoinverse-based transformation. The model is pre-trained on 60 million TCGA cell crops balanced across 19 cancer types and 16 tissue types. Across seven public datasets for mitotic figure recognition, nucleus and cell-type classification, and immune-cell phenotyping, frozen-feature evaluation yields mean macro-F1 0.670, close to CytoFormer's 0.682 with about 30 times fewer parameters. These findings are limited to the reported evaluation setting.

### Source excerpt

arXiv:2611.26316v1 Announce Type: cross Abstract: Characterising individual cells is fundamental to computational pathology, as cellular morphology informs tasks such as tumour grading, mitotic assessment and immune profiling. However, most pathology foundation models are trained on tissue patches and capture cellular features only implicitly, while existing cell-level models are either restricted to specific cell populations or rely on computationally expensive architectures with hundreds of millions of parameters. Applying ViTs directly to small cellular crops also presents an architectural challenge: upsampling increases computational cost without adding morphological information and may introduce interpolation artefacts. To address these limitations, we introduce C-LiTE, a lightweight foundation model for cellular representation learning in H&E-stained histopathology, with only 22 million parameters. C-LiTE employs a native-resolution tokenisation strategy tailored to cellular inputs, processing 64 x 64 px cell-centred crops using a 4 x 4 patch embedding to produce a 16 x 16 token grid without image upsampling. To transfer visual knowledge from large-scale pre-training, we adapt the patch embedding weights of a pre-trained ViT-5-S using a pseudoinverse-based transformation, enabling weight initialisation at the finer patch resolution. We further assemble a pre-training dataset of 60 million cell-centred crops from TCGA, balanced across 19 cancer types and 16 tissue types. To our knowledge, this represents the largest public dataset for self-supervised pre-training on H&E images at the cellular level. We evaluate C-LiTE on seven public datasets spanning mitotic figure recognition, nucleus and cell-type classification, and immune cell phenotyping. Under frozen-feature evaluation, C-LiTE achieves a mean macro-F1 of 0.670, approaching CytoFormer (0.682) with approximately 30x fewer parameters.

## Class-Conditional Conformal Triage for ICAO Face-Image Compliance under Class Imbalance

DevFeed: [Class-Conditional Conformal Triage for ICAO Face-Image Compliance under Class Imbalance](<https://devfeed.tech/articles/class-conditional-conformal-triage-for-icao-face-image-compliance-under-class-imbalance-145045.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25342>)

Author: Mustafa Vedat Yildirim, Inna Skarga-Bandurova

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Image](<https://devfeed.tech/topics/image.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [classification](<https://devfeed.tech/tags/classification.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [conditional](<https://devfeed.tech/tags/conditional.md>), [conformal-prediction](<https://devfeed.tech/tags/conformal-prediction.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [false-positive](<https://devfeed.tech/tags/false-positive.md>), [image](<https://devfeed.tech/tags/image.md>), [images](<https://devfeed.tech/tags/images.md>), [layer](<https://devfeed.tech/tags/layer.md>), [performance](<https://devfeed.tech/tags/performance.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [reduction](<https://devfeed.tech/tags/reduction.md>), [triage](<https://devfeed.tech/tags/triage.md>), [uncertainty](<https://devfeed.tech/tags/uncertainty.md>)

### AI overview

The study evaluates conformal prediction as an uncertainty-based triage layer for BioGaze's 14 ICAO/ISO face-image criteria, using synthetic TONO data and subject-disjoint splits without retraining the analyser. Marginal conformal prediction reached about 0.90 overall coverage but under-covered violations (as low as a 0.37 ten-partition mean for one criterion). Mondrian class-conditional coverage means were 0.89-0.92 across criteria. Most criterion-level false-positive reduction came from adding per-criterion logistic classifiers (0.145 to 0.048); tuned abstention rules had lower false-positive rates than Mondrian at comparable retake rates. Bonferroni correction for joint coverage across all 14 criteria required retaking nearly every image, exposing a trade-off between coverage guarantees and practical retake burden.

### Source excerpt

arXiv:2611.25342v1 Announce Type: new Abstract: Automated ICAO/ISO face-image compliance analysers provide criterion-level pass/fail decisions, yet these verdicts do not quantify uncertainty when deciding whether to accept, reject, or retake a photograph. We investigate conformal prediction as a triage layer for BioGaze, evaluating 14 compliance criteria on the synthetic TONO benchmark. Without retraining the analyser, we fit per-criterion logistic classifiers and compare marginal and label-conditional (Mondrian) conformal prediction with conventional abstention rules using subject-disjoint splits. Marginal conformal prediction achieved approximately 0.90 overall coverage but substantially under-covered violations, with a ten-partition mean of 0.37 for one criterion. The corresponding Mondrian means ranged from 0.89 to 0.92 across criteria. However, most of the reduction in criterion-level false positives came from the logistic layer (0.145 to 0.048), while tuned abstention rules achieved lower false-positive rates than Mondrian at comparable retake rates. Bonferroni correction for joint coverage across 14 criteria required retaking nearly all images. These findings show that class-conditional conformal prediction can achieve near-target empirical coverage for minority violation classes and reveal trade-offs between statistical coverage, classification performance, and retake requirements in multi-criterion face-image compliance assessment.

## Ask in the Crowd: Differentially Private LLM Inference via Dummy-Augmented Shuffling

DevFeed: [Ask in the Crowd: Differentially Private LLM Inference via Dummy-Augmented Shuffling](<https://devfeed.tech/articles/ask-in-the-crowd-differentially-private-llm-inference-via-dummy-augmented-shuffling-145566.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25669>)

Author: Zhihao Liu, Zixiong Guo, Shuo Shao, Yu He, Wenli Wang, Meihui Chen, Di Wang, Yuke Hu

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [LLM security](<https://devfeed.tech/topics/llm-security.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [balance](<https://devfeed.tech/tags/balance.md>), [cache](<https://devfeed.tech/tags/cache.md>), [classification](<https://devfeed.tech/tags/classification.md>), [client](<https://devfeed.tech/tags/client.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [decoding](<https://devfeed.tech/tags/decoding.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generation](<https://devfeed.tech/tags/generation.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [inference](<https://devfeed.tech/tags/inference.md>), [inference-efficiency](<https://devfeed.tech/tags/inference-efficiency.md>), [inference-framework](<https://devfeed.tech/tags/inference-framework.md>), [input](<https://devfeed.tech/tags/input.md>), [kv-cache](<https://devfeed.tech/tags/kv-cache.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-inference](<https://devfeed.tech/tags/llm-inference.md>), [private](<https://devfeed.tech/tags/private.md>)

### AI overview

DP-SPD hides a user's real query among client-generated dummy queries, shuffles the queries before sending them to the LLM server, and reuses transformer key-value caches for queries with shared prefixes during decoding. The paper analyzes its privacy guarantee and evaluates classification and generation utility and protection against QIA, EIA, and GPT-based attacks. The abstract reports strong inference-time privacy, near-plaintext utility, and improved efficiency, but gives no quantitative results or implementation details.

### Source excerpt

arXiv:2611.25669v1 Announce Type: new Abstract: Large language models are increasingly deployed as LLM-as-a-Service (LLMaaS), where user queries are sent to remote LLMs for inference, raising severe privacy concerns about the exposure of sensitive user inputs. Differentially private inference mitigates these risks by injecting noise into input embeddings. However, existing methods struggle to balance privacy and utility, as stronger privacy protection often leads to substantial accuracy degradation in LLM inference. In this work, we propose DP-SPD, a differentially private LLM inference framework that protects user queries by hiding the real query among client-generated dummy queries. All queries are randomly shuffled before being sent to the server, preventing direct identification of the user's true intent. To improve inference efficiency, we exploit the shared-prefix structure among queries and reuse transformer key--value (KV) caches during decoding. We analyze the privacy guarantee of DP-SPD and evaluate its utility on classification and generation tasks, as well as its privacy protection under QIA, EIA, and GPT-based attacks. Experimental results show that our method achieves strong inference-time privacy protection and near-plaintext utility while improving inference efficiency through shared-prefix KV-cache reuse.

## ShapleyPipe: A Game-Theoretic Approach to Data Preparation Pipeline Construction

DevFeed: [ShapleyPipe: A Game-Theoretic Approach to Data Preparation Pipeline Construction](<https://devfeed.tech/articles/shapleypipe-a-game-theoretic-approach-to-data-preparation-pipeline-construction-145728.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2510.27168>)

Author: Jing Chang, Shuyuan Zheng, Jinbin Huang, Chang Liu, Jianbin Qin

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Advanced AI workflows](<https://devfeed.tech/topics/advanced-ai-workflows.md>), [Feature Engineering](<https://devfeed.tech/topics/feature-engineering.md>)

Tags: [automated](<https://devfeed.tech/tags/automated.md>), [classification](<https://devfeed.tech/tags/classification.md>), [coherence](<https://devfeed.tech/tags/coherence.md>), [construction](<https://devfeed.tech/tags/construction.md>), [contribution](<https://devfeed.tech/tags/contribution.md>), [contributions](<https://devfeed.tech/tags/contributions.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [data-preparation](<https://devfeed.tech/tags/data-preparation.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [framework](<https://devfeed.tech/tags/framework.md>), [frontier](<https://devfeed.tech/tags/frontier.md>), [game](<https://devfeed.tech/tags/game.md>), [machine](<https://devfeed.tech/tags/machine.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [practical](<https://devfeed.tech/tags/practical.md>), [rank](<https://devfeed.tech/tags/rank.md>), [records](<https://devfeed.tech/tags/records.md>), [reduce](<https://devfeed.tech/tags/reduce.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [transformation](<https://devfeed.tech/tags/transformation.md>)

### AI overview

ShapleyPipe builds data preparation pipelines by estimating each operator's position-dependent contribution to downstream model utility. Its Pipeline Shapley value distinguishes repeated uses of the same operator type, and the framework selects and orders operators using those contributions. Hierarchical ShapleyPipe (H-SP) makes the approach more practical through representative selection based on a Category Coherence Assumption and adaptive early termination. Across 27 classification datasets, H-SP reports the highest average accuracy (0.847) and best average rank among evaluated practical methods, on the empirical accuracy-runtime Pareto frontier. On three datasets with up to 581K records, searching 10K subsamples with 16 workers averaged 891 seconds and accuracy of 0.705.

### Source excerpt

arXiv:2510.27168v2 Announce Type: replace Abstract: Data preparation is a critical yet highly time-consuming component of machine learning (ML) workflows and has a substantial impact on downstream model performance. Automated data preparation pipeline construction requires selecting appropriate operators, such as missing-value imputation, feature scaling, and feature transformation, and placing them at suitable pipeline positions. However, existing methods lack a principled and interpretable mechanism for understanding the marginal contribution of each operator at a specific position. To address this limitation, we study data preparation pipeline construction from a cooperative game-theoretic perspective. We formulate the task as a pipeline construction game, in which operators act as players that cooperatively improve downstream model utility. Based on this formulation, we propose the Pipeline Shapley value (PipeShapley), a contribution-attribution method that explicitly captures position-dependent contributions and distinguishes repeated occurrences of the same operator type. Building on PipeShapley, we introduce ShapleyPipe, an interpretable pipeline construction framework that selects and orders operators according to their position-aware contributions. To make PipeShapley practical, we develop Hierarchical ShapleyPipe (H-SP) based on a Category Coherence Assumption to exploit coherent contribution patterns, combining MAB-based representative selection with adaptive early termination. Experiments on 27 classification datasets show that H-SP achieves the highest average accuracy of 0.847 and the best average rank among the evaluated practical methods, while lying on the empirical accuracy--runtime Pareto frontier. On three datasets with up to 581K records, 10K-subsample search and 16-worker parallel execution reduce the average wall-clock time to 891 seconds while retaining the highest average accuracy of 0.705.

## Phantom of the Masquerade: Graph Neural Network-Based Detection of Masquerade Attacks in Controller Area Networks

DevFeed: [Phantom of the Masquerade: Graph Neural Network-Based Detection of Masquerade Attacks in Controller Area Networks](<https://devfeed.tech/articles/phantom-of-the-masquerade-graph-neural-network-based-detection-of-masquerade-attacks-in-controller-area-networks-145139.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26094>)

Author: Nehal Ameen, Pablo Moriano, Irfan Ahmed

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Cybersecurity](<https://devfeed.tech/topics/cybersecurity.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [network security](<https://devfeed.tech/topics/network-security.md>)

Tags: [attacks](<https://devfeed.tech/tags/attacks.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [can](<https://devfeed.tech/tags/can.md>), [classification](<https://devfeed.tech/tags/classification.md>), [controller](<https://devfeed.tech/tags/controller.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [detection](<https://devfeed.tech/tags/detection.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [features](<https://devfeed.tech/tags/features.md>), [gnn](<https://devfeed.tech/tags/gnn.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [intrusion-detection](<https://devfeed.tech/tags/intrusion-detection.md>), [latency](<https://devfeed.tech/tags/latency.md>), [learning](<https://devfeed.tech/tags/learning.md>), [network](<https://devfeed.tech/tags/network.md>), [networks](<https://devfeed.tech/tags/networks.md>), [neural](<https://devfeed.tech/tags/neural.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>)

### AI overview

PhantoMasq detects masquerade attacks in CAN traffic by representing message sequences as graphs enriched with lightweight signal-behavior statistics, then classifying each graph with a graph convolutional network. On the ROAD dataset, evaluated with overlapping windows kept from crossing the train-test boundary, it achieved mean AUC-ROC from 0.831 to 0.999 across five attack types; performance varied with the targeted identifier's transmission rate and the size of the signal deviation. Against a graph-embedding baseline on the same window configurations, it scored 0.13-0.36 higher in AUC-ROC for every attack type and was less sensitive to window configuration. CPU processing took 2.33-5.94 ms per window (168-429 windows per second).

### Source excerpt

arXiv:2611.26094v1 Announce Type: cross Abstract: The lack of built-in security in controller area networks (CANs) exposes modern vehicles and industrial systems to masquerade attacks that can compromise safety and reliability. These attacks inject malicious messages that mimic legitimate communication patterns, making them difficult to detect using existing intrusion detection systems (IDS). Prior graph-based IDS approaches often rely on shallow embeddings that decouple representation learning from classification, which may limit their ability to fully exploit structural and signal-level information. In this paper, we propose PhantoMasq, a graph neural network (GNN)-based framework for detecting masquerade attacks in CAN systems. PhantoMasq models CAN traffic as message sequence graphs enriched with lightweight statistical features derived from signal behavior, enabling joint learning of structural dependencies and temporal characteristics. The detection task is formulated as a graph-level classification problem and solved using graph convolutional networks (GCNs). We evaluate PhantoMasq on the ROAD dataset under a protocol that prevents overlapping windows from spanning training and test data. Across five masquerade attack types, PhantoMasq achieves mean AUC-ROC between 0.831 and 0.999, with performance depending on the transmission rate of the targeted identifier and the magnitude of the induced signal deviation. Against a state-of-the-art graph-embedding baseline evaluated on the same sliding-window configurations, PhantoMasq achieves higher AUC-ROC on all five attack types, by 0.13 to 0.36, and is less sensitive to window configuration. Window-processing latency ranges from 2.33 to 5.94 ms per window on CPU, corresponding to a throughput of 168 to 429 windows per second. We make our implementation and experimental artifacts available to support reproducibility.

## Loss-Guided Tsetlin Machines: Making the Learning Objective Explicit

DevFeed: [Loss-Guided Tsetlin Machines: Making the Learning Objective Explicit](<https://devfeed.tech/articles/loss-guided-tsetlin-machines-making-the-learning-objective-explicit-145145.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26114>)

Author: Mayur Shende, Runar Helin, Ole-Christoffer Granmo, Vladimir I. Zadorozhny

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Model Development](<https://devfeed.tech/topics/model-development.md>), [Calibrated uncertainty](<https://devfeed.tech/topics/calibrated-uncertainty.md>)

Tags: [classification](<https://devfeed.tech/tags/classification.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [interpretability](<https://devfeed.tech/tags/interpretability.md>), [loss-functions](<https://devfeed.tech/tags/loss-functions.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>)

### AI overview

Loss-Guided Tsetlin Machines replace the fixed, implicit margin-based update rule with a swappable explicit loss that drives clause feedback and weight updates, while leaving the Tsetlin Automaton and clause logic unchanged. The paper evaluates cross entropy (CE), symmetric cross entropy (SCE), and asymmetric loss (ASL) on six multiclass, multilabel, and binary classification datasets. With a suitable loss, accuracy and F1 match or exceed the baseline on five datasets; ASL improves macro F1 by up to 9 percentage points on imbalanced multilabel data. CE reduces calibration error by a factor of 3 to 11 across all six datasets. A qualitative per-class inspection on image and text data reports that clause-based global interpretability is preserved.

### Source excerpt

arXiv:2611.26114v1 Announce Type: new Abstract: The Tsetlin Machine (TM) has no explicit notion of a loss function. Its learning signal is fixed to an implicit, margin-based update rule (MBUR), with no way to choose an objective function suited to a specific task. This paper introduces Loss-Guided TM, which replaces MBUR with an explicit and swappable loss function. In our proposed method, clause feedback and weight updates are driven by the loss, while keeping the Tsetlin Automaton and clause logic unchanged. The approach incorporates cross entropy (CE), symmetric cross entropy (SCE), and asymmetric loss (ASL). We evaluate Loss-Guided TM across six datasets that span multiclass, multilabel, and binary classification tasks. With a suitable loss, Loss-Guided TM matches or improves accuracy and F1 over MBUR on five of the six datasets. The gains are greatest for the imbalanced multilabel datasets, where ASL improves macro F1 by up to 9 percentage points. With CE, Loss-Guided TM is also significantly better calibrated than MBUR on all six datasets, reducing calibration error by a factor of 3 to 11. A qualitative inspection shows that the clause-based global interpretability, examined at the per-class level on image and text data, is preserved when using the Loss-Guided mechanism. These results show that our explicit TM learning objective allows direct targeting of uncertainty calibration, data imbalance, and task structure, opening the TM to the broader literature on loss functions.

## Learning to Defer under Expert Drift

DevFeed: [Learning to Defer under Expert Drift](<https://devfeed.tech/articles/learning-to-defer-under-expert-drift-145181.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26440>)

Author: Ziyao Mou, Andrea Wynn, Eric Nalisnick

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [annotation](<https://devfeed.tech/tags/annotation.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [aviation](<https://devfeed.tech/tags/aviation.md>), [classification](<https://devfeed.tech/tags/classification.md>), [code](<https://devfeed.tech/tags/code.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [defer](<https://devfeed.tech/tags/defer.md>), [detection](<https://devfeed.tech/tags/detection.md>), [diagnosis](<https://devfeed.tech/tags/diagnosis.md>), [drift](<https://devfeed.tech/tags/drift.md>), [eda](<https://devfeed.tech/tags/eda.md>), [effective](<https://devfeed.tech/tags/effective.md>), [effectively](<https://devfeed.tech/tags/effectively.md>), [everyday](<https://devfeed.tech/tags/everyday.md>), [learning](<https://devfeed.tech/tags/learning.md>)

### AI overview

EDA-L2D adapts learning-to-defer policies to changing human-expert reliability by conditioning the deferral head on recent expert outcomes through a sequence model. The paper evaluates it on image classification, medical diagnosis, and hate speech detection, including generalization under realistic deferral conditions and irregular reliability shifts. The authors report that it adapts more effectively than prior L2D methods across diverse temporal patterns, improving system performance and deferral decisions. The supplied text does not provide quantitative results or implementation details.

### Source excerpt

arXiv:2611.26440v1 Announce Type: new Abstract: The learning to defer (L2D) framework enables safety in machine learning and AI systems by allocating difficult or critical decisions to a human expert. However, most prior work on L2D assumes fixed expert reliability, overlooking temporal fluctuations in human performance due to factors such as fatigue and cognitive biases. Humans commonly exhibit such substantial, systematic performance shifts across a wide range of domains, from high-stakes settings such as radiology, aviation, and judicial decision-making, to everyday tasks such as crowdsourced image annotation. We propose Expert-Drift-Adapted Learning-to-Defer (EDA-L2D), a novel expert-aware L2D framework that explicitly models these temporal shifts by conditioning the deferral head on recent histories of expert outcomes via a sequence model. This history-aware approach enables adaptive deferral policies that anticipate reliability fluctuations and better allocate decisions between human and machine over time. We provide comprehensive experiments across three diverse tasks -- image classification, medical diagnosis, and hate speech detection -- including generalization analyses under realistic deferral conditions and irregular shifts in expert reliability. Our results show that EDA-L2D adapts more effectively than prior L2D methods to diverse temporal patterns of expert reliability, resulting in improved system performance and more effective deferral decisions. Code is available at https://github.com/ZiyaoMou/L2D-Expert-Drift.

## Where Global Context and Weight Sharing Work in Compact Vision Backbones

DevFeed: [Where Global Context and Weight Sharing Work in Compact Vision Backbones](<https://devfeed.tech/articles/where-global-context-and-weight-sharing-work-in-compact-vision-backbones-142656.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23446>)

Author: Michael Schroeder

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [image recognition](<https://devfeed.tech/topics/image-recognition.md>), [ImageNet](<https://devfeed.tech/topics/imagenet.md>)

Tags: [attention](<https://devfeed.tech/tags/attention.md>), [batchnorm](<https://devfeed.tech/tags/batchnorm.md>), [block](<https://devfeed.tech/tags/block.md>), [blocks](<https://devfeed.tech/tags/blocks.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [classification](<https://devfeed.tech/tags/classification.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [convolution](<https://devfeed.tech/tags/convolution.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [efficientnet](<https://devfeed.tech/tags/efficientnet.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [global](<https://devfeed.tech/tags/global.md>), [global-context](<https://devfeed.tech/tags/global-context.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [scale](<https://devfeed.tech/tags/scale.md>), [self-attention](<https://devfeed.tech/tags/self-attention.md>), [sharing](<https://devfeed.tech/tags/sharing.md>), [stage](<https://devfeed.tech/tags/stage.md>), [vision](<https://devfeed.tech/tags/vision.md>), [weight](<https://devfeed.tech/tags/weight.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

Controlled EfficientNet-B0 experiments on ImageNet-1k suggest that global context helps when added to an intact MBConv trunk: zero-gated residual attention adapters at P3 (windowed) and P4/P5 (global) scored 73.88% versus 72.92% for a matched plain-B0 control, with attention amplitude increasing at deeper stages. A BiFPN wrapper alone scored 69.99-71.81%, below plain B0's 72.86%; adding stage attention raised it to 73.15%. For weight sharing, averaging kernels collapsed accuracy to 17.03%, while tying one template across a stage reduced parameters 27.6% but reached only 66.10%. Alternating two shared templates in Stage 6 cut parameters 10.9% (582K weights) and reached 70.92% after one recovery epoch, 1.84 points below the unshared control. Findings are limited to the described experiments and training schedule.

### Source excerpt

arXiv:2611.23446v1 Announce Type: cross Abstract: Compact convolutional backbones such as EfficientNet achieve strong parameter efficiency through local depthwise separable convolutions, yet two structural questions remain central to hybrid design: where does global self-attention improve recognition over pure convolution, and can repeated blocks share weights without losing representational capacity? We investigate both questions on ImageNet-1k (50,000-image validation) using controlled EfficientNet-B0 experiments. First, we show that wrapping a classification backbone in multi-scale feature pyramids (BiFPN) fails to outperform a plain MBConv trunk (69.99% - 71.81% vs. 72.86% plain B0) until paired with stage attention (73.15%). In contrast, keeping the MBConv trunk intact and inserting lightweight zero-gated residual self-attention adapters at stages P3 (28x28 windowed), P4 (14x14 global), and P5 (7x7 global) reaches 74.02% standalone and outperforms a bit-for-bit matched plain-B0 control by +0.954 percentage points (73.88% vs. 72.92%) across an 88-epoch stateless replay schedule, with learned attention amplitude rising monotonically with semantic depth (27.2% at P3 -> 45.4% at P4 -> 66.3% at P5). Second, we evaluate recurrent weight sharing across repeated MBConv blocks with pass-specific BatchNorm statistics (+1,536 parameters per pass). While post-hoc kernel averaging degrades accuracy to 17.03% and single-template stage tying (-27.6% parameters) plateaus at 66.10%, alternating two shared block templates ([B1, A, B, A]) in Stage 6 cuts total model parameters by 10.9% (582K weights) and recovers by +10.82 points in a single epoch to 70.92% (-1.84 points vs. unshared control).

## SoU-RHS: Bayesian Structured Sparsity for Compact Architecture Recovery in CNNs

DevFeed: [SoU-RHS: Bayesian Structured Sparsity for Compact Architecture Recovery in CNNs](<https://devfeed.tech/articles/sou-rhs-bayesian-structured-sparsity-for-compact-architecture-recovery-in-cnns-143489.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24166>)

Author: Rafael Mouallem Rosa (STATIFY), Julyan Arbel (STATIFY)

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Model Optimizer](<https://devfeed.tech/topics/model-optimizer.md>), [Occam's razor machine learning](<https://devfeed.tech/topics/occam-s-razor-machine-learning.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [bayesian](<https://devfeed.tech/tags/bayesian.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cnns](<https://devfeed.tech/tags/cnns.md>), [convolutional-neural-networks](<https://devfeed.tech/tags/convolutional-neural-networks.md>), [costs](<https://devfeed.tech/tags/costs.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [error](<https://devfeed.tech/tags/error.md>), [global](<https://devfeed.tech/tags/global.md>), [image](<https://devfeed.tech/tags/image.md>), [image-classification](<https://devfeed.tech/tags/image-classification.md>), [large](<https://devfeed.tech/tags/large.md>), [layer](<https://devfeed.tech/tags/layer.md>), [local](<https://devfeed.tech/tags/local.md>), [log](<https://devfeed.tech/tags/log.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [sparsity](<https://devfeed.tech/tags/sparsity.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>), [structured](<https://devfeed.tech/tags/structured.md>)

### AI overview

SoU-RHS combines Regularized Horseshoe Shrinkage with a Sources of Uncertainty Sparse Global-Local mechanism to separate active from inactive CNN filters and recover compact architectures. The abstract reports that recovered model size and layer-wise allocation remain similar across different overparameterized starting widths and a reasonable range of pruning thresholds. On standard image-classification benchmarks, SoU-RHS produces substantially smaller architectures than deterministic structured-sparsity baselines while maintaining competitive accuracy; it also achieves lower negative log-likelihood in every evaluated configuration and generally lower expected calibration error. The supplied text does not give benchmark names or numerical results.

### Source excerpt

arXiv:2611.24166v1 Announce Type: new Abstract: Highly parameterized convolutional neural networks often achieve strong predictive performance, but their memory, computation, and deployment costs motivate the search for methods that recover compact architectures from large reference models. We propose SoU-RHS, a Bayesian structured-sparsity procedure that augments Regularized Horseshoe Shrinkage (RHS) with the so-called Sources of Uncertainty Sparse Global-Local mechanism (SoU-SGL). The resulting model sharpens the separation between active and inactive filters, providing an effective mechanism for architecture recovery. A key property of SoU-RHS is stability: across different overparameterized starting widths and under a reasonable range of pruning thresholds, it recovers compact architectures with similar total size and layer-wise allocation. This supports the interpretation that the procedure is identifying a compact structure adapted to the data, rather than merely compressing each initial model separately. Across standard image-classification benchmarks, SoU-RHS recovers substantially smaller architectures than deterministic structured-sparsity baselines, while maintaining competitive accuracy, achieving lower negative log-likelihood in every evaluated configuration and generally lower expected calibration error.

## In Situ Training of Optical Neural Networks by Coding Agents

DevFeed: [In Situ Training of Optical Neural Networks by Coding Agents](<https://devfeed.tech/articles/in-situ-training-of-optical-neural-networks-by-coding-agents-142715.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23875>)

Author: Ilker Oguz, Colin Christian, Christophe Moser, Demetri Psaltis, Gordon Wetzstein

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Ray Tracing](<https://devfeed.tech/topics/ray-tracing.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [backpropagation](<https://devfeed.tech/tags/backpropagation.md>), [camera](<https://devfeed.tech/tags/camera.md>), [classification](<https://devfeed.tech/tags/classification.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [hypothesis](<https://devfeed.tech/tags/hypothesis.md>), [image](<https://devfeed.tech/tags/image.md>), [images](<https://devfeed.tech/tags/images.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [measurements](<https://devfeed.tech/tags/measurements.md>), [networks](<https://devfeed.tech/tags/networks.md>), [neural](<https://devfeed.tech/tags/neural.md>), [neural-networks](<https://devfeed.tech/tags/neural-networks.md>), [optical](<https://devfeed.tech/tags/optical.md>), [physics-optics](<https://devfeed.tech/tags/physics-optics.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

The "optics as code" method trains an optical neural network directly from measurements, without per-device calibration or gradients through the hardware. A coding agent receives camera images of optical probes and must state a hypothesis with each request; it then reparameterizes the network using interpretable optical elements tuned on the device. The abstract reports better classification and image encoding performance than gradient-free methods, approaching backpropagation through a calibrated model at a fraction of its cost. It says results improve with more capable models, while presenting the approach as a potential route to larger optical networks and a tool for optimizing optical experiments.

### Source excerpt

arXiv:2611.23875v1 Announce Type: cross Abstract: Optical neural networks promise fast, energy-efficient computing, but every device departs from its design and must be trained with the hardware. In situ training relies on an expert-built calibrated digital model of each device or on gradient-free trial and error. Coding agents, large language models that write and run programs, have shown an emergent ability to understand and edit the weights of digital neural networks. Here we introduce optics as code, a method in which a coding agent trains an optical neural network from measurements alone, through a harness that returns camera images of its probes and requires a hypothesis per request. We discovered that the agent forms a physical understanding of the optics and reparametrizes the network with interpretable optical elements tuned on the hardware. It outperforms gradient-free methods in classification and image encoding, approaching backpropagation through a calibrated model at a fraction of the cost. Needing neither per-device calibration nor gradients through the hardware, and improving with more capable models, optics as code offers a practical route to large, scalable optical neural networks and a general tool for calibrating and optimizing optical experiments.

## RFBench: A Simulator-Grounded Multimodal Benchmark for Passive RF Layout Design and Understanding

DevFeed: [RFBench: A Simulator-Grounded Multimodal Benchmark for Passive RF Layout Design and Understanding](<https://devfeed.tech/articles/rfbench-a-simulator-grounded-multimodal-benchmark-for-passive-rf-layout-design-and-understanding-142654.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23410>)

Author: Jiarui Cui, Boxun Yan

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [communications](<https://devfeed.tech/topics/communications.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [design](<https://devfeed.tech/tags/design.md>), [diagnosis](<https://devfeed.tech/tags/diagnosis.md>), [domain](<https://devfeed.tech/tags/domain.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [generate](<https://devfeed.tech/tags/generate.md>), [generation](<https://devfeed.tech/tags/generation.md>), [grid](<https://devfeed.tech/tags/grid.md>), [grounded](<https://devfeed.tech/tags/grounded.md>), [image](<https://devfeed.tech/tags/image.md>), [improvement](<https://devfeed.tech/tags/improvement.md>), [input](<https://devfeed.tech/tags/input.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [layout](<https://devfeed.tech/tags/layout.md>), [layouts](<https://devfeed.tech/tags/layouts.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [rf](<https://devfeed.tech/tags/rf.md>), [simulator](<https://devfeed.tech/tags/simulator.md>)

### AI overview

RFBench tests whether multimodal models can connect passive RF design intent and layout geometry to simulated electromagnetic behavior. Its 10,000 two-port planar layouts, simulated with ADS Momentum, pair editable primitives, raster images and occupancy grids with complex S-parameters across 201 frequency points, structural categories, and response labels. Seven tasks cover layout generation, representation translation, response prediction, simulator-based validation, design diagnosis and improvement, structural understanding, and response classification. Baselines across seven models show weaknesses in structurally valid generation and electromagnetically faithful prediction. RF-specific fine-tuning raised T1a structural validity from 0.0% to 83.2% and the T3 primitive-input within-2-dB rate from 17.7% to 62.8%, though the abstract says substantial room for improvement remains.

### Source excerpt

arXiv:2611.23410v1 Announce Type: new Abstract: While multimodal language models can interpret diagrams and generate structured outputs, their capacity to connect passive radio-frequency (RF) design intent, layout geometry, and electromagnetic behavior remains largely untested. To address this gap, we introduce RFBench, a simulator-grounded dataset and benchmark for passive RF layout design and understanding. The dataset contains 10,000 two-port planar layouts simulated using ADS Momentum, with each layout represented by editable geometric primitives, a raster image, a 16x16 occupancy grid, complex S-parameters at 201 frequency points, a structural category, and an RF response label. Building on these aligned representations, we define seven tasks spanning specification-conditioned layout generation, representation translation, response prediction, simulator-based validation, design diagnosis and improvement, structural understanding, and response classification. Extensive baselines across seven multimodal language models reveal systematic weaknesses in generating structurally valid layouts and predicting electromagnetically faithful responses. We show that RF-specific fine-tuning increases T1a structural validity from 0.0% to 83.2% and the T3 primitive-input within-2-dB rate from 17.7% to 62.8%, demonstrating the value of domain adaptation while leaving considerable room for further progress. RFBench establishes a common testbed for evaluating multimodal RF capabilities and guiding the development of models that connect design intent and layout representations with physical behavior.

[Next page](<https://devfeed.tech/tags/classification.md?cursor=WyIyMDI2LTExLTE5VDA1OjAwOjAwKzAwOjAwIiwgImU5NGZjOGNlLWRjYTQtNDMzZi05NDFkLWI4ODY3MTMxNTEyYyJd>)