# Embeddings

Embeddings are vector representations of data in a lower-dimensional space that capture semantic relationships and support machine-learning and similarity-search applications.

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

## D\\'ej\\\`a Cue: Localizing States in Object Histories via Vocabulary-Relative Coordinates

DevFeed: [D\\'ej\\\`a Cue: Localizing States in Object Histories via Vocabulary-Relative Coordinates](<https://devfeed.tech/articles/d-ej-a-cue-localizing-states-in-object-histories-via-vocabulary-relative-coordinates-144916.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.02044>)

Author: Haofan Cao, Zhichao You, Yunkai Yang, Liang Guo, Jie Wang, Chongshou 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: [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [absolute](<https://devfeed.tech/tags/absolute.md>), [alternatives](<https://devfeed.tech/tags/alternatives.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-mm](<https://devfeed.tech/tags/cs-mm.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [encoder](<https://devfeed.tech/tags/encoder.md>), [localization](<https://devfeed.tech/tags/localization.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [object](<https://devfeed.tech/tags/object.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [search](<https://devfeed.tech/tags/search.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [semantics](<https://devfeed.tech/tags/semantics.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [text](<https://devfeed.tech/tags/text.md>), [vision](<https://devfeed.tech/tags/vision.md>)

### AI overview

Déjà Cue localizes described states in tracked object histories by comparing each description against the alternatives in a supplied, state-balanced vocabulary. The training-free method centers description embeddings on the vocabulary mean, then uses frozen vision-language encoders to calibrate frame scores and retrieve intervals of multiple durations within contiguous visible runs. The authors introduce MS-VOST, annotating 620 object histories with 2,465 states. With the encoder and temporal search fixed, it outperforms absolute scoring on all three localization metrics across eight encoder configurations, improving Top-1 temporal IoU by 0.42-1.14 percentage points. Reported gains persist across four text constructions; candidate-ranking analysis indicates relevant intervals are ranked higher within the same search space.

### Source excerpt

arXiv:2608.02044v2 Announce Type: replace-cross Abstract: Object tracking preserves identity through visual changes, but cannot tell when an object is whole, cut, or peeled. We study state-moment retrieval: locating when a tracked object exhibits each state in a supplied set of descriptions. However, absolute image--text similarity can favor shared object semantics, obscuring the distinctions needed to localize individual states. Our insight is that the alternatives themselves provide a reference for measuring state evidence. We introduce D\'ej\`a Cue, a training-free framework that centers description embeddings on a state-balanced vocabulary mean, producing query directions that compare each state against its alternatives. Using frozen vision--language encoders, D\'ej\`a Cue calibrates frame scores and retrieves intervals at multiple durations within contiguous visible runs. We construct MS-VOST by annotating 620 object histories with 2,465 states. With the encoder and temporal search fixed, D\'ej\`a Cue improves all three localization metrics over absolute scoring across eight encoder configurations, raising Top-1 temporal IoU by 0.42--1.14 percentage points. These gains persist across four text constructions, and candidate-ranking analysis shows that the vocabulary reference brings relevant intervals forward within the same search space. These results establish the supplied state vocabulary as an object-specific reference for localizing semantic states from frozen visual representations.

## RePAIR: Predictive Self-Supervised Representation Learning in Chess

DevFeed: [RePAIR: Predictive Self-Supervised Representation Learning in Chess](<https://devfeed.tech/articles/repair-predictive-self-supervised-representation-learning-in-chess-144905.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.11860>)

Author: Christoph Koller, Johannes F\\"urnkranz, Timo Bertram

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>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Self-supervised learning](<https://devfeed.tech/topics/self-supervised-learning.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [bert](<https://devfeed.tech/topics/bert.md>)

Tags: [autoencoders](<https://devfeed.tech/tags/autoencoders.md>), [bert](<https://devfeed.tech/tags/bert.md>), [chess](<https://devfeed.tech/tags/chess.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [learning](<https://devfeed.tech/tags/learning.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [representation-learning](<https://devfeed.tech/tags/representation-learning.md>), [sequence](<https://devfeed.tech/tags/sequence.md>), [space](<https://devfeed.tech/tags/space.md>)

### AI overview

RePAIR learns compact representations of consecutive chess positions by masking large portions of latent-state sequences, then using a lightweight predictor to repair the gaps in a lower-dimensional embedding space. The authors report that its encoder clusters meaningful chess concepts, and that reconstructing masked board states captures piece movements without reinforcement learning. They also use trajectories through the representation space to inspect games. These findings are reported for chess; the supplied excerpt does not establish performance on other sequential data.

### Source excerpt

arXiv:2606.11860v2 Announce Type: replace Abstract: In this paper, we introduce Representation Prediction via Autoencoding using Iterative Refinement (RePAIR) - a novel self-supervised representation learning architecture that synthesizes Masked Autoencoders (MAE), Joint Embedding Predictive Architectures (JEPA), and Bidirectional Encoder Representations from Transformers (BERT). We demonstrate how it can be used to encode objects in sequential data like consecutive chess positions into compact yet meaningful representations. The basic principle of the architecture is to mask large portions of a sequence of latent states, similar to BERT and MAE. Then, we apply a lightweight Predictor to the latent representations that repairs gaps in the sequence in a lower-dimensional embedding space akin to JEPA. Our experiments in the domain of chess show that the Encoder refines the board representations such that meaningful chess concepts emerge clustered in the latent space. Furthermore, reconstructions of the masked board states show that the model is able to reason about the piece movements without relying on costly reinforcement learning methods. Lastly, we find that the resulting representation space allows for quick and intuitive dissections of chess games by observing the game path trajectories in this semantically rich space.

## SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs

DevFeed: [SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs](<https://devfeed.tech/articles/space-source-free-proxy-anchor-concept-erasure-for-mllms-144904.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.09868>)

Author: Zhijing Zhang, Jiaqi Ding, Qianshan Wei, Nan Zhou, Jiaqi Li, Yongliang Wu, Tongxin Zhu, Xiaolin Fang

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: [Model Development](<https://devfeed.tech/topics/model-development.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [code](<https://devfeed.tech/tags/code.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data-retention](<https://devfeed.tech/tags/data-retention.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [entropy](<https://devfeed.tech/tags/entropy.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [machine-unlearning](<https://devfeed.tech/tags/machine-unlearning.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [proxy](<https://devfeed.tech/tags/proxy.md>), [regulatory](<https://devfeed.tech/tags/regulatory.md>)

### AI overview

SPACE is a source-free machine unlearning framework for multimodal large language models that aims to erase target concepts without access to their visual data. Text-Guided Proxy Anchor Selection retrieves semantically aligned proxy anchors from the shared feature space; Dual-Constraint Semantic Isolation then optimizes those anchors to indirectly erase the concepts while confining updates to the null space of retained knowledge. The authors state that this bounds perturbations to retained knowledge and maximizes feature spectral entropy. Experiments across six datasets reportedly achieve performance comparable to state-of-the-art methods that use target data.

### Source excerpt

arXiv:2606.09868v2 Announce Type: replace Abstract: As Multimodal Large Language Models (MLLMs) face growing privacy risks and regulatory constraints, machine unlearning (MU) has emerged as a crucial solution for removing sensitive data while preserving model performance. However, existing MU methods typically rely on visual data of the target concepts, which is often unavailable due to strict data retention policies, thus creating a demand for source-free unlearning approaches that operate without access to the target data. In this work, we propose Source-free Proxy Anchor Concept Erasure (SPACE), the first source-free unlearning framework specialized for MLLMs. SPACE consists of two stages: (1) Text-Guided Proxy Anchor Selection (TPAS), which retrieves semantically aligned proxy anchors from the shared feature space. (2) Dual-Constraint Semantic Isolation (DCSI), which optimizes these anchors to indirectly erase target concepts. DCSI confines updates to the null space of retained knowledge, ensuring structural integrity. We theoretically prove that SPACE strictly bounds the perturbation on retained knowledge and maximizes feature spectral entropy, thereby maintaining the model's performance. Furthermore, extensive experiments across six datasets show that SPACE achieves performance comparable to that of state-of-the-art data-dependent methods, validating its effectiveness in source-free MU scenarios. The source code will be released.

## 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.

## From Sessions to Serving: Integrating LLM-Based Embeddings into Retrieval for Production Content Recommendation

DevFeed: [From Sessions to Serving: Integrating LLM-Based Embeddings into Retrieval for Production Content Recommendation](<https://devfeed.tech/articles/from-sessions-to-serving-integrating-llm-based-embeddings-into-retrieval-for-production-content-recommendation-145141.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26096>)

Author: Zhixiong Hu, Meng Li, Maggie Zhang, Deborshi Goswami, David Bailey, James Bradley

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

Content type: article

Language: en

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

Topics: [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [personalization](<https://devfeed.tech/topics/personalization.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>)

Tags: [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [llm](<https://devfeed.tech/tags/llm.md>), [production](<https://devfeed.tech/tags/production.md>), [recommendation](<https://devfeed.tech/tags/recommendation.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [serving](<https://devfeed.tech/tags/serving.md>)

### AI overview

LSER adds session- and history-level embeddings from a pretrained LLM as auxiliary user-side signals in the retrieval-stage user tower, alongside existing learned sequence encoders. For freshness as behavior changes, an asynchronous nearline serving path refreshes sequential and LLM-derived user vectors for the recommendation server. An ablation across a multi-content-type catalog indicates the LLM features can improve model performance, and the authors report that this approach is technically feasible in production. The excerpt gives no quantitative results or details of the serving implementation.

### Source excerpt

arXiv:2611.26096v1 Announce Type: cross Abstract: Personalized content recommendation on large marketplace websites must reconcile heterogeneous candidate content (e.g., customer stories, product pages, industry pages, and learning content) with sparse, fast-changing user behavior, placing increasing demands on the retrieval stage to represent user interest well, not just the downstream ranking stage. We present LSER (LLM Session Embedding Retrieval), a production content recommendation system for autodesk.com that derives session- and history-level embeddings from a pretrained large language model (LLM) and adds them as auxiliary user-side features in the retrieval-stage user tower alongside existing learned sequence encoders. To keep user-side embeddings fresh under real-time behavior, we build a nearline serving path that asynchronously refreshes sequential and LLM-derived user vectors for our main content recommendation server. We validate the incremental value of the LLM features through an ablation study across our full multi-content-type catalog. Our results indicate that integrating LLM-derived embeddings as additional retrieval signals, together with production-grade nearline serving, is technically feasible and can improve model performances.

## Erasing the Wrong Thing: Conditional Attribute Leakage and Concept Erasure in Shared Foundation-Model Embeddings

DevFeed: [Erasing the Wrong Thing: Conditional Attribute Leakage and Concept Erasure in Shared Foundation-Model Embeddings](<https://devfeed.tech/articles/erasing-the-wrong-thing-conditional-attribute-leakage-and-concept-erasure-in-shared-foundation-model-embeddings-145084.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25640>)

Author: Haijun He, Fei Li, Donghong Ji, Junjun He

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

Topics: [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>)

Tags: [association](<https://devfeed.tech/tags/association.md>), [attack](<https://devfeed.tech/tags/attack.md>), [biomedical](<https://devfeed.tech/tags/biomedical.md>), [conditional](<https://devfeed.tech/tags/conditional.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [diagnosis](<https://devfeed.tech/tags/diagnosis.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [foundation-model](<https://devfeed.tech/tags/foundation-model.md>), [linear](<https://devfeed.tech/tags/linear.md>), [model](<https://devfeed.tech/tags/model.md>), [strata](<https://devfeed.tech/tags/strata.md>), [utility](<https://devfeed.tech/tags/utility.md>)

### AI overview

Population-level concept erasure can leave sensitive attributes detectable within task groups when task and sensitive labels are associated. The authors prove that global and task-conditional linear guardedness cannot both preserve a nonzero linear task signal under this association. They introduce TC-LEACE, which enforces linear guardedness within each task stratum. Across four vision models and 85 CelebA attribute pairs, conditional leakage persisted after LEACE, with the gap between marginal and conditional audits growing with association strength; a pre-erasure-statistics estimate tracked observed utility costs. In chest-radiograph experiments using three models, chest-tube status remained detectable within diagnosis strata after LEACE, even though a marginal attack performed worse than a diagnosis-only reference. TC-LEACE recovered most of LEACE's linear task-utility loss while keeping conditional leakage within a prespecified margin of LEACE's.

### Source excerpt

arXiv:2611.25640v1 Announce Type: cross Abstract: Medical-image embeddings are increasingly shared in place of raw images for authorized downstream tasks, yet they may reveal sensitive attributes. Standard concept-erasure methods target population-level guardedness. However, we prove that, when binary task and sensitive labels are associated, global and task-conditional linear guardedness cannot both hold while a nonzero linear task signal is preserved, so global erasure must either eliminate that signal or retain task-conditional linear leakage. We further show how global erasure affects linear readers' discrimination between positive and negative samples with different sensitive attributes, deriving an approximate closed-form prediction of its utility cost from pre-erasure statistics. Motivated by this conflict, we introduce Task-Conditional LEACE (TC-LEACE), a closed-form variant of LEACE that enforces linear guardedness within each task stratum of its fitting data. We evaluate four vision foundation models on 85 CelebA attribute pairs spanning a broad range of associations. After LEACE, conditional leakage persists across all four encoders, the discrepancy between marginal and conditional audits increases with association strength, and predicted utility costs track observed losses. We then examine hospital chest radiographs using three foundation models, including two biomedical models, in which chest-tube status is strongly associated with diagnosis. Although a marginal attack on LEACE-erased embeddings underperforms a diagnosis-only reference, chest-tube status remains detectable within diagnosis strata. TC-LEACE recovers most of LEACE's linear task-utility loss while keeping task-conditional leakage within a prespecified margin of LEACE's.

## Hybrid Retrieval for Government Scheme Search in English and Marathi

DevFeed: [Hybrid Retrieval for Government Scheme Search in English and Marathi](<https://devfeed.tech/articles/hybrid-retrieval-for-government-scheme-search-in-english-and-marathi-145189.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26514>)

Author: Aishwarya Gunjal, Kanchan Khemnar, Pawan Poojary, Pranav Kulkarni, Raviraj Joshi, Manish Khodaskar

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

Content type: article

Language: en

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

Topics: [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [bm25](<https://devfeed.tech/tags/bm25.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [fusion](<https://devfeed.tech/tags/fusion.md>), [government](<https://devfeed.tech/tags/government.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [information](<https://devfeed.tech/tags/information.md>), [languages](<https://devfeed.tech/tags/languages.md>), [lexical](<https://devfeed.tech/tags/lexical.md>), [mrr](<https://devfeed.tech/tags/mrr.md>), [precision](<https://devfeed.tech/tags/precision.md>), [recall](<https://devfeed.tech/tags/recall.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [scheme](<https://devfeed.tech/tags/scheme.md>), [search](<https://devfeed.tech/tags/search.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [service](<https://devfeed.tech/tags/service.md>), [services](<https://devfeed.tech/tags/services.md>), [study](<https://devfeed.tech/tags/study.md>), [translation](<https://devfeed.tech/tags/translation.md>)

### AI overview

The system searches aligned English and Marathi descriptions of Maharashtra government schemes by combining BM25 with sentence-embedding similarity using equal-weight score fusion. On manually curated bilingual queries, BM25 achieves an MRR of 0.864; hybrid retrieval raises it modestly to 0.872 with IndicSBERT and 0.879 with MahaSBERT. Dense-only retrieval scores lower, at 0.663 and 0.655 respectively. MahaSBERT fusion also improves precision from 0.781 to 0.808 while matching BM25 recall at 0.946. The reported results indicate that lexical and semantic signals complement each other in this collection, with gains over the strong BM25 baseline modest and dependent on the metric.

### Source excerpt

arXiv:2611.26514v1 Announce Type: new Abstract: Retrieving government schemes requires matching citizens' information needs to formal administrative descriptions, often across languages and terminology. We present a bilingual search system for Maharashtra government schemes and public services that combines BM25 retrieval with sentence-embedding similarity through equal-weight score fusion. The system indexes aligned English-Marathi scheme descriptions and supports multilingual, Marathi-focused, and translation-mediated semantic configurations. Evaluation on manually curated bilingual queries compares BM25, dense retrieval, and hybrid retrieval using IndicSBERT and MahaSBERT. BM25 provides a strong baseline with a mean reciprocal rank (MRR) of 0.864. Hybrid retrieval increases MRR to 0.872 with IndicSBERT and 0.879 with MahaSBERT, whereas the corresponding dense-only systems achieve 0.663 and 0.655. MahaSBERT-based fusion also increases precision from 0.781 to 0.808 while matching BM25 recall at 0.946. These results support the complementary use of lexical and semantic signals in this collection, while showing that improvements over a strong lexical baseline are modest and metric-dependent. The study provides an application-focused analysis of hybrid retrieval for bilingual public-service information access.

## One Latent, Many Tokens: Jointly Learning Compressed Embeddings for Efficient Language Diffusion

DevFeed: [One Latent, Many Tokens: Jointly Learning Compressed Embeddings for Efficient Language Diffusion](<https://devfeed.tech/articles/one-latent-many-tokens-jointly-learning-compressed-embeddings-for-efficient-language-diffusion-145381.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.33698>)

Author: Yulin Yuan, Ying Zhang, Xiangming Meng

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

Content type: article

Language: en

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

Topics: [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>)

Tags: [compression](<https://devfeed.tech/tags/compression.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [flow](<https://devfeed.tech/tags/flow.md>), [flow-matching](<https://devfeed.tech/tags/flow-matching.md>), [generation](<https://devfeed.tech/tags/generation.md>), [language](<https://devfeed.tech/tags/language.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [learning](<https://devfeed.tech/tags/learning.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [structured](<https://devfeed.tech/tags/structured.md>), [throughput](<https://devfeed.tech/tags/throughput.md>), [tokens](<https://devfeed.tech/tags/tokens.md>)

### AI overview

JPEG-DLM reduces diffusion language generation cost by jointly training a compressor, flow matching model, and decoder, so compressed embeddings are designed to be easier to model and decode. This contrasts with two-stage methods that fix the compressed embedding space before training the diffusion model, which the abstract says can hinder modeling and token recovery. The authors report the highest throughput among recent diffusion and flow models on LM1B and OWT, with Gen-PPL lower than most. On OWT at a 0.5 compression rate, JPEG-DLM reports Gen-PPL 34.52 and about 2.3x ELF's throughput.

### Source excerpt

arXiv:2609.33698v2 Announce Type: replace Abstract: Most continuous diffusion language models process one latent position per token at each sampling step, making generation expensive. Two-stage methods lower the cost by reducing the latent length, but they fix the compressed embedding space before training the diffusion model. Embeddings from the fixed space can be difficult to model with diffusion and decode reliably into tokens, which limits generation quality after compression. To address this problem, we introduce JPEG-DLM (Joint-embedding Prediction for Efficient Generation with Diffusion Language Model), which jointly trains a compressor, a flow matching model and a decoding module. With joint-embedding prediction, JPEG-DLM learns compressed embeddings that are more structured, easier to model with diffusion and reliably decodable into tokens.JPEG-DLM achieves the highest throughput among recent diffusion and flow models on LM1B and OWT, with a Gen-PPL lower than most of them. At a compression rate of 0.5 on OWT, it reaches a Gen-PPL of 34.52 and approximately 2.3 times ELF's throughput. These results suggest that jointly learning compressed embeddings offers a promising path toward efficient diffusion language modeling.Code is available at https://github.com/infiniteYuanyl/JPEG-DLM.

## Protein Functional Semantic Alignment via Representation Rectification

DevFeed: [Protein Functional Semantic Alignment via Representation Rectification](<https://devfeed.tech/articles/protein-functional-semantic-alignment-via-representation-rectification-145050.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25396>)

Author: Chuyang Zhou, Bingxin Zhou, Andi Han, Chang Xu

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>), [post-training](<https://devfeed.tech/topics/post-training.md>), [The Gene Ontology Consortium](<https://devfeed.tech/topics/geneontology.md>)

Tags: [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [covariance](<https://devfeed.tech/tags/covariance.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [function](<https://devfeed.tech/tags/function.md>), [functional](<https://devfeed.tech/tags/functional.md>), [go](<https://devfeed.tech/tags/go.md>), [homology](<https://devfeed.tech/tags/homology.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [post-training](<https://devfeed.tech/tags/post-training.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [protein](<https://devfeed.tech/tags/protein.md>)

### AI overview

SAVR uses Pfam family co-membership as a homology-guided signal for contrastive post-training of protein language models, aiming to separate functional information from sequence variation. The method reduces directional dominance and variance concentration while increasing the effective dimensionality of embedding representations. It uses no task-specific labels during post-training and reports state-of-the-art results on Enzyme Commission benchmarks and competitive results on Gene Ontology benchmarks with frozen backbones. The supplied abstract does not provide benchmark details or quantify improvements.

### Source excerpt

arXiv:2611.25396v1 Announce Type: new Abstract: Protein language models (PLMs) are commonly pretrained with likelihood-based objectives such as masked language modeling or denoising. These objectives capture sequence-level regularities, but can produce representations in which functional signals are entangled with non-functional variation (e.g., sequence identity, compositional bias, and frequent local motifs), creating a readout bottleneck for downstream function prediction. We introduce Functional Semantic Alignment via Representation Rectification (SAVR), a contrastive post-training method using Pfam family co-membership as a homology-guided discrete semantic signal to reshape PLM representations. SAVR reduces directional dominance and redistributes variance across embedding dimensions, decreasing variance concentration, and increasing effective dimensionality of the embedding covariance spectrum. Without observing any task-specific labels during post-training, SAVR achieves state-of-the-art results on Enzyme Commission (EC) benchmarks and competitive results on Gene Ontology (GO) benchmarks under frozen-backbone evaluation. These results suggest that homology-guided contrastive post-training can rectify PLM representation geometry and improve sequence-based protein function prediction.

## A Neurosymbolic Multimodal Framework for 30-Day Diabetic Readmission Prediction: Integrating Structured EHR Data, Dense Clinical Embeddings, and Knowledge-Grounded Symbolic Extraction

DevFeed: [A Neurosymbolic Multimodal Framework for 30-Day Diabetic Readmission Prediction: Integrating Structured EHR Data, Dense Clinical Embeddings, and Knowledge-Grounded Symbolic Extraction](<https://devfeed.tech/articles/a-neurosymbolic-multimodal-framework-for-30-day-diabetic-readmission-prediction-integrating-structured-ehr-data-dense-clinical-embeddings-and-knowledge-grounded-symbolic-145488.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25236>)

Author: Una Suman Kumar Patro, Sibangi Subhadarsani, Narendra Badam

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

Content type: article

Language: en

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

Topics: [Vectors & LLMs](<https://devfeed.tech/topics/vectors-llms.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [AI for data automation](<https://devfeed.tech/topics/ai-for-data-automation.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>)

Tags: [cross-encoder](<https://devfeed.tech/tags/cross-encoder.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [hallucinations](<https://devfeed.tech/tags/hallucinations.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [retrieval-augmented-generation](<https://devfeed.tech/tags/retrieval-augmented-generation.md>), [structured](<https://devfeed.tech/tags/structured.md>), [xgboost](<https://devfeed.tech/tags/xgboost.md>)

### AI overview

On a held-out cohort of 20,153 encounters, the multimodal model improved sensitivity over the structured EHR baseline (0.6667 vs. 0.5839), achieved the best F2-score (0.3824) and lower Brier score (0.0977 vs. 0.1080), but had slightly lower AUROC (0.6375 vs. 0.6477) and specificity (0.5161). It combines engineered structured features, 32 compressed Bio_ClinicalBERT embedding components, and symbolic entities extracted through hybrid retrieval and negation auditing, then predicts with cost-sensitive XGBoost. In a separate 500-note code-switched benchmark, grounded retrieval raised Hinglish symptom recall and precision and reduced entity hallucinations. Prior utilization was the dominant risk signal. The reported findings are from the abstract's dataset and evaluations.

### Source excerpt

arXiv:2611.25236v1 Announce Type: new Abstract: Unplanned 30-day readmissions among patients with diabetes mellitus impose a substantial clinical and economic burden, yet most predictive models use only structured electronic health record (EHR) data and ignore free-text clinical notes, which often contain code-mixed Hindi-English (Hinglish) phrasing and negation that general-purpose language models parse unreliably. We propose a neurosymbolic multimodal framework evaluated on the public Diabetes 130-US Hospitals dataset (101,766 encounters; 71,518 patients) with a patient-level grouped 80/20 split. Three streams are fused: engineered structured features; 32 components of Bio_ClinicalBERT note embeddings obtained by truncated singular value decomposition; and symbolic entities extracted by an open-weight clinical language model within a three-stage hybrid retrieval-augmented generation pipeline (dense retrieval, sparse lexical retrieval, and cross-encoder re-ranking) with reflective negation auditing. A cost-sensitive XGBoost classifier with a decision threshold calibrated by Youden's J statistic produces the prediction. On the held-out test cohort (n = 20,153), the structured baseline achieved an area under the receiver operating characteristic curve (AUROC) of 0.6477, sensitivity of 0.5839, and Brier score of 0.1080. The full multimodal model achieved the highest sensitivity (0.6667; +8.28 percentage points), the best F2-score (0.3824), and the lowest Brier score (0.0977), at a slightly lower AUROC (0.6375) and specificity (0.5161). Shapley additive explanations showed that prior utilization dominates risk, with compressed narrative components among the top predictors. On a 500-note code-switched benchmark, grounded retrieval raised Hinglish symptom recall from 4.8% to 40.2% and precision from 3.1% to 45.2%, while reducing entity hallucinations from 1.74 to 0.00 per note.

## Learning from Context: Leave-One-Out Prediction in Jump Diffusions

DevFeed: [Learning from Context: Leave-One-Out Prediction in Jump Diffusions](<https://devfeed.tech/articles/learning-from-context-leave-one-out-prediction-in-jump-diffusions-145169.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26359>)

Author: Christian Wald

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>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [completion](<https://devfeed.tech/tags/completion.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [drift](<https://devfeed.tech/tags/drift.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [generation](<https://devfeed.tech/tags/generation.md>), [graph](<https://devfeed.tech/tags/graph.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [prediction](<https://devfeed.tech/tags/prediction.md>)

### AI overview

The paper studies leave-one-out (LOO) prediction in jump diffusions, where each coordinate is predicted from the corrupted states of the other coordinates to encourage learning dependencies between them. Under stated assumptions, complete coordinate resets with state-independent clocks preserve prescribed marginals when reset destinations use exact LOO probabilities and drift uses the full endpoint posterior. The authors show this drift can be built from LOO probabilities through analytic likelihood completion, without extra network evaluations. On Text8, LM1B, and ZINC250k, LOO-based variants improve key generation metrics over matched unrestricted controls. Controlled interventions examine reliance on local inputs and context; the abstract does not specify the metrics or size of the improvements.

### Source excerpt

arXiv:2611.26359v1 Announce Type: new Abstract: Continuous diffusion models generate discrete data through stochastic dynamics in an embedding space. We consider jump diffusions that additionally reset coordinates to embeddings of categorical values. A coordinate's own corrupted state can make prediction easy, potentially reducing the pressure to learn dependencies between coordinates. We study leave-one-out (LOO) prediction, in which each coordinate is predicted from the corrupted states of the other coordinates. We show that, under stated assumptions, jump diffusions with complete coordinate resets and state-independent clocks preserve the prescribed marginals when reset destinations use exact LOO probabilities and the drift uses the full endpoint posterior. We further show that this drift can be constructed from LOO probabilities by analytic likelihood completion without additional network evaluations. We evaluate unrestricted, LOO, and completed predictions on Text8 and LM1B text generation and ZINC250k molecular graph generation. LOO-based variants improve key generation metrics over matched unrestricted controls on all three datasets. Controlled interventions assess reliance on local inputs and context, and we analyze the effect of analytic likelihood completion.

## Spring AI 2.1.0 GA and 2.0.3 GA Available Now

DevFeed: [Spring AI 2.1.0 GA and 2.0.3 GA Available Now](<https://devfeed.tech/articles/spring-ai-2-1-0-ga-and-2-0-3-ga-available-now-146701.md>)

Original publisher: [Read original article](<https://spring.io/blog/2026/11/20/spring-ai-2-1-0-GA-available-now>)

Author: tzolov

Published: 2026-11-20T00:00:00Z

Content type: release

Language: en

Sources: [Spring](<https://devfeed.tech/sources/spring.md>)

Topics: [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [batch](<https://devfeed.tech/tags/batch.md>), [boot](<https://devfeed.tech/tags/boot.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [guardrail](<https://devfeed.tech/tags/guardrail.md>), [harness](<https://devfeed.tech/tags/harness.md>), [java](<https://devfeed.tech/tags/java.md>), [maven](<https://devfeed.tech/tags/maven.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [memory](<https://devfeed.tech/tags/memory.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [model-context-protocol](<https://devfeed.tech/tags/model-context-protocol.md>), [openai](<https://devfeed.tech/tags/openai.md>), [parts](<https://devfeed.tech/tags/parts.md>), [reactive](<https://devfeed.tech/tags/reactive.md>), [recall](<https://devfeed.tech/tags/recall.md>), [release](<https://devfeed.tech/tags/release.md>), [responses-api](<https://devfeed.tech/tags/responses-api.md>), [security](<https://devfeed.tech/tags/security.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [session](<https://devfeed.tech/tags/session.md>), [spring](<https://devfeed.tech/tags/spring.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [web-applications](<https://devfeed.tech/tags/web-applications.md>)

### AI overview

Spring AI 2.1.0 GA, built on Spring Boot 4.2, adds a stateless MCP 2026-07-28 protocol, typed Decision Models, ordered message parts that preserve reasoning and provider-specific payloads, and an OpenAI Responses API chat model. Its agent building blocks include a Session API with compaction and event recall (ChatMemory is deprecated for removal in 3.0), per-tool approval pauses, configurable per-turn call limits, and marked guardrail refusals. Eleven vector stores can now write and search vectors computed elsewhere, with width checks and stable-ID replacement. The release also includes reference-documentation changes and security fixes; Spring AI 2.0.3 carries the fixes on the 2.0.x line. Upgrading to 2.1 generally involves updating Spring AI and Spring Boot together, but some security fixes change behavior, and applications upgrading from 2.0.2 or earlier are directed to review the 2.0.2 and 2.0.3 notes.

### Source excerpt

On behalf of the Spring AI team and everyone who has contributed, I'm happy to announce that Spring AI 2.1.0 has been released and is now available from Maven Central! Release notes | Upgrade notes | Reference documentation Spring AI 2.1 arrives five months after 2.0.0 GA. It is built on Spring Boot 4.2 and contains more than 430 commits from 86 contributors. This post covers everything that changed since 2.0.0: the features of the 2.1 milestones and release candidates, what was added after RC2, and the additions that already shipped in 2.0.1 and 2.0.2. The short version: MCP 2026-07-28. Servers and clients for the new, stateless revision of the Model Context Protocol, next to the existing ones. Decision Models. A new model API for typed yes/no, choice and score decisions, with three providers. A richer message model. Messages hold ordered parts, so reasoning, tool calls and provider-specific blocks survive a round trip. The OpenAI Responses API is supported next to Chat Completions. The building blocks of an agent harness. The Session API, with session memory, compaction and recall, replaces ChatMemory. Tool calls can wait for a person's approval and are limited per turn, and guardrail refusals are marked as such. Your own embeddings. Eleven vector stores can write and search with vectors you computed yourself. New reference documentation, organized around tasks, with a quickstart and tutorials. Security. Fixes for 13 CVEs, which Spring AI 2.0.3 has as well. Next: Spring AI Agent. A new project for composing and orchestrating agents, built on Spring AI 2.1, starts incubating in early December. See What's next. The following map shows the building blocks of Spring AI 2.1, with the community projects in blue. It comes from the new reference documentation, where the blocks link to their pages. MCP 2026-07-28 The 2026-07-28 revision is a redesign of the Model Context Protocol. It is stateless: there is no initialize handshake and no session, every request carries the p

## What Is a Vector Database? How It Works and Why AI Needs One

DevFeed: [What Is a Vector Database? How It Works and Why AI Needs One](<https://devfeed.tech/articles/what-is-a-vector-database-how-it-works-and-why-ai-needs-one-145883.md>)

Original publisher: [Read original article](<https://montecarlo.ai/blog-what-is-a-vector-database>)

Author: Virna Sekuj

Published: 2026-11-19T17:18:16Z

Content type: article

Language: en

Sources: [Monte Carlo](<https://devfeed.tech/sources/monte-carlo.md>)

Topics: [Vectors & LLMs](<https://devfeed.tech/topics/vectors-llms.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [vector embeddings in AI](<https://devfeed.tech/topics/vector-embeddings-in-ai.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [ann](<https://devfeed.tech/topics/ann.md>), [Database](<https://devfeed.tech/topics/database.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>)

Tags: [agent-trust](<https://devfeed.tech/tags/agent-trust.md>), [agent-trust-glossary](<https://devfeed.tech/tags/agent-trust-glossary.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [data](<https://devfeed.tech/tags/data.md>), [database](<https://devfeed.tech/tags/database.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [glossary](<https://devfeed.tech/tags/glossary.md>), [rag](<https://devfeed.tech/tags/rag.md>), [rag-systems](<https://devfeed.tech/tags/rag-systems.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [retrieval-augmented-generation](<https://devfeed.tech/tags/retrieval-augmented-generation.md>), [retrieval-augmented-generation-rag](<https://devfeed.tech/tags/retrieval-augmented-generation-rag.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-database](<https://devfeed.tech/tags/vector-database.md>), [vector-database-examples](<https://devfeed.tech/tags/vector-database-examples.md>), [vector-database-for-rag](<https://devfeed.tech/tags/vector-database-for-rag.md>), [vector-database-vs-relational-database](<https://devfeed.tech/tags/vector-database-vs-relational-database.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-store](<https://devfeed.tech/tags/vector-store.md>)

### AI overview

Vector databases store content embeddings and use similarity search to retrieve relevant passages even when query wording differs. In a typical RAG flow, source content is chunked and embedded, stored with metadata, and indexed for approximate nearest-neighbor search; the user query is embedded and matching chunks are passed to the LLM as context. ANN indexing trades a small amount of precision for speed, and metadata filters can narrow results. Options include dedicated databases, database extensions, and vector search built into data platforms; choice depends on scale, latency, data location, and operational overhead. Retrieval can silently degrade when source syncs become stale, ingestion or chunking breaks, embedding models change without re-embedding, duplicate versions compete, or permission filters are missing. The text recommends monitoring freshness and ingestion volume, checking chunk quality, tracking embedding versions, measuring relevance and grounding, and tracing which chunks each agent request retrieves.

### Source excerpt

A vector database is a database built to store embeddings, which are numeric representations of the meaning of text, images, or other data, and to quickly find the embeddings most similar to a query. It's the retrieval layer behind most retrieval-augmented generation (RAG) systems and many AI agents, letting them find relevant information by meaning instead of exact keywords.

## Sex Differences in the Detection of Parkinson's Disease from Speech

DevFeed: [Sex Differences in the Detection of Parkinson's Disease from Speech](<https://devfeed.tech/articles/sex-differences-in-the-detection-of-parkinson-s-disease-from-speech-143553.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24741>)

Author: Hiba Akhaddar, Peter Plantinga, Mirco Ravanelli, Tristan Glatard

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

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>), [Feature Engineering](<https://devfeed.tech/topics/feature-engineering.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [classifiers](<https://devfeed.tech/tags/classifiers.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [detection](<https://devfeed.tech/tags/detection.md>), [disease](<https://devfeed.tech/tags/disease.md>), [eess-as](<https://devfeed.tech/tags/eess-as.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fail](<https://devfeed.tech/tags/fail.md>), [features](<https://devfeed.tech/tags/features.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [men](<https://devfeed.tech/tags/men.md>), [models](<https://devfeed.tech/tags/models.md>), [results](<https://devfeed.tech/tags/results.md>), [speech](<https://devfeed.tech/tags/speech.md>), [systems](<https://devfeed.tech/tags/systems.md>), [variable](<https://devfeed.tech/tags/variable.md>), [women](<https://devfeed.tech/tags/women.md>)

### AI overview

The study evaluates speech-based Parkinson's disease detection using embeddings from three pretrained speech models, handcrafted acoustic features and several classifiers. It tests balanced, sex-specific subsets from four sustained phonation datasets, controlling for sex and disease status and, where possible, age. In the larger dataset, female speakers were classified more accurately than male speakers. Models trained on one sex failed to generalize to the other, pointing to sex as an important variable in developing these detection systems. The supplied text is an abstract and does not provide further methodological detail or performance measures.

### Source excerpt

arXiv:2611.24741v1 Announce Type: cross Abstract: Parkinson's disease (PD) is the second most common neurodegenerative disease in the world, and 70\% to 75\% of PD patients suffer from speech disorders at some stage. Since PD affects men more frequently than women, previous publications tend to rely on unbalanced datasets that potentially introduce sex biases into trained models. This study investigates sex differences in PD detection from speech using deep learning and traditional machine learning approaches. We evaluated speech-based PD detection using embeddings from three pre-trained speech models, combined with handcrafted acoustic features and different classifiers. Sex-specific experiments were conducted on balanced subsets of four sustained phonation datasets, controlling for sex, disease status, and, where possible, age. All recordings were obtained during a sustained phonation task. Results show that female speakers were more accurately classified than male speakers in the larger dataset. Sex-specific results show that when the models are trained on one sex, they fail to generalize to the other one. Our results highlight the importance of including sex as a variable in the development of PD detection systems.

## Soft Mixture of Quantum Experts for Hybrid Quantum-Classical Learning

DevFeed: [Soft Mixture of Quantum Experts for Hybrid Quantum-Classical Learning](<https://devfeed.tech/articles/soft-mixture-of-quantum-experts-for-hybrid-quantum-classical-learning-142834.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24798>)

Author: Valeria Repetto, Romina D'Aurizio, Piero Farinelli

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

Content type: article

Language: en

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

Topics: [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [circuits](<https://devfeed.tech/tags/circuits.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [experts](<https://devfeed.tech/tags/experts.md>), [feature](<https://devfeed.tech/tags/feature.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [learning](<https://devfeed.tech/tags/learning.md>), [mnist](<https://devfeed.tech/tags/mnist.md>), [qml](<https://devfeed.tech/tags/qml.md>), [quant-ph](<https://devfeed.tech/tags/quant-ph.md>), [quantum](<https://devfeed.tech/tags/quantum.md>), [quantum-circuits](<https://devfeed.tech/tags/quantum-circuits.md>), [quantum-classical](<https://devfeed.tech/tags/quantum-classical.md>), [quantum-machine-learning](<https://devfeed.tech/tags/quantum-machine-learning.md>), [results](<https://devfeed.tech/tags/results.md>), [routing](<https://devfeed.tech/tags/routing.md>), [selection](<https://devfeed.tech/tags/selection.md>), [training](<https://devfeed.tech/tags/training.md>), [weight](<https://devfeed.tech/tags/weight.md>)

### AI overview

Soft-MoQE avoids training quantum circuit parameters by combining fixed quantum feature maps through a classical gating network that selects weights for each input. On PCA-reduced MNIST parity, MNIST 10-class, and FashionMNIST tasks, it outperformed the best single expert, uniform expert averaging, and a linear baseline. Its performance was comparable, depending on the task, to a trainable quantum neural network, with quantum training cost reported as orders of magnitude lower. The learned routing combined a few experts per input and varied by class. These findings are limited to the three evaluated tasks.

### Source excerpt

arXiv:2611.24798v1 Announce Type: cross Abstract: Quantum Machine Learning (QML) has attracted increasing interest as a possible route to construct feature representations that are difficult to reproduce with classical models. However, near-term QML architectures based on trainable parametrized quantum circuits remain affected by limited hardware resources, noise, and severe optimization difficulties such as barren plateaus. In this work we propose Soft-MoQE, a Soft Mixture of Quantum Experts architecture that replaces variational quantum training with the input-dependent selection and combination of fixed quantum feature maps. The model is composed of a heterogeneous pool of non-trainable quantum circuits, each defining a distinct embedding, and a classical gating network that learns how to weight these embeddings for each data point. We benchmark Soft-MoQE on three PCA-reduced tasks: MNIST parity, MNIST 10-class, and FashionMNIST. Soft-MoQE outperforms the single best expert, the uniform average of all experts and a linear baseline, achieving task-dependent performance comparable to that of a trainable quantum neural network, without optimizing any quantum parameter and with a quantum training cost that is lower by orders of magnitude. The analysis of the class- conditioned expert usage shows that the learned routing combines a few experts for each input, with a selection that depends on the class. These results support the learned routing among fixed quantum circuits as a trainability-aware design principle for hybrid QML.

## Improving Cross-Lingual Token Representations by Adding a Pinch of SALT

DevFeed: [Improving Cross-Lingual Token Representations by Adding a Pinch of SALT](<https://devfeed.tech/articles/improving-cross-lingual-token-representations-by-adding-a-pinch-of-salt-142559.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.09953>)

Author: Guillem Ram\\'irez

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

Content type: article

Language: en

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

Topics: [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [Internationalization (i18n)](<https://devfeed.tech/topics/i18n.md>)

Tags: [alignment](<https://devfeed.tech/tags/alignment.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [detection](<https://devfeed.tech/tags/detection.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [hallucination-detection](<https://devfeed.tech/tags/hallucination-detection.md>), [languages](<https://devfeed.tech/tags/languages.md>), [learning](<https://devfeed.tech/tags/learning.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [mining](<https://devfeed.tech/tags/mining.md>), [performance](<https://devfeed.tech/tags/performance.md>), [post-training](<https://devfeed.tech/tags/post-training.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [salt](<https://devfeed.tech/tags/salt.md>), [sequence](<https://devfeed.tech/tags/sequence.md>), [signal](<https://devfeed.tech/tags/signal.md>), [span](<https://devfeed.tech/tags/span.md>), [supervision](<https://devfeed.tech/tags/supervision.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [token](<https://devfeed.tech/tags/token.md>), [translation](<https://devfeed.tech/tags/translation.md>)

### AI overview

SALT improves token representations in cross-lingual sentence encoders by post-training them with span-level supervision. Across five multilingual token-level benchmarks, it achieves the best overall results on four, outperforming alternative fine-tuning strategies and competitive encoders. The abstract also reports gains on cross-lingual retrieval and classification, suggesting the method can benefit sentence-level performance too.

### Source excerpt

arXiv:2609.09953v2 Announce Type: replace-cross Abstract: Cross-lingual sentence encoders enable scalable transfer across hundreds of languages, powering applications such as translation mining and zero-shot learning in low-resource settings. Although trained for sentence-level alignment, they are increasingly also applied to token-level tasks such as hallucination detection and sequence tagging, exposing a mismatch between training and usage. We propose SALT, a lightweight post-training method that improves token representations by injecting span-level supervision into existing sentence encoders. Across five multilingual token-level benchmarks, SALT achieves the best overall results on four of them, outperforming alternative fine-tuning strategies and competitive encoders. It also improves sentence-level performance on cross-lingual retrieval and classification tasks. These results demonstrate that span-level supervision is an effective signal for improving both token and sentence representations.

## Label-Free Role-Aware Segmentation of Classroom Recordings: Recovering the Teacher from Transferable Structure

DevFeed: [Label-Free Role-Aware Segmentation of Classroom Recordings: Recovering the Teacher from Transferable Structure](<https://devfeed.tech/articles/label-free-role-aware-segmentation-of-classroom-recordings-recovering-the-teacher-from-transferable-structure-143413.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23609>)

Author: Nitin Jain, Tim F\\"utterer, Babette B\\"uhler, \\c{C}a\\u{g}atay Y{\\i}ld{\\i}z

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

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>), [On-device AI](<https://devfeed.tech/topics/on-device-ai.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [audio](<https://devfeed.tech/tags/audio.md>), [classroom](<https://devfeed.tech/tags/classroom.md>), [clustering](<https://devfeed.tech/tags/clustering.md>), [cross-validation](<https://devfeed.tech/tags/cross-validation.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-sd](<https://devfeed.tech/tags/cs-sd.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [device](<https://devfeed.tech/tags/device.md>), [diarization](<https://devfeed.tech/tags/diarization.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [english](<https://devfeed.tech/tags/english.md>), [error](<https://devfeed.tech/tags/error.md>), [f1](<https://devfeed.tech/tags/f1.md>), [failures](<https://devfeed.tech/tags/failures.md>), [faster](<https://devfeed.tech/tags/faster.md>), [flag](<https://devfeed.tech/tags/flag.md>), [gdpr](<https://devfeed.tech/tags/gdpr.md>), [human-review](<https://devfeed.tech/tags/human-review.md>), [inference](<https://devfeed.tech/tags/inference.md>), [recordings](<https://devfeed.tech/tags/recordings.md>), [structure](<https://devfeed.tech/tags/structure.md>)

### AI overview

The paper proposes an on-device pipeline that identifies teacher speech without labels at inference or per-session calibration, addressing a constraint in which classroom audio must remain on the recording device. It combines voice activity detection, pretrained speaker embeddings, agglomerative clustering, and logistic regression that assigns the teacher role from session-relative structure rather than voice identity. In leave-one-teacher-out evaluation on 292 recordings from 63 teachers, teacher F1 was 0.81 for English and 0.87 for German, exceeding the reported enrollment-based baselines and 30-second supervised enrollment ceiling. On a commodity smartphone, performance matched pyannote while running 4.8 times faster at comparable peak memory. Filtering audio raised teacher word error rate only slightly, from 0.26 to 0.28. Failures were concentrated where teacher and student voices were acoustically inseparable; the method can flag such sessions for human review.

### Source excerpt

arXiv:2611.23609v1 Announce Type: new Abstract: How much the teacher talks and when are among the most informative and costly-to-measure signals of teaching. Yet, classroom audio is among the most sensitive data an AI system can process: recordings capture minors and fall under GDPR, preventing raw audio from leaving the recording device. We present a teacher-student segmentation pipeline designed to meet exactly this constraint: label-free at inference, running on a recording device, and requiring no per-session calibration. The pipeline chains a lightweight voice activity detector, compactly pretrained speaker embeddings, agglomerative clustering, and a small logistic regression that assigns the teacher role based on session-relative structure rather than voice identity. We show that our structural cue transfers across classrooms, languages, and acoustic conditions. In leave-one-teacher-out cross-validation on 292 recordings from 63 teachers across English and German corpora, our pipeline achieves teacher F1 of 0.81 and 0.87, respectively, outperforming both enrollment-based baselines and a 30-second supervised enrollment ceiling. On a commodity smartphone, its performance matches pyannote, a strong neural diarization tool, while running 4.8x faster at comparable peak memory at a real-time factor of ~0.18. We also find that transcribing filtered audio only marginally increases teacher's word error rate from $0.26$ to 0.28. Residual failures concentrate where teacher and student voices are not acoustically separable. However, we show how to flag these sessions label-free at inference so that they can be routed to human review, enabling selective, privacy-preserving deployment.

## Searching the Pareto Front: Multi-Objective Retrieval for Heterogeneous Scientific Modalities

DevFeed: [Searching the Pareto Front: Multi-Objective Retrieval for Heterogeneous Scientific Modalities](<https://devfeed.tech/articles/searching-the-pareto-front-multi-objective-retrieval-for-heterogeneous-scientific-modalities-142684.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23639>)

Author: Song Young Oh, Nesar Ramachandra, Bin Xia, Ian Foster, Kyle Chard

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

Content type: article

Language: en

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

Topics: [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [approach](<https://devfeed.tech/tags/approach.md>), [astro-ph-im](<https://devfeed.tech/tags/astro-ph-im.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fm](<https://devfeed.tech/tags/fm.md>), [foundation-models](<https://devfeed.tech/tags/foundation-models.md>), [fusion](<https://devfeed.tech/tags/fusion.md>), [galaxy](<https://devfeed.tech/tags/galaxy.md>), [history](<https://devfeed.tech/tags/history.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [nearest-neighbor](<https://devfeed.tech/tags/nearest-neighbor.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [pareto-optimality](<https://devfeed.tech/tags/pareto-optimality.md>), [properties](<https://devfeed.tech/tags/properties.md>), [proximity](<https://devfeed.tech/tags/proximity.md>), [query](<https://devfeed.tech/tags/query.md>), [raw](<https://devfeed.tech/tags/raw.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [searching](<https://devfeed.tech/tags/searching.md>), [similarity](<https://devfeed.tech/tags/similarity.md>)

### AI overview

The study compares a multimodal foundation model (FM) with separately trained modality embeddings combined through Pareto-based multi-objective optimization for galaxy retrieval across star-formation histories, spectra, and observations from two telescopes. The FM provides strong embedding-space proximity, while late fusion retains modality-specific distances so scientists can inspect which physical signals contribute to similarity. Across six measured properties, the method's nearest neighbor is reported to be 8% closer to the query in raw-data space on average than kNN in the FM embedding space (spread 0.128 versus 0.139). The abstract suggests this may surface astrophysically coherent candidates overlooked by single-objective search.

### Source excerpt

arXiv:2611.23639v1 Announce Type: new Abstract: In cosmology, surveys span different sky regions and wavelength ranges, resulting in uneven modality coverage across observational datasets. Such heterogeneity can be addressed through either multimodal foundation models (FMs), which learn shared embedding spaces, or independently learned modality embeddings combined via late fusion. We investigate whether the latter provides an adaptive alternative to FM-based scientific retrieval. We evaluate this approach on a galaxy retrieval task spanning diverse modalities--history of star formation, spectra of light emitted, and multi-wavelength observations from two telescopes--comparing an FM baseline with separately trained embeddings fused through multi-objective optimization based on Pareto optimality. We find that the FM baseline achieves strong embedding-space proximity, but our method preserves modality-specific distance structure that allows scientists to inspect which physical signals drive similarity. Our method also achieves improved fidelity in raw-data space: across six measured properties, its nearest neighbor is 8% closer to the query on average than that retrieved by kNN in the FM embedding space (spread 0.128 vs. 0.139). These results suggest that multi-objective retrieval can surface astrophysically coherent candidates that single-objective search alone may overlook.

## Recurrent Domain Incremental Adaptation of Time-Series Foundation Models

DevFeed: [Recurrent Domain Incremental Adaptation of Time-Series Foundation Models](<https://devfeed.tech/articles/recurrent-domain-incremental-adaptation-of-time-series-foundation-models-142751.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24075>)

Author: Sachith Abeywickrama, Peiliang Gong, Emadeldeen Eldele, Min Wu, Chau Yuen

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 Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Time Series](<https://devfeed.tech/topics/time-series.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [adapting](<https://devfeed.tech/tags/adapting.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [charts](<https://devfeed.tech/tags/charts.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [eess-sp](<https://devfeed.tech/tags/eess-sp.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [gate](<https://devfeed.tech/tags/gate.md>), [incremental](<https://devfeed.tech/tags/incremental.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [retention](<https://devfeed.tech/tags/retention.md>), [shift](<https://devfeed.tech/tags/shift.md>), [stream](<https://devfeed.tech/tags/stream.md>), [time-series-foundation-models](<https://devfeed.tech/tags/time-series-foundation-models.md>)

### AI overview

PACT addresses incremental adaptation to changing operating conditions by partitioning a frozen time-series foundation model's embedding space into local charts and learning lightweight residual transports only for affected regions. An identity path is retained, and a learned gate selects between it and accumulated transports without requiring condition identity at inference. The encoder, classifier head, and prior transports stay fixed. With 5% labeled calibration data per arriving condition, the authors report average macro-F1 above 0.95 across a four-condition bearing-fault stream; they report similar retention and adaptation on public benchmarks when tasks and label spaces are homogeneous.

### Source excerpt

arXiv:2611.24075v1 Announce Type: new Abstract: Pretrained Time-Series Foundation Models (TSFMs) provide strong representations for downstream classification tasks. Yet adapting a TSFM under changing operating conditions remains challenging. A model must improve on each newly observed condition without sacrificing conditions it has already learned, often from only a small labeled calibration set and without knowing the operating condition at inference time. We find that this difficulty has an important geometric structure. Under an operating-condition shift, the embedding space of a TSFM does not move uniformly: some local regions change substantially, while others remain nearly unchanged. Consequently, a global adaptation can unnecessarily move embeddings that were already correctly classified. To address this, we propose the novel PACT (Piecewise Adaptation via Chart Transport). PACT partitions the frozen source embedding space into local charts and learns lightweight residual transports for the regions affected by each new condition. An explicit identity path is always retained, and a learned gate softly selects among the identity and accumulated transports for each input. The pretrained TSFM encoder, classifier head, and previously learned transports remain fixed. With only 5% labeled calibration data per arriving condition and no condition identity at test time, PACT maintains an average macro-F1 above 0.95 across a four-condition bearing-fault stream. Under homogeneous tasks and label spaces, similar retention-adaptation behavior is observed across public benchmarks. Code is available at https://github.com/Sachithx/PACT.

## NaviGATE: Noise-Aware Dual-View Generation for Multimodal Knowledge Graph Reasoning

DevFeed: [NaviGATE: Noise-Aware Dual-View Generation for Multimodal Knowledge Graph Reasoning](<https://devfeed.tech/articles/navigate-noise-aware-dual-view-generation-for-multimodal-knowledge-graph-reasoning-142808.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24552>)

Author: Jie Peng, Yongxue Shan, Yongfu Zha, Cui Miao, Xiaodong Wang

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

Content type: article

Language: en

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

Topics: [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [activation](<https://devfeed.tech/tags/activation.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [generation](<https://devfeed.tech/tags/generation.md>), [generative](<https://devfeed.tech/tags/generative.md>), [graph](<https://devfeed.tech/tags/graph.md>), [inference](<https://devfeed.tech/tags/inference.md>), [instruction-tuning](<https://devfeed.tech/tags/instruction-tuning.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [noise](<https://devfeed.tech/tags/noise.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [robust](<https://devfeed.tech/tags/robust.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [semantics](<https://devfeed.tech/tags/semantics.md>), [stage](<https://devfeed.tech/tags/stage.md>), [view](<https://devfeed.tech/tags/view.md>)

### AI overview

NaviGATE addresses noisy retrieval and invalid entity generation in multimodal knowledge graph reasoning. It aligns graph structure with text, fine-tunes a multimodal language model using entity summaries and structural tokens, then trains retrieval-free and retrieval-aware views together. Contrastive logit sharpening reinforces reliable retrieved candidates; parametric consistency distillation suppresses misleading ones. At inference, structure-constrained decoding limits outputs to valid graph entities. The abstract reports that NaviGATE outperforms strong unimodal, multimodal, and generation-based baselines on standard benchmarks and remains robust under noisy retrieval.

### Source excerpt

arXiv:2611.24552v1 Announce Type: new Abstract: Multimodal knowledge graph reasoning (MKGR) aims to infer missing facts by jointly exploiting relational structures, textual descriptions, and visual evidence. Existing embedding-based methods effectively capture graph topology, but their fixed multimodal representations are less effective for query-specific fine-grained semantic reasoning, while generation-based methods are vulnerable to noisy retrieval and may produce invalid entities. To address these challenges, we propose NaviGATE, a noise-aware generative framework for MKGR. NaviGATE first aligns graph-derived structural representations with textual semantics, then performs structure-aware internal knowledge activation by fine-tuning the multimodal language model with multimodal entity summaries and injected structural tokens. In the noise-aware dual-view instruction tuning stage, NaviGATE jointly optimizes retrieval-free and retrieval-aware views: reliable retrieved candidates are reinforced through contrastive logit sharpening, while misleading candidates are suppressed through parametric consistency distillation. In inference, structure-constrained decoding restricts generation to valid entities in the target knowledge graph. Experiments on standard benchmarks show that NaviGATE consistently outperforms strong unimodal, multimodal, and generation-based baselines, and remains robust under noisy retrieval scenarios.

## Towards Online Adaptive LLM-based Semantic Filtering

DevFeed: [Towards Online Adaptive LLM-based Semantic Filtering](<https://devfeed.tech/articles/towards-online-adaptive-llm-based-semantic-filtering-142289.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24518>)

Author: Ziqi Zou, Zhenyan Nie, Kangfei Zhao, Zhiwei Zhang, Aoqian Zhang, Peng Wu, Xuefeng Zhao

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

Content type: article

Language: en

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

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [llm](<https://devfeed.tech/tags/llm.md>), [online](<https://devfeed.tech/tags/online.md>), [semantic](<https://devfeed.tech/tags/semantic.md>)

### AI overview

OASIS reduces the cost and latency of LLM-based semantic filtering by combining a document similarity graph with query-specific proxy learning and adaptive sampling. For each query, a graph attention network scores documents; density-aware active learning selects informative labels and stops when more labels are unlikely to help. Calibration sets also grow adaptively to the query's score distribution. In reported experiments, at 0.9 accuracy, OASIS cut online latency by 1.75x-5.42x and reduced the number of documents processed by an LLM by 35%-75% versus state-of-the-art methods.

### Source excerpt

arXiv:2611.24518v1 Announce Type: new Abstract: Large language models (LLMs) enable semantic filtering over unstructured documents using natural language predicates, but invoking an oracle LLM on every document incurs prohibitive monetary cost and online latency. Existing model-cascade approaches reduce this cost by using a lightweight proxy model to score each document and forwarding only uncertain documents to the oracle. However, their proxy models have limited generalization capability, and they typically adopt fixed sampling budgets for proxy training and threshold calibration, which insufficiently adapts to diverse online queries. To address this, we present OASIS, an online adaptive framework for LLM-based semantic filtering. OASIS combines a query-agnostic document similarity prior with query-adaptive online learning and sampling. In the offline phase, OASIS utilizes query-agnostic document similarity as a prior and constructs a document navigating spread-out graph (NSG) over document embeddings. For each online query, OASIS trains a query-conditioned graph attention network over the document NSG to obtain proxy scores through semi-supervised node classification. To allocate labels effectively, OASIS adopts density-aware active learning to explore uncertain score regions, selectively annotate informative documents, retrain the proxy, and stop early when additional labels are unlikely to improve the cascade. During threshold calibration, OASIS progressively samples an adaptively sized calibration set, adapting calibration cost to the query's score distribution. Extensive experiments demonstrate that OASIS achieves a 1.75x-5.42x reduction in online latency and reduces the number of LLM-processed documents by 35%-75% relative to the state-of-the-art methods at an achieved accuracy of 0.9.

## FACET - Facet Aware Contrastive Embeddings for Traits- Big Five Estimation from Life Narratives

DevFeed: [FACET - Facet Aware Contrastive Embeddings for Traits- Big Five Estimation from Life Narratives](<https://devfeed.tech/articles/facet-facet-aware-contrastive-embeddings-for-traits-big-five-estimation-from-life-narratives-142670.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23560>)

Author: Balakrishnan Arumugam, Priyen Parekh, Mehak Gupta, Joshua Oltmanns

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

Content type: article

Language: en

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

Topics: [Data Science](<https://devfeed.tech/topics/data-science.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [vector embeddings in AI](<https://devfeed.tech/topics/vector-embeddings-in-ai.md>), [concatenation](<https://devfeed.tech/topics/concatenation.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [aging](<https://devfeed.tech/tags/aging.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [attention](<https://devfeed.tech/tags/attention.md>), [based](<https://devfeed.tech/tags/based.md>), [can](<https://devfeed.tech/tags/can.md>), [combines](<https://devfeed.tech/tags/combines.md>), [compare](<https://devfeed.tech/tags/compare.md>), [concatenation](<https://devfeed.tech/tags/concatenation.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [decision](<https://devfeed.tech/tags/decision.md>), [domain](<https://devfeed.tech/tags/domain.md>), [domains](<https://devfeed.tech/tags/domains.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [error](<https://devfeed.tech/tags/error.md>), [existing](<https://devfeed.tech/tags/existing.md>), [features](<https://devfeed.tech/tags/features.md>), [framework](<https://devfeed.tech/tags/framework.md>), [gives](<https://devfeed.tech/tags/gives.md>), [input](<https://devfeed.tech/tags/input.md>), [life](<https://devfeed.tech/tags/life.md>)

### AI overview

FACET estimates Big Five scores from life-narrative interviews by separately encoding text and psycholinguistic features, learning contrastive embeddings for personality facets, then using attention to pool them into domain predictions. In 1,332 SPAN participants, facet AUC reached 0.740 and domain R² reached 0.328, highest for Openness. End-to-end training had lower error than staged training in every domain, and attention pooling had the lowest error in every domain. Combining feature views reduced error versus text alone for Conscientiousness and Agreeableness; learned weighting showed no consistent advantage over concatenation. The method modestly outperformed raw-feature regression in four of five domains and provides facet-level predictions unavailable from a domain-only model.

### Source excerpt

arXiv:2611.23560v1 Announce Type: new Abstract: Personality is only weakly and inconsistently signaled by written language, and existing text-based methods typically combine language-model and psycholinguistic representations at the input or decision level. It remains open whether a more deliberate combination of the two views, and a decomposition of the prediction target, can recover more of the signal. We present a three-phase framework for estimating Big Five personality domain scores from life-narrative interview text. It encodes text and psycholinguistic features separately and combines them by concatenation or by a learned weighting, decomposes each domain into contrastively trained facet embeddings instead of predicting the domain directly, and pools the facet embeddings by attention into a domain-level prediction. We compare end-to-end with staged training and ablate the input modalities, their combination, and the facet-pooling strategy. On 1,332 participants from the St. Louis Personality and Aging Network (SPAN) study, facet embeddings reach AUC up to 0.740, and domain-level R2 reaches 0.328, highest for Openness. End-to-end training gives lower error than staged training in every domain, and attention pooling gives the lowest error in every domain. Combining the two views lowers error relative to text alone for Conscientiousness and Agreeableness, whereas a learned weighting of the views shows no consistent advantage over concatenation. The framework provides facet- level predictions that a domain-only model cannot, and it improves modestly on a regression from the raw features in four of the five domains.

## Exa boosts embedding throughput by 50% to index billions of documents on AWS AI chips

DevFeed: [Exa boosts embedding throughput by 50% to index billions of documents on AWS AI chips](<https://devfeed.tech/articles/exa-boosts-embedding-throughput-by-50-to-index-billions-of-documents-on-aws-ai-chips-141408.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/exa-boosts-embedding-throughput-by-50-to-index-billions-of-documents-on-aws-ai-chips/>)

Author: Summer Devlin

Published: 2026-11-18T23:58:22Z

Content type: news

Language: en

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

Topics: [AWS Inferentia](<https://devfeed.tech/topics/aws-inferentia.md>), [AWS AI chips](<https://devfeed.tech/topics/aws-ai-chips.md>), [neuron](<https://devfeed.tech/topics/neuron.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>), [AWS Trainium](<https://devfeed.tech/topics/aws-trainium.md>), [search-engines](<https://devfeed.tech/topics/search-engines.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-chips](<https://devfeed.tech/tags/ai-chips.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-ai-chips](<https://devfeed.tech/tags/aws-ai-chips.md>), [aws-inferentia](<https://devfeed.tech/tags/aws-inferentia.md>), [aws-neuron](<https://devfeed.tech/tags/aws-neuron.md>), [aws-trainium](<https://devfeed.tech/tags/aws-trainium.md>), [cost](<https://devfeed.tech/tags/cost.md>), [custom](<https://devfeed.tech/tags/custom.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [database](<https://devfeed.tech/tags/database.md>), [economics](<https://devfeed.tech/tags/economics.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [index](<https://devfeed.tech/tags/index.md>), [inference](<https://devfeed.tech/tags/inference.md>), [kernels](<https://devfeed.tech/tags/kernels.md>), [neuron](<https://devfeed.tech/tags/neuron.md>), [optimized](<https://devfeed.tech/tags/optimized.md>), [performance](<https://devfeed.tech/tags/performance.md>), [search](<https://devfeed.tech/tags/search.md>), [throughput](<https://devfeed.tech/tags/throughput.md>), [unit-economics](<https://devfeed.tech/tags/unit-economics.md>), [vector](<https://devfeed.tech/tags/vector.md>)

### AI overview

Exa reports a 47% improvement in performance and cost per million documents embedded on AWS Neuron hardware versus its initial baseline. Starting with FP16 data parallelism on Inferentia2, it optimized weight layout and precision, used a drop-in attention kernel, and built a fused SwiGLU MLP kernel to reduce memory spill. Custom attention kernels tailored to the model's shapes then cut padding work and instruction steps. Each change passed a correctness gate of 0.999 cosine similarity to the reference; performance was measured with a 30-minute saturation benchmark. The workload uses one NeuronCore per pod, and the same approach scales through data parallelism on Trainium2. Exa says tuning across hardware and Regions helps its scheduler match shifting demand and availability. The excerpt describes these results and methods but does not provide absolute throughput or cost figures.

### Source excerpt

Exa's neural search engine is backed by an in-house vector database, so the unit economics of embedding tens of billions of web documents drive the business. This post shares how Exa optimized embedding inference on AWS Neuron hardware (Inferentia2 and Trainium2) with custom NKI kernels, reaching a 47% gain in performance and cost per million documents.

## What Is an Embedding? How AI Turns Meaning Into Numbers

DevFeed: [What Is an Embedding? How AI Turns Meaning Into Numbers](<https://devfeed.tech/articles/what-is-an-embedding-how-ai-turns-meaning-into-numbers-141932.md>)

Original publisher: [Read original article](<https://montecarlo.ai/blog-embedding>)

Author: Ruslan Sultanov

Published: 2026-11-18T18:58:12Z

Content type: article

Language: en

Sources: [Monte Carlo](<https://devfeed.tech/sources/monte-carlo.md>)

Topics: [vector embeddings in AI](<https://devfeed.tech/topics/vector-embeddings-in-ai.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [cosine similarity search](<https://devfeed.tech/topics/cosine-similarity-search.md>), [Data Quality](<https://devfeed.tech/topics/data-quality.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [clustering](<https://devfeed.tech/topics/clustering.md>)

Tags: [agent-trust](<https://devfeed.tech/tags/agent-trust.md>), [agent-trust-glossary](<https://devfeed.tech/tags/agent-trust-glossary.md>), [ai](<https://devfeed.tech/tags/ai.md>), [cosine-similarity](<https://devfeed.tech/tags/cosine-similarity.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embedding-model](<https://devfeed.tech/tags/embedding-model.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [embeddings-in-machine-learning](<https://devfeed.tech/tags/embeddings-in-machine-learning.md>), [embeddings-rag](<https://devfeed.tech/tags/embeddings-rag.md>), [glossary](<https://devfeed.tech/tags/glossary.md>), [meaning](<https://devfeed.tech/tags/meaning.md>), [text-embeddings](<https://devfeed.tech/tags/text-embeddings.md>), [vector-database](<https://devfeed.tech/tags/vector-database.md>), [vector-embeddings](<https://devfeed.tech/tags/vector-embeddings.md>), [what-is-an-embedding](<https://devfeed.tech/tags/what-is-an-embedding.md>)

### AI overview

Embeddings represent text, images, or other data as numeric vectors, placing semantically similar items near each other so systems can retrieve by meaning rather than exact wording. In a typical RAG pipeline, documents are split into chunks, embedded and indexed with metadata; a query is embedded to retrieve nearby passages for an LLM. Vectors are meaningful only within the model that produced them, and they become outdated when source content changes. Production reliability therefore depends on versioning vectors, re-embedding changed documents, removing deleted content, monitoring index freshness and evaluating and tracing retrieval. Stale or missing passages can lead an agent to give confident but outdated answers.

### Source excerpt

A customer types "can I send this back?" Your help center never uses that phrase. It talks about the "return window" and the "refund policy." Keyword search finds nothing. Yet a modern AI agent pulls up the right policy in milliseconds, because it isn't matching words. It's matching meaning. That's what embeddings do. This guide ...

[Next page](<https://devfeed.tech/topics/embeddings.md?cursor=WyIyMDI2LTExLTE4VDE4OjU4OjEyKzAwOjAwIiwgIjdiZWE0M2QxLWQ5MjUtNDNmZC1hOGY0LWMyYTAxZDAzODRkYyJd>)