# VAE

A machine-learning method for variational inference and learning in directed probabilistic models with continuous latent variables.

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

## LIFT: Latent Flow Matching for Probabilistic Cell Fate Dynamics with Single Cell Snapshots

DevFeed: [LIFT: Latent Flow Matching for Probabilistic Cell Fate Dynamics with Single Cell Snapshots](<https://devfeed.tech/articles/lift-latent-flow-matching-for-probabilistic-cell-fate-dynamics-with-single-cell-snapshots-145117.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25917>)

Author: Bowen Yang, Junda Ying, Yuxuan Wang, Peijie Zhou, Lei Zhang

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

Content type: article

Language: en

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

Topics: [VAE](<https://devfeed.tech/topics/vae.md>), [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [decoder](<https://devfeed.tech/tags/decoder.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [error](<https://devfeed.tech/tags/error.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [fate](<https://devfeed.tech/tags/fate.md>), [flow](<https://devfeed.tech/tags/flow.md>), [flow-matching](<https://devfeed.tech/tags/flow-matching.md>), [framework](<https://devfeed.tech/tags/framework.md>), [future](<https://devfeed.tech/tags/future.md>), [generation](<https://devfeed.tech/tags/generation.md>), [inference](<https://devfeed.tech/tags/inference.md>), [learning](<https://devfeed.tech/tags/learning.md>), [monte-carlo](<https://devfeed.tech/tags/monte-carlo.md>), [one-to-many](<https://devfeed.tech/tags/one-to-many.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [probabilistic](<https://devfeed.tech/tags/probabilistic.md>), [sampling](<https://devfeed.tech/tags/sampling.md>), [single-cell](<https://devfeed.tech/tags/single-cell.md>)

### AI overview

LIFT models probabilistic cell fates from lineage-informed couplings, which connect cells through clonal ancestry without identifying unique source-to-descendant pairs. Variational inference represents alternative outcomes in a latent space, and a conditional prior allows sampling using only an initial cell state. Its Mean Flow decoder predicts the future state in a single evaluation per sample, supporting large-scale Monte Carlo prediction. The paper also analyzes conditional prediction error and reports experiments on synthetic and real datasets that recover population distributions and cell-fate probabilities.

### Source excerpt

arXiv:2611.25917v1 Announce Type: new Abstract: Lineage tracing links cell states through clonal ancestry, but does not generally identify unique source-descendant pairings. Learning from such data therefore requires a model of conditional outcomes, rather than only the terminal population distribution. We introduce LIFT, a latent flow framework for probabilistic cell-state generation from lineage-informed couplings. Variational inference encodes alternative outcomes in a latent space, while a conditional prior enables sampling from the initial state alone. A Mean Flow decoder predicts future cell state directly, requiring one decoder evaluation per sampling, which makes it convenient to predict cell fate through large scale Monte-Carlo sampling. This construction combines a representation of one-to-many relationships with efficient sampling and an analysis of conditional prediction error. Experiments on synthetic and real datasets demonstrate LIFT's ability to recover both population distribution and cell fate probabilities.

## Serialization Tax in Shared-Latent Exchangeable Decisions

DevFeed: [Serialization Tax in Shared-Latent Exchangeable Decisions](<https://devfeed.tech/articles/serialization-tax-in-shared-latent-exchangeable-decisions-145625.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26029>)

Author: Siming Zhang, Zhehui Shen, Shijie Chen, Xinle Gu, Yansen Yu, Hang Yu

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

Content type: article

Language: en

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

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [VAE](<https://devfeed.tech/topics/vae.md>)

Tags: [aggregate](<https://devfeed.tech/tags/aggregate.md>), [approximation](<https://devfeed.tech/tags/approximation.md>), [audits](<https://devfeed.tech/tags/audits.md>), [batch](<https://devfeed.tech/tags/batch.md>), [blocks](<https://devfeed.tech/tags/blocks.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [comparisons](<https://devfeed.tech/tags/comparisons.md>), [convex](<https://devfeed.tech/tags/convex.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [decision](<https://devfeed.tech/tags/decision.md>), [defer](<https://devfeed.tech/tags/defer.md>), [error](<https://devfeed.tech/tags/error.md>), [independent](<https://devfeed.tech/tags/independent.md>), [inspect](<https://devfeed.tech/tags/inspect.md>), [large](<https://devfeed.tech/tags/large.md>), [law](<https://devfeed.tech/tags/law.md>), [margin](<https://devfeed.tech/tags/margin.md>), [means](<https://devfeed.tech/tags/means.md>), [routing](<https://devfeed.tech/tags/routing.md>), [score](<https://devfeed.tech/tags/score.md>), [serialization](<https://devfeed.tech/tags/serialization.md>)

### AI overview

Independent item scoring can preserve each item's mean probability while losing shared latent-state dependence, leading to inaccurate group decisions such as slate display or batch inspection. The paper calls this error the "serialization tax." For binary items sharing a success rate, it reports that the exact count distribution is more dispersed than an independent completion with the same total mean, and connects approximation gaps to threshold separation and decision regret. TaxScore flags large hidden blocks with unresolved uncertainty near a decision boundary for routing to richer posterior heads. In pre-specified MovieLens 1M/10M audits, shared-latent heads improved high-score NLL/utility from 0.673/0.696 to 0.629/0.723 and 0.670/0.691 to 0.639/0.715; routing yielded 0.006-0.012 full-population utility gains. The abstract also says results cover non-binary outcomes, heterogeneous items, and sufficient posterior resolution.

### Source excerpt

arXiv:2611.26029v1 Announce Type: new Abstract: Accurate item probabilities can produce inaccurate group-level decisions. A system may score each item separately, yet act on whether enough hidden items succeed: show a slate, defer a panel decision, or inspect a batch. When items share an uncertain latent state, independent marginalization preserves means but removes dependence from the aggregate posterior. We call this error the serialization tax. For binary items sharing one success rate, classical convex-order comparisons give a more dispersed exact count law than any independent completion with the same total mean. We quantify variance and total-variation gaps, derive threshold separation under margin conditions, and connect posterior approximation to decision regret. Separate results cover non-binary outcomes, heterogeneous items, and sufficient posterior resolution. TaxScore identifies large hidden blocks with unresolved uncertainty near a decision boundary for routing to richer posterior heads. On pre-specified, hidden-target-free MovieLens 1M/10M audits, existing shared-latent heads improve high-score negative log-likelihood (NLL)/utility from 0.673/0.696 to 0.629/0.723 and from 0.670/0.691 to 0.639/0.715. Routing gives 0.006--0.012 full-population utility gains, with matched controls identifying their sources. Our code is available at https://github.com/SiminChang/Serialization-Tax-in-Shared-Latent-Exchangeable-Decisions.

## Statistical, Machine Learning and Deep Learning Methods for Missing Covariates: An Empirical Evaluation with Applications to Alzheimer's Disease Research

DevFeed: [Statistical, Machine Learning and Deep Learning Methods for Missing Covariates: An Empirical Evaluation with Applications to Alzheimer's Disease Research](<https://devfeed.tech/articles/statistical-machine-learning-and-deep-learning-methods-for-missing-covariates-an-empirical-evaluation-with-applications-to-alzheimer-s-disease-research-145025.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25219>)

Author: Yiqing Pan, Sharon X. Xie, Shujie Ma, Angela L. Jefferson, Panpan Zhang

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

Content type: comparison

Language: en

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

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Deep learning](<https://devfeed.tech/topics/deep-learning.md>), [VAE](<https://devfeed.tech/topics/vae.md>)

Tags: [adversarial](<https://devfeed.tech/tags/adversarial.md>), [aging](<https://devfeed.tech/tags/aging.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [application](<https://devfeed.tech/tags/application.md>), [applications](<https://devfeed.tech/tags/applications.md>), [autoencoders](<https://devfeed.tech/tags/autoencoders.md>), [bias](<https://devfeed.tech/tags/bias.md>), [biomarkers](<https://devfeed.tech/tags/biomarkers.md>), [biomedical](<https://devfeed.tech/tags/biomedical.md>), [case](<https://devfeed.tech/tags/case.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [confidence-interval](<https://devfeed.tech/tags/confidence-interval.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [disease](<https://devfeed.tech/tags/disease.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [research](<https://devfeed.tech/tags/research.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>)

### AI overview

The study evaluates eight methods for handling missing covariates in biomedical research, including complete-case analysis, multiple imputation, machine learning techniques, and deep learning frameworks such as multilayer perceptrons, variational autoencoders, and generative adversarial networks. Simulations compare estimation bias, efficiency, standard error accuracy, confidence interval coverage, and computational burden across missingness mechanisms and proportions. An application to the Vanderbilt Memory and Aging Project examines implications for regression analysis. The abstract says the study offers practical method-selection recommendations, but the supplied excerpt does not report which methods performed best.

### Source excerpt

arXiv:2611.25219v1 Announce Type: cross Abstract: Missing data are common in biomedical research, particularly when biomarkers are costly or require invasive procedures to obtain, such as cerebrospinal fluid measures in Alzheimer's disease. Although a wide range of missing data methods exists, from traditional statistical approaches to modern machine learning (ML) and deep learning (DL) algorithms, their comparative performance under different missingness mechanisms remains insufficiently understood. In this study, we provide an empirical evaluation of eight methods for handling missing covariates, including complete-case analysis, multiple imputation, ML-based techniques, and DL frameworks such as multilayer perceptrons, variational autoencoders, and generative adversarial networks. We summarize their conceptual foundations, practical implementation considerations, strengths, and limitations. Through extensive simulations, we assess estimation bias, efficiency, standard error accuracy, confidence interval coverage, and computational burden across different missingness mechanisms and proportions. An application to the Vanderbilt Memory and Aging Project further illustrates the implications of different methods for regression analysis in a real-world biomedical setting. Finally, we provide practical recommendations for method selection and highlight remaining challenges that warrant future investigation.

## Omni-modal decomposition autoencoders learn full-stack wearable disentangled representations

DevFeed: [Omni-modal decomposition autoencoders learn full-stack wearable disentangled representations](<https://devfeed.tech/articles/omni-modal-decomposition-autoencoders-learn-full-stack-wearable-disentangled-representations-144917.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.07385>)

Author: Ioannis Ziogas, Ensieh Khazaei, Bilal Taha, Aamna Al Shehhi, Ahsan H. Khandoker, Leontios J. Hadjileontiadis, Dimitrios Hatzinakos

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: [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [VAE](<https://devfeed.tech/topics/vae.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Self-supervised learning](<https://devfeed.tech/topics/self-supervised-learning.md>)

Tags: [autoencoders](<https://devfeed.tech/tags/autoencoders.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [eess-as](<https://devfeed.tech/tags/eess-as.md>), [eess-sp](<https://devfeed.tech/tags/eess-sp.md>), [full-stack](<https://devfeed.tech/tags/full-stack.md>), [fusion](<https://devfeed.tech/tags/fusion.md>), [generation](<https://devfeed.tech/tags/generation.md>), [series](<https://devfeed.tech/tags/series.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>), [vae](<https://devfeed.tech/tags/vae.md>), [wearable](<https://devfeed.tech/tags/wearable.md>)

### AI overview

Omni-modal Variational Decomposition Autoencoders (OmniDecVAEs) use a shared encoder-decoder to learn representations across heterogeneous wearable time-series modalities. They extend DecVAEs with per-modality time-frequency latent subspaces, a multi-view self-supervised decomposition loss, and a component-wise conditional decoder. On HARWE, UCI HAR, and WESAD, the abstract reports up to 3.0 percentage points higher DCI disentanglement for unseen subjects. On HARWE, results improve subject-dependent activity and identity recognition by 1.1 and 5.8 points; on unseen subjects in multi-device datasets, they exceed supervised end-to-end models by 31.6 and 22.3 points. Reconstruction error is 34-74% lower than with multi-modal VAEs, and synthetic data improve unseen-subject affect recognition by 2 points. The model has 4.1 million parameters, with parameter count reported as invariant to modality count and 21 times fewer parameters than a multi-branch VAE.

### Source excerpt

arXiv:2608.07385v2 Announce Type: replace Abstract: Learning disentangled representations is key for general-purpose multi-modal wearable models, yet existing approaches rarely combine classification, disentanglement, fusion, and generation of heterogeneous multi-modal time series in a single model. We introduce Omni-modal Variational Decomposition Autoencoders (OmniDecVAEs), a framework that learns multi-purpose representations from arbitrarily many modalities with a single shared encoder-decoder. OmniDecVAEs extend DecVAEs by learning time-frequency latent subspaces per modality through a multi-view self-supervised decomposition loss and a component-wise conditional decoder. On the omni-modal human activity recognition (HAR) HARWE dataset (up to thirty channels) and the public UCI HAR and WESAD datasets, OmniDecVAEs learn the most disentangled representations for unseen subjects (DCI disentanglement up to 3.0 percentage points (pp) higher). On HARWE, they improve subject-dependent HAR and identity recognition by 1.1 pp and 5.8 pp, and outperform supervised end-to-end models by +31.6 pp and +22.3 pp on unseen subjects of multi-device datasets. Moreover, their generative capacity improves reconstruction mean squared error over multi-modal VAEs (34-74% improvement) and their synthetic data improve affect recognition on unseen subjects (2 pp). With 4.1M parameters, invariant to the number of modalities (21xfewer than a multi-branch VAE), OmniDecVAEs are scalable, single-model full-stack learners for wearable representations.

## Process-Knowledge-Guided Latent Diffusion for Generative Design of Porous Architectures: A Case Study in Aerosol Jet Printing

DevFeed: [Process-Knowledge-Guided Latent Diffusion for Generative Design of Porous Architectures: A Case Study in Aerosol Jet Printing](<https://devfeed.tech/articles/process-knowledge-guided-latent-diffusion-for-generative-design-of-porous-architectures-a-case-study-in-aerosol-jet-printing-145030.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25264>)

Author: Ngoc Dang Khoa Nguyen, Hyunwoong Ko

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

Content type: article

Language: en

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

Topics: [stable-diffusion](<https://devfeed.tech/topics/stable-diffusion.md>), [VAE](<https://devfeed.tech/topics/vae.md>)

Tags: [autoencoder](<https://devfeed.tech/tags/autoencoder.md>), [cs-ce](<https://devfeed.tech/tags/cs-ce.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [design](<https://devfeed.tech/tags/design.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [flow](<https://devfeed.tech/tags/flow.md>), [generative](<https://devfeed.tech/tags/generative.md>), [generative-design](<https://devfeed.tech/tags/generative-design.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [printing](<https://devfeed.tech/tags/printing.md>), [process](<https://devfeed.tech/tags/process.md>), [sampling](<https://devfeed.tech/tags/sampling.md>), [score](<https://devfeed.tech/tags/score.md>), [topology](<https://devfeed.tech/tags/topology.md>)

### AI overview

The study shows that process knowledge can steer latent diffusion toward porous layouts with lower process-dependent utilization scores. Its generator combines a VQ-VAE latent representation, topology U-Net, ControlNet branch for domain conditioning, and a separately trained score regressor whose gradient guides denoising. For aerosol jet printing, atomizer and sheath gas flows enter the score through a flow-focusing relation. Across seven modeled flow settings, the lowest-scoring layout differed between settings in 191 of 500 design domains. In sampling tests on three validation domains and one test domain, mean directly computed scores fell from 0.642 with domain conditioning alone to 0.636 at steering weight 300 and 0.450 at 12,000 (112 scores per weight; lower is better). These findings apply under the paper's stated assumptions.

### Source excerpt

arXiv:2611.25264v1 Announce Type: new Abstract: Printed porous layouts interleave functional material with open channels, and the layout that uses the material best depends on how the process settings shape the deposit. Generative models propose layouts quickly, but a generator that does not receive the process setting samples from the same distribution at every setting, even when the process-dependent score ranks candidate layouts differently. This paper examines whether process knowledge can steer a latent diffusion generator toward layouts suited to a given process setting in a prescribed design domain. We formulate a process-dependent utilization score in which a process model sets the length over which the utility of printed material decays with distance from a channel. The generator combines a vector-quantized variational autoencoder (VQ-VAE) latent representation, a topology U-Net, a ControlNet domain branch, and a separately trained regressor that predicts the score from noised latents; the domain branch conditions each denoising step and the regressor gradient steers it. The method is applied to aerosol jet printing, where the atomizer and sheath gas flows enter the score through the flow-focusing relation. Across seven modeled flow settings, the lowest-scoring candidate layout of a domain differed between settings in 191 of 500 domains. In a sampling study, the mean directly computed score on three validation domains and one test domain was 0.642 with domain conditioning alone, 0.636 at a weight of 300, and 0.450 at 12,000 (112 scores per weight; lower is better). The results support process-knowledge-guided generation as an approach to process-specific porous design under the stated assumptions.

## Towards Autoregressive Neural Network Parameter Generation

DevFeed: [Towards Autoregressive Neural Network Parameter Generation](<https://devfeed.tech/articles/towards-autoregressive-neural-network-parameter-generation-145068.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25538>)

Author: Bedionita Soro, Bruno Andreis, Song Chong, Sung Ju Hwang

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: [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [VAE](<https://devfeed.tech/topics/vae.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [autoregressive](<https://devfeed.tech/tags/autoregressive.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [generation](<https://devfeed.tech/tags/generation.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [model](<https://devfeed.tech/tags/model.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [parameter](<https://devfeed.tech/tags/parameter.md>), [performance](<https://devfeed.tech/tags/performance.md>)

### AI overview

Instruction-Guided Parameter Generation (IGPG) generates neural network parameters by first quantizing pretrained weights with a VQ-VAE, then training a prefix-conditioned autoregressive model on the resulting tokens. At inference, the VQ-VAE decoder maps generated tokens back into parameter space. The abstract reports competitive in-distribution generation and useful initializations for held-out datasets and architectures; after adaptation, these improve downstream performance over random initialization. The work evaluates in-distribution generation, cross-dataset transfer, and cross-architecture settings, but the supplied text gives no quantitative results or details about the evaluation.

### Source excerpt

arXiv:2611.25538v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently established a new paradigm in machine learning, demonstrating exceptional zero-shot generalization and complex reasoning capabilities. Concurrently, neural network parameter generation has emerged as a promising avenue for rapid task adaptation and model synthesis. Existing weight generation techniques, however, struggle to jointly learn the distribution of diverse models, to encode heterogeneous architectures within a single generator, and to generalize out of distribution. We therefore ask whether pretrained parameters can be encoded into a discrete domain so that the zero-shot generalization LLMs exhibit in text generation can be transferred to weight generation. Following this view, we propose an LLM-inspired approach, Instruction-Guided Parameter Generation (IGPG), that formulates network parameter generation as an autoregressive modeling problem. We first quantize pretrained weights with a VQ-VAE, then train a prefix-conditioned autoregressive generator over the resulting tokens. At inference, the generated weight tokens are mapped back to parameter space by the VQ-VAE decoder. We evaluate the framework across in-distribution generation, cross-dataset transfer, and cross-architecture settings. The proposed method achieves competitive performance in in-distribution generation and provides useful parameter initializations for held-out datasets and architectural configurations, improving downstream performance over random initialization after adaptation. These results suggest that discrete autoregressive modeling provides a promising framework for learning and transferring structure across collections of pretrained neural network parameters.

## Exact Bayesian layers via characteristic functions

DevFeed: [Exact Bayesian layers via characteristic functions](<https://devfeed.tech/articles/exact-bayesian-layers-via-characteristic-functions-145180.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26426>)

Author: William H. W. Thompson, Guillaume St-Onge, Laurent H\\'ebert-Dufresne, Jean-Gabriel Young

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

Content type: article

Language: en

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

Topics: [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [VAE](<https://devfeed.tech/topics/vae.md>), [Error Propagation](<https://devfeed.tech/topics/error-propagation.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [bayesian](<https://devfeed.tech/tags/bayesian.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [inference](<https://devfeed.tech/tags/inference.md>), [layers](<https://devfeed.tech/tags/layers.md>), [networks](<https://devfeed.tech/tags/networks.md>), [stat-co](<https://devfeed.tech/tags/stat-co.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>), [uncertainty](<https://devfeed.tech/tags/uncertainty.md>)

### AI overview

CF-Prop uses characteristic functions to compute the exact output distribution of a Bayesian ReLU layer without sampling, including in non-Gaussian settings. This enables CF-VI to calculate the variational evidence lower bound in closed form for likelihoods including Gaussian, Poisson, and Gamma. In the reported experiments, CF-VI had the lowest calibration error among tested methods on CIFAR-100, about 35% better than the next best, and captured tail uncertainty on a heavy-tailed insurance claims dataset that other sampling-free and Monte Carlo methods substantially underestimated.

### Source excerpt

arXiv:2611.26426v1 Announce Type: cross Abstract: Bayesian neural networks provide principled uncertainty estimates, but training them with Monte Carlo sampling can be expensive. Sampling-free variational inference algorithms make training Bayesian neural networks feasible, but existing approaches assume a Gaussian output distribution, which can be inaccurate in applied problems. Here, we introduce CF-Prop, an uncertainty propagation method that uses characteristic functions to compute the exact output distribution of a Bayesian ReLU layer, without any sampling, even in non-Gaussian settings. Because CF-Prop propagates characteristic functions, the evidence lower bound---the objective of variational training---can be computed in closed form for a broad class of likelihoods, including the Gaussian, Poisson, and Gamma. This allows to implement an efficient resulting variational inference algorithm, CF-VI. On CIFAR-100, CF-VI achieves the lowest calibration error of any tested method, improving on the next best method by about 35%. On a heavy-tailed insurance claim dataset, CF-VI accurately captures tail uncertainty that is severely underestimated by both other sampling-free methods and Monte Carlo methods.

## Uncertainty-aware damage identification in short-span bridges via physics-informed variational autoencoder

DevFeed: [Uncertainty-aware damage identification in short-span bridges via physics-informed variational autoencoder](<https://devfeed.tech/articles/uncertainty-aware-damage-identification-in-short-span-bridges-via-physics-informed-variational-autoencoder-143287.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.05025>)

Author: Ana Fernandez-Navamuel, A. Javier Omella, Diego Zamora-Sanchez, David Pardo

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

Content type: article

Language: en

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

Topics: [VAE](<https://devfeed.tech/topics/vae.md>), [Physics-guided deep learning](<https://devfeed.tech/topics/physics-guided-deep-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Finite Element Method (FEM)](<https://devfeed.tech/topics/finite-element-method.md>)

Tags: [autoencoder](<https://devfeed.tech/tags/autoencoder.md>), [bridge](<https://devfeed.tech/tags/bridge.md>), [bridges](<https://devfeed.tech/tags/bridges.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [health-monitoring](<https://devfeed.tech/tags/health-monitoring.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [physics-informed](<https://devfeed.tech/tags/physics-informed.md>), [probabilistic](<https://devfeed.tech/tags/probabilistic.md>), [uncertainty](<https://devfeed.tech/tags/uncertainty.md>), [uncertainty-quantification](<https://devfeed.tech/tags/uncertainty-quantification.md>)

### AI overview

The proposed physics-informed Gaussian copula variational autoencoder estimates bridge damage and diagnostic uncertainty from vibration data. It embeds a numerical eigenvalue solver as its decoder, so posterior samples satisfy structural dynamics equations, and uses a Gaussian copula to capture correlations among stiffness reduction factors with fewer parameters than Gaussian mixtures. In a numerical short-span bridge study with elastic bearings, modeling errors, measurement noise, and a finer test discretization, its damage posteriors closely matched sequential Monte Carlo estimates. The method can indicate damage location while representing uncertainty, including cases where noise masks light damage or modal properties are weakly sensitive to damage.

### Source excerpt

arXiv:2607.05025v3 Announce Type: replace Abstract: Vibration-based damage identification in civil infrastructure is a challenging, ill-posed inverse problem due to measurement noise, sparse sensor arrays, and modeling errors. While deep learning is powerful for system identification, deterministic approaches lack reliable uncertainty quantification and can yield physically inconsistent results. This work proposes a probabilistic Scientific Machine Learning framework for structural health monitoring: a physics-informed Gaussian copula variational autoencoder. The methodology introduces two main contributions. First, a numerical eigenvalue solver is embedded directly into the variational autoencoder as its decoder, which replaces data-driven surrogates, ensures that every posterior sample satisfies the governing equations of structural dynamics, and reduces the number of trainable parameters. Second, a Gaussian copula describes the posterior distribution of the stiffness factors, capturing cross-correlations between components with fewer parameters than Gaussian mixtures in real time. We validate the method numerically on a short-span bridge supported on elastic bearings, whose response is dominated by vertical bending, accounting for modeling errors, measurement noise, and a finer finite element discretization for testing. The method estimates the posterior distribution of the damage condition, i.e., the stiffness reduction factors of the deck zones and bearings, and these posteriors closely match the exact ones computed with sequential Monte Carlo sampling. The results reveal that the proposed methodology offers a robust and interpretable decision-making tool, able not only to indicate the presence and location of damage, but also to inform on the uncertainty associated with the diagnosis, for instance, when light damage is masked by the effect of noise or when the measured modal properties present limited sensitivity to damage.

## Controllable Generative Trajectory Prediction via Weak Preference Alignment

DevFeed: [Controllable Generative Trajectory Prediction via Weak Preference Alignment](<https://devfeed.tech/articles/controllable-generative-trajectory-prediction-via-weak-preference-alignment-143221.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2510.10731>)

Author: Yongxi Cao, Julian F. Schumann, Jens Kober, Joni Pajarinen, Arkady Zgonnikov

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

Content type: article

Language: en

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

Topics: [VAE](<https://devfeed.tech/topics/vae.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-vehicle](<https://devfeed.tech/tags/autonomous-vehicle.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [diversity](<https://devfeed.tech/tags/diversity.md>), [generative](<https://devfeed.tech/tags/generative.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [supervision](<https://devfeed.tech/tags/supervision.md>)

### AI overview

PrefCVAE adds weakly labeled preference pairs to a conditional variational autoencoder so its latent variables represent semantic attributes and can steer trajectory generation. Using average velocity as an example, the authors report controllable, semantically meaningful predictions without degrading baseline accuracy. The abstract presents preference supervision as a cost-effective way to make generated trajectories more useful for safe planning than random diversity; it does not provide details on evaluation settings or other attributes.

### Source excerpt

arXiv:2510.10731v3 Announce Type: replace-cross Abstract: Deep generative models such as conditional variational autoencoders (CVAEs) have shown great promise for predicting trajectories of surrounding agents in autonomous vehicle planning. State-of-the-art models have achieved remarkable accuracy in such prediction tasks. Besides accuracy, diversity is also crucial for safe planning because human behaviors are inherently uncertain and multimodal. However, existing methods generally lack a scheme to generate controllably diverse trajectories, which is arguably more useful than randomly diversified trajectories, to the end of safe planning. To address this, we propose PrefCVAE, an augmented CVAE framework that uses weakly labeled preference pairs to imbue latent variables with semantic attributes. Using average velocity as an example attribute, we demonstrate that PrefCVAE enables controllable, semantically meaningful predictions without degrading baseline accuracy. Our results show the effectiveness of preference supervision as a cost-effective way to enhance sampling-based generative models.

## Risk-Triggered Search: Behavior-Preserving Safe Control

DevFeed: [Risk-Triggered Search: Behavior-Preserving Safe Control](<https://devfeed.tech/articles/risk-triggered-search-behavior-preserving-safe-control-142792.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24409>)

Author: Xinyu Deng, Bohao Lan, Kunpeng Li, Mingkai Yuan, Weihang Pan, Binbin Lin

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

Content type: article

Language: en

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

Topics: [safety mechanism](<https://devfeed.tech/topics/safety-mechanism.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>), [VAE](<https://devfeed.tech/topics/vae.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [control](<https://devfeed.tech/tags/control.md>), [controller](<https://devfeed.tech/tags/controller.md>), [cross-entropy-method](<https://devfeed.tech/tags/cross-entropy-method.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [navigation](<https://devfeed.tech/tags/navigation.md>), [risk](<https://devfeed.tech/tags/risk.md>), [search](<https://devfeed.tech/tags/search.md>), [world-models](<https://devfeed.tech/tags/world-models.md>)

### AI overview

Risk-Triggered Search (RTS) aims to prevent process violations in frozen JEPA visual world models while preserving safe nominal behavior. It predicts risk by unrolling action-conditioned latent prefixes and training a lightweight risk head with process-violation supervision. Safe plans execute directly; alarms trigger local Cross-Entropy Method search constrained by the same risk criterion. An amplitude-preserving metric is designed to retain tangential progress and avoid stalling. In the reported five-task benchmark, RTS improved Safe Arrival Rate over Direct by 12.67-41.67 percentage points on navigation and articulated-control tasks and 2.08/4.17 points on Cube/PushT boundary cohorts. Across 1,968 paired trajectories, it matched every-step search in action identity and reduced controller time by 17.71%-70.41%.

### Source excerpt

arXiv:2611.24409v1 Announce Type: new Abstract: Pre-trained visual world models generate multi-step action plans from current and goal observations, yet terminal-proximity objectives fail to prevent forbidden-zone traversal or rigid-body collision sliding. Purely visual interfaces may lack analytical dynamics, structured states, or explicit collision geometry, requiring internal prediction of action-conditioned process risk. We propose Risk-Triggered Search (RTS) for frozen Joint-Embedding Predictive Architecture (JEPA) world models. Rather than relying on static state features that cannot distinguish candidate plans sharing an observation, RTS unrolls action-conditioned future latent prefixes in the frozen world model and trains a lightweight risk head with process-violation supervision. To intervene selectively while preserving safe nominal behavior, RTS uses the same predicted prefix-risk criterion as both the search trigger gate and hard feasibility gate: safe nominal plans execute directly, whereas alarms trigger local Cross-Entropy Method (CEM) search to minimize nominal deviation within the feasible set. To prevent isotropic Euclidean minimal modification from shrinking obstacle-directed actions into zero-amplitude stalling, we introduce an amplitude-preserving metric $d_{\mathrm{AP}}$ that retains tangential progression while maintaining a unique zero at the nominal plan. Under unified gating and this unique-zero condition, bypassing safe-state search yields closed-loop trajectories strictly identical to every-step same-kernel search. Evaluated under a process-safety benchmark and Safe Arrival Rate (SAR) metric across five tasks, RTS improves SAR over Direct by 12.67--41.67 percentage points on navigation and articulated control and +2.08/+4.17 pp on Cube/PushT boundary cohorts, maintaining 100% action identity with every-step search while cutting controller time by 17.71%--70.41% across 1,968 paired trajectories.

## Dual-Manifold Variational Autoencoders

DevFeed: [Dual-Manifold Variational Autoencoders](<https://devfeed.tech/articles/dual-manifold-variational-autoencoders-142732.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23964>)

Author: Hongxu Chen, Chun Wang, Yanghao Wang, Hongxiang Li, Zhen Wang, Zhixiang Zhang, Long Chen

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

Content type: article

Language: en

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

Topics: [VAE](<https://devfeed.tech/topics/vae.md>), [stable-diffusion](<https://devfeed.tech/topics/stable-diffusion.md>), [ImageNet](<https://devfeed.tech/topics/imagenet.md>)

Tags: [alignment](<https://devfeed.tech/tags/alignment.md>), [autoencoders](<https://devfeed.tech/tags/autoencoders.md>), [cfg](<https://devfeed.tech/tags/cfg.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [dimension](<https://devfeed.tech/tags/dimension.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [domains](<https://devfeed.tech/tags/domains.md>), [drift](<https://devfeed.tech/tags/drift.md>), [features](<https://devfeed.tech/tags/features.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [foundation-model](<https://devfeed.tech/tags/foundation-model.md>), [generation](<https://devfeed.tech/tags/generation.md>), [generator](<https://devfeed.tech/tags/generator.md>), [guidance](<https://devfeed.tech/tags/guidance.md>), [inference](<https://devfeed.tech/tags/inference.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [space](<https://devfeed.tech/tags/space.md>), [subspace](<https://devfeed.tech/tags/subspace.md>), [training](<https://devfeed.tech/tags/training.md>), [ts](<https://devfeed.tech/tags/ts.md>)

### AI overview

DM-VAE addresses off-manifold drift in high-dimensional VAE latents by pairing a reconstructive branch with a low-dimensional branch that supplies a smooth topological skeleton to anchor the latent manifold. It avoids relying on a frozen foundation model as its primary regularizer. Topological representation alignment (TRA) supervises intermediate generator features during training; internal guidance with topological skeleton (IG_TS) guides structural components at inference while preserving high-frequency detail. On ImageNet-1K at 256x256, the foundation-model-free method reports rFID 0.12 and FID50K 1.28 without classifier-free guidance (CFG), or 1.20 with CFG. Combined orthogonally with DINOv2, it reports FID50K 1.11.

### Source excerpt

arXiv:2611.23964v1 Announce Type: cross Abstract: In latent diffusion models, expanding the latent dimension of variational autoencoders (VAEs) is essential to push the upper bound of reconstruction quality. However, without explicit structural constraints, such unregularized expansion easily yields a rugged and ill-conditioned latent manifold, causing generated latents to drift off the manifold during generation (i.e., off-manifold problem). Recent works smooth this manifold by using external foundation models (e.g., DINOv2) as a topological regularizer. However, we argue that tying the latent space to frozen external priors inherently restricts generalization: bound by their pre-training distributions and semantic biases, they may fail to capture faithful visual details on out-of-distribution domains. Observing that low-dimensional latents naturally form a smoother, generation-friendly manifold, we propose dual-manifold VAE (DM-VAE) to leverage internal representations as a topological regularizer. Specifically, DM-VAE pairs a high-dimensional reconstructive branch with a low-dimensional branch that extracts a clean topological skeleton, anchoring the high-dimensional manifold to this smooth subspace. Building upon this framework, we further introduce topological representation alignment (TRA) to supervise intermediate generator features during training, and internal guidance with topological skeleton (IG_TS) to guide structural components while preserving high-frequency details at inference. On ImageNet-1K (256x256), our foundation-model-free DM-VAE achieves a state-of-the-art rFID of 0.12 and a generation FID50K of 1.28 (w/o CFG) and 1.20 (w/CFG), and further reaches 1.11 when orthogonally combined with DINOv2.

## Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RL

DevFeed: [Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RL](<https://devfeed.tech/articles/efficient-generative-retrieval-for-e-commerce-search-with-semantic-cluster-ids-and-expert-guided-rl-139770.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.14434>)

Author: Jianbo Zhu, Xing Fang, Jing Wang, Mingmin Jin, Bokang Wang, Guangxin Song, Zhenyu Xie, Junjie Bai

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

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

Topics: [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [grpo](<https://devfeed.tech/topics/grpo.md>), [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [VAE](<https://devfeed.tech/topics/vae.md>)

Tags: [beam](<https://devfeed.tech/tags/beam.md>), [cluster](<https://devfeed.tech/tags/cluster.md>), [contrastive-learning](<https://devfeed.tech/tags/contrastive-learning.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [e-commerce](<https://devfeed.tech/tags/e-commerce.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generative](<https://devfeed.tech/tags/generative.md>), [group-relative-policy-optimization](<https://devfeed.tech/tags/group-relative-policy-optimization.md>), [grpo](<https://devfeed.tech/tags/grpo.md>), [ids](<https://devfeed.tech/tags/ids.md>), [learning](<https://devfeed.tech/tags/learning.md>), [offline](<https://devfeed.tech/tags/offline.md>), [online](<https://devfeed.tech/tags/online.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [performance](<https://devfeed.tech/tags/performance.md>), [policy](<https://devfeed.tech/tags/policy.md>), [production](<https://devfeed.tech/tags/production.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [rl](<https://devfeed.tech/tags/rl.md>), [search](<https://devfeed.tech/tags/search.md>), [semantic](<https://devfeed.tech/tags/semantic.md>)

### AI overview

The framework positions generative retrieval as a recall-stage supplement to existing e-commerce search, addressing catalog scale, latency, and downstream ranking alignment. CQ-SID combines category-aware and query-item contrastive learning with Residual Quantized VAEs to create hierarchical semantic IDs and reduce beam-search complexity. On TmallAPP search logs, it improves semantic and personalized click hitrate by up to 26.76% and 11.11% over RQ-VAE baselines while halving beam-search size. EG-GRPO uses ground-truth samples to stabilize reinforcement learning under sparse rewards and further improves multi-objective performance. Online A/B tests report GMV gains of 1.15% and UCTCVR gains of 0.40%; in production, the generative recall channel accounts for 50.25% of exposures, 58.96% of clicks, and 72.63% of purchases.

### Source excerpt

arXiv:2605.14434v2 Announce Type: replace-cross Abstract: Generative retrieval offers a promising alternative by unifying the fragmented multi-stage retrieval process into a single end-to-end model. However, its practical adoption in industrial e-commerce search remains challenging, given the massive and dynamic product catalogs, strict latency requirements, and the need to align retrieval with downstream ranking goals. In this work, we propose a retrieval framework tailored for real-world recall scenarios, positioning generative retrieval as a recall-stage supplement rather than an end-to-end replacement. Our method, CQ-SID (Category-and-Query constrained Semantic ID), employs category-aware and query-item contrastive learning along with Residual Quantized VAEs to encode items into hierarchical semantic cluster identifiers, significantly reducing beam search complexity. Additionally, we develop EG-GRPO (Expert-Guided Group Relative Policy Optimization), a reinforcement learning approach that aligns generative recall with downstream ranking under sparse rewards by injecting ground-truth samples to stabilize training. Offline experiments on TmallAPP search logs show that CQ-SID achieves up to 26.76% and 11.11% relative gains in semantic and personalized click hitrate over RQ-VAE baselines, while halving beam search size. EG-GRPO further improves multi-objective performance. Online A/B tests confirm gains in GMV (+1.15%) and UCTCVR (+0.40%). The generative recall channel now contributes substantially in production, accounting for over 50.25% of exposures, 58.96% of clicks, and 72.63% of purchases, demonstrating a viable path for deploying generative retrieval in real-world e-commerce systems.

## Modeling Document and Section Hierarchies in Embedding Space

DevFeed: [Modeling Document and Section Hierarchies in Embedding Space](<https://devfeed.tech/articles/modeling-document-and-section-hierarchies-in-embedding-space-139942.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21980>)

Author: Kriste Krstovski, Sharyn O'Halloran, Kshitij Chandna

Published: 2026-11-18T05:00:00Z

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: [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [VAE](<https://devfeed.tech/topics/vae.md>), [clustering](<https://devfeed.tech/topics/clustering.md>)

Tags: [clustering](<https://devfeed.tech/tags/clustering.md>), [coherent](<https://devfeed.tech/tags/coherent.md>), [company](<https://devfeed.tech/tags/company.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [discussion](<https://devfeed.tech/tags/discussion.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [domains](<https://devfeed.tech/tags/domains.md>), [embedded](<https://devfeed.tech/tags/embedded.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [flat](<https://devfeed.tech/tags/flat.md>), [forums](<https://devfeed.tech/tags/forums.md>), [government](<https://devfeed.tech/tags/government.md>), [inference](<https://devfeed.tech/tags/inference.md>), [legal](<https://devfeed.tech/tags/legal.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [models](<https://devfeed.tech/tags/models.md>), [performance](<https://devfeed.tech/tags/performance.md>), [perplexity](<https://devfeed.tech/tags/perplexity.md>), [quality](<https://devfeed.tech/tags/quality.md>), [reports](<https://devfeed.tech/tags/reports.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>)

### AI overview

The Hierarchical Embedded Topic Model (hETM) addresses the fact that flat embedded topic models assign one topic distribution to an entire document, overlooking distinct section topics. It couples document and section topic distributions through a hierarchical prior in embedding space and uses amortized variational inference. On structured collections of legal documents, reports and online discussions, hETM achieved the lowest or near-lowest held-out perplexity among flat and hierarchical baselines, with comparable or higher topic quality. It also had the best clustering performance on most collections.

### Source excerpt

arXiv:2611.21980v1 Announce Type: cross Abstract: Embedded topic models integrate word embeddings into the topic generation process, producing coherent topics and robust performance on large vocabularies. However, each document is represented by a single topic distribution, ignoring its internal structure. Many real world collections, including legal documents, company and government reports, and online discussion forums, exhibit hierarchical organization in which documents consist of multiple sections that often address distinct subtopics. We introduce the Hierarchical Embedded Topic Model (hETM), a structured topic model that couples the topic distribution of a document and those of its sections through a hierarchical prior in the embedding space. We derive an amortized variational inference procedure for hETM and evaluate it on structured collections from each of these domains. Experimental results show that hETM achieves the lowest or near-lowest held-out perplexity among flat and hierarchical topic model baselines, along with comparable or higher topic quality. It also performs strongly on a downstream clustering task, achieving the best clustering performance on most of the collections.

## Residual-Tail-Informed Flow Matching for Time Series Anomaly Detection

DevFeed: [Residual-Tail-Informed Flow Matching for Time Series Anomaly Detection](<https://devfeed.tech/articles/residual-tail-informed-flow-matching-for-time-series-anomaly-detection-137563.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20334>)

Author: Shyam Sundar Saravanan, Tie Luo, Sanjay Madria

Published: 2026-11-17T05:00:00Z

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: [Time Series](<https://devfeed.tech/topics/time-series.md>), [AI Models](<https://devfeed.tech/topics/ai-models.md>), [VAE](<https://devfeed.tech/topics/vae.md>), [Temporal data](<https://devfeed.tech/topics/temporal-data.md>)

Tags: [anomaly-detection](<https://devfeed.tech/tags/anomaly-detection.md>), [autoencoder](<https://devfeed.tech/tags/autoencoder.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [flow-matching](<https://devfeed.tech/tags/flow-matching.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [time-series](<https://devfeed.tech/tags/time-series.md>)

### AI overview

RT-FM targets false alarms on rare but valid time-series regimes that data-space flow matching may score like true anomalies. It uses a temporal variational autoencoder to estimate residual latent tailness, then turns that estimate into bounded, warmup-annealed weights for training an unsupervised data-space flow-matching model. Across seven TSAD benchmarks, the authors report better rare-normal coverage, fewer false alarms on those windows, and improved aggregate detection while preserving strong anomaly discrimination.

### Source excerpt

arXiv:2611.20334v1 Announce Type: cross Abstract: Time series anomaly detection (TSAD) models are often trained on nominal data using average-risk objectives, which emphasize dominant normal patterns. However, real time series can contain rare but valid nominal regimes that are underrepresented in the training distribution. We show that data-space flow matching can over-penalize such rare-normal windows and assign them anomaly scores comparable to those of true anomalies. To address this, we propose Residual-Tail-Informed Flow Matching (RT-FM), an unsupervised framework that uses a temporal variational autoencoder to estimate residual latent tailness and converts it into bounded, warmup-annealed weights for training a data-space flow matching model. Experiments on seven TSAD benchmarks show that RT-FM improves rare-normal coverage while preserving strong anomaly discrimination, substantially reducing false alarms on such windows and resulting in improved aggregate detection performance. The code is available at: https://github.com/trustAIoT/RT-FM_time-series-anomaly

## Integrating Latent Block Models into Variational Autoencoders for Disentangled Representation Learning

DevFeed: [Integrating Latent Block Models into Variational Autoencoders for Disentangled Representation Learning](<https://devfeed.tech/articles/integrating-latent-block-models-into-variational-autoencoders-for-disentangled-representation-learning-137552.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20253>)

Author: Anasse Essalih, Reda Khoufache, Laurent Durville, Mohamed-Cherif Rahal, Mustapha Lebbah, Hanene Azzag, Walid Kheriji, Fouad Hadj Selem

Published: 2026-11-17T05:00:00Z

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: [VAE](<https://devfeed.tech/topics/vae.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [clustering](<https://devfeed.tech/topics/clustering.md>)

Tags: [autoencoders](<https://devfeed.tech/tags/autoencoders.md>), [block](<https://devfeed.tech/tags/block.md>), [clustering](<https://devfeed.tech/tags/clustering.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [dimensions](<https://devfeed.tech/tags/dimensions.md>), [framework](<https://devfeed.tech/tags/framework.md>), [groups](<https://devfeed.tech/tags/groups.md>), [inference](<https://devfeed.tech/tags/inference.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [representation-learning](<https://devfeed.tech/tags/representation-learning.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>), [structured](<https://devfeed.tech/tags/structured.md>)

### AI overview

LBM-VAE combines Latent Block Models with variational autoencoders to jointly cluster observations and latent dimensions. Its block-structured representation can encode factors of variation across groups of latent dimensions, rather than assigning each factor to a single dimension. The abstract reports promising clustering performance and competitive disentangled representation learning, but provides no experimental details or comparisons.

### Source excerpt

arXiv:2611.20253v1 Announce Type: cross Abstract: We introduce LBM-VAE, a novel framework that integrates Latent Block Models (LBMs) into Variational Autoencoders (VAEs) to jointly cluster observations and latent dimensions. Beyond its clustering capabilities, LBM-VAE provides a block-structured latent representation that naturally supports disentangled representation learning. In contrast to conventional approaches that associate each factor of variation with an individual latent dimension, our framework allows factors of variation to be encoded across groups of latent dimensions. Experimental results demonstrate the promising clustering performance of LBM-VAE, while achieving competitive results in disentangled representation learning. LBM-VAE highlights the potential of combining co-clustering and variational inference to learn structured and interpretable latent representations.

## PlanDiv: Test-Time Scaling with Latent Plans for Vision-Language-Action Models

DevFeed: [PlanDiv: Test-Time Scaling with Latent Plans for Vision-Language-Action Models](<https://devfeed.tech/articles/plandiv-test-time-scaling-with-latent-plans-for-vision-language-action-models-138975.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20010>)

Author: Hanbo Zhang, Lianlei Shan, Liuhaichen Yang, Zezhi Tang

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

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

Topics: [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [diffusion-transformers](<https://devfeed.tech/topics/diffusion-transformers.md>), [VAE](<https://devfeed.tech/topics/vae.md>)

Tags: [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [vision-language-action](<https://devfeed.tech/tags/vision-language-action.md>), [vision-language-action-models](<https://devfeed.tech/tags/vision-language-action-models.md>)

### AI overview

PlanDiv improves test-time scaling for vision-language-action policies by making action candidates represent different latent plans instead of resampling noise from one decoder. A lightweight planner proposes plans learned from demonstrations, and a shared masked-diffusion executor produces an action chunk for each; the policy selects the chunk with the highest likelihood. With the backbone, data, and training recipe held fixed, eight candidates raised CALVIN five-task chain success from 56.9% to 69.9%, while matched alternatives reached at most 64.9%. On LIBERO-Long, four plans removed 40% of single-candidate failures, versus at most 21% for matched resampling. On a real Franka arm, PlanDiv matched the single-output baseline on a task with one solution and succeeded in 51 of 54 trials versus 40 of 54 across two tasks with two solutions.

### Source excerpt

arXiv:2611.20010v1 Announce Type: cross Abstract: Test-time scaling improves vision-language-action (VLA) policies by drawing several action candidates and executing the best one. We find that its returns diminish quickly when the candidates are resampled from one decoder: they differ by noise rather than by plan, and for each of three resampling sources, going from four to eight candidates adds only 0.06-0.07 to the average number of completed tasks on CALVIN. We introduce PlanDiv, an action head that makes the candidates differ by plan: a lightweight planner proposes K latent plan hypotheses, a shared masked-diffusion executor decodes one action chunk per plan from a single backbone pass, and the policy executes the chunk that its own likelihood ranks highest. The plans are learned from demonstrations alone, without plan labels or rewards. With the backbone, data and training recipe held fixed, eight plan-conditioned candidates raise five-task chain success on CALVIN ABC$\rightarrow$D from 56.9% to 69.9%, while eight candidates from autoregressive, plan-free or same-plan resampling reach at most 64.9%. The same-plan baseline is PlanDiv's own checkpoint with the plan held fixed, so this gap comes from the plans, not from drawing more samples. On LIBERO-Long, four plans remove 40% of single-candidate failures, against at most 21% for matched resampling. On a real Franka arm the gain appears where a task admits more than one solution: PlanDiv is on par with a single-output OpenVLA-OFT+ baseline on a one-solution task and succeeds in 51 of 54 trials against 40 of 54 on two tasks with two solutions.

## The structure of variational autoencoder latent spaces and its consequences for representation and optimization

DevFeed: [The structure of variational autoencoder latent spaces and its consequences for representation and optimization](<https://devfeed.tech/articles/the-structure-of-variational-autoencoder-latent-spaces-and-its-consequences-for-representation-and-optimization-138968.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.19972>)

Author: Sergei V. Kalinin

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

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

Topics: [VAE](<https://devfeed.tech/topics/vae.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>)

Tags: [covariance](<https://devfeed.tech/tags/covariance.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [decoder](<https://devfeed.tech/tags/decoder.md>), [deep](<https://devfeed.tech/tags/deep.md>), [error](<https://devfeed.tech/tags/error.md>), [flow](<https://devfeed.tech/tags/flow.md>), [folding](<https://devfeed.tech/tags/folding.md>), [generation](<https://devfeed.tech/tags/generation.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [microscopy](<https://devfeed.tech/tags/microscopy.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [properties](<https://devfeed.tech/tags/properties.md>), [prototype](<https://devfeed.tech/tags/prototype.md>), [spaces](<https://devfeed.tech/tags/spaces.md>), [theory](<https://devfeed.tech/tags/theory.md>), [vae](<https://devfeed.tech/tags/vae.md>)

### AI overview

For prototype data with squared-error reconstruction and an optimal decoder, the VAE latent-space objective corresponds directly to Flory-Huggins regular-solution theory. Data families form domains separated by finite-width walls; stronger regularization broadens the walls until posterior collapse erases class separation. The prior confines class centroids while structural dissimilarity softly repels them, with spacing increasing logarithmically with dissimilarity. Rare states may be unresolved, form islands, gather in walls or become intervening domains depending on frequency and similarity. Axis-aligned domains do not necessarily represent separate physical factors; rotations and limited latent dimensionality can yield rings, encoder cuts, suppression, mixing or folding. Comparisons with flow models, DKL and hybrid VAE-DKL models examine how these patterns change when reconstruction and prediction have different roles. The source is an abstract, so detailed comparison results are not provided.

### Source excerpt

arXiv:2611.19972v1 Announce Type: new Abstract: Variational autoencoders (VAEs) are widely used to build low-dimensional representations of scientific data, with the expectation that regularization yields smooth coordinates for interpolation, generation and optimization. However, applications in microscopy reveal domains, narrow transitions and rare-state islands in VAE latent spaces that smoothness alone does not explain. We show that, for prototype data with squared-error reconstruction and an optimal decoder, the latent-space objective has a direct correspondence with the Flory-Huggins theory of a regular solution, and use it to analyze how the objective, posterior distributions and latent dimensionality organize the representation. Data families occupy domains separated by finite-width walls that broaden with increasing regularization until class separation is lost through posterior collapse. Class centroids behave like particles in a harmonic trap: the prior confines them, and structural dissimilarity sets a soft repulsion that determines which classes become neighbors and how far apart they sit, with separations growing only logarithmically with dissimilarity. Rare states can remain unresolved, form small islands, accumulate within walls or develop intervening domains, depending on their frequency and similarity to common states. The posterior covariance can align domains with the latent axes, but axis alignment does not imply separation of physical factors. Rotations can produce rings and encoder cuts that reflect data symmetry, while insufficient dimensionality can lead to suppression, mixing or folding of additional factors. Comparisons with flow models, deep kernel learning (DKL) and hybrid VAE-DKL models show how these structures change when reconstruction and prediction play different roles. We discuss implications for interpreting data, discovering rare states, generating intermediate states and optimizing properties.

## Recursive Entropic Variational Inference for Nonlinear State-Space Models

DevFeed: [Recursive Entropic Variational Inference for Nonlinear State-Space Models](<https://devfeed.tech/articles/recursive-entropic-variational-inference-for-nonlinear-state-space-models-138728.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2511.15409>)

Author: Hany Abdulsamad, \\'Angel F. Garc\\'ia-Fern\\'andez, Simo S\\"arkk\\"a

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

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

Topics: [VAE](<https://devfeed.tech/topics/vae.md>)

Tags: [algorithms](<https://devfeed.tech/tags/algorithms.md>), [bayesian-inference](<https://devfeed.tech/tags/bayesian-inference.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [inference](<https://devfeed.tech/tags/inference.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [stat-me](<https://devfeed.tech/tags/stat-me.md>), [state-space-models](<https://devfeed.tech/tags/state-space-models.md>)

### AI overview

The paper presents recursive algorithms for state estimation in nonlinear, non-Gaussian state-space models. A variational Lagrangian formulation treats Bayesian inference as entropic trust-region updates constrained by dynamic consistency, yielding forward-backward algorithms whose structure depends on the variational posterior's factorization. For Gauss-Markov approximations, the authors derive recursive schemes they characterize as having favorable computational complexity. For more general models, they close the recursions with generalized statistical linear regression and Fourier-Hermite moment matching.

### Source excerpt

arXiv:2511.15409v3 Announce Type: replace Abstract: We present a class of algorithms for state estimation in nonlinear, non-Gaussian state-space models. Our approach is based on a variational Lagrangian formulation that casts Bayesian inference as a sequence of entropic trust-region updates subject to dynamic consistency constraints. This framework gives rise to a family of forward-backward algorithms whose structure is determined by the chosen factorization of the variational posterior. By focusing on Gauss--Markov approximations, we derive recursive schemes with favorable computational complexity. For general nonlinear, non-Gaussian models, we close the recursions using generalized statistical linear regression and Fourier--Hermite moment matching.

## Amortized Inference of Multi-Modal Posteriors using Likelihood-Weighted Normalizing Flows

DevFeed: [Amortized Inference of Multi-Modal Posteriors using Likelihood-Weighted Normalizing Flows](<https://devfeed.tech/articles/amortized-inference-of-multi-modal-posteriors-using-likelihood-weighted-normalizing-flows-135655.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2512.04954>)

Author: Rajneil Baruah

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

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

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [VAE](<https://devfeed.tech/topics/vae.md>)

Tags: [2d](<https://devfeed.tech/tags/2d.md>), [3d](<https://devfeed.tech/tags/3d.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [bias](<https://devfeed.tech/tags/bias.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [flow](<https://devfeed.tech/tags/flow.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [hep-ex](<https://devfeed.tech/tags/hep-ex.md>), [hep-ph](<https://devfeed.tech/tags/hep-ph.md>), [inference](<https://devfeed.tech/tags/inference.md>), [markov](<https://devfeed.tech/tags/markov.md>), [markov-chain-monte-carlo](<https://devfeed.tech/tags/markov-chain-monte-carlo.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [physics](<https://devfeed.tech/tags/physics.md>), [physics-comp-ph](<https://devfeed.tech/tags/physics-comp-ph.md>), [physics-data-an](<https://devfeed.tech/tags/physics-data-an.md>), [probability](<https://devfeed.tech/tags/probability.md>), [reference](<https://devfeed.tech/tags/reference.md>), [sampling](<https://devfeed.tech/tags/sampling.md>), [theoretical](<https://devfeed.tech/tags/theoretical.md>), [training](<https://devfeed.tech/tags/training.md>), [wolfenstein](<https://devfeed.tech/tags/wolfenstein.md>)

### AI overview

The method estimates posteriors by training normalizing flows with likelihood-weighted importance sampling, using the prior as the proposal and requiring no posterior training samples. In 2D and 3D multimodal benchmarks, standard unimodal base distributions produced spurious probability bridges between separated modes; initializing with a Gaussian mixture matching the target's number of modes improved reconstruction fidelity on reported distance and divergence metrics. The authors also applied the approach to extracting Wolfenstein parameters from CP asymmetry in B⁰ -> J/ψ K⁰, comparing with converged MCMC and quadrature references. In that application, using the trained flow as an importance-sampling proposal removed its remaining bias and provided the evidence.

### Source excerpt

arXiv:2512.04954v4 Announce Type: replace Abstract: We present a technique for posterior estimation using Normalizing Flows trained with likelihood-weighted importance sampling, the special case of neural importance sampling in which the proposal is the prior. This approach allows for the efficient inference of theoretical parameters in high-dimensional inverse problems without the need for posterior training samples. We implement the method on multi-modal benchmark tasks in 2D and 3D to check for the efficacy. A critical observation of our study is the impact of the base distribution on the modelled posteriors. We find that standard unimodal base distributions leave spurious probability \textit{bridges} between well-separated modes. We demonstrate that initializing the flow with a Gaussian Mixture Model that matches the number of target modes significantly improves reconstruction fidelity, as measured by some distance and divergence metrics. Finally, we apply this method to a curated problem in heavy flavour physics --- the extraction of the Wolfenstein parameters from the CP asymmetry in $B^0\to J/\psi\,K^0$; it is multimodal, non-Gaussian, and asymmetric in its mode weights --- and compare the results against a well-converged Markov Chain Monte Carlo reference and an exact reference computed by quadrature, using different metrics. Used as a proposal for importance sampling, the trained flow removes its remaining bias and gives the evidence.

## Classifier-Guided Latent Diffusion for Small-Molecule Generation

DevFeed: [Classifier-Guided Latent Diffusion for Small-Molecule Generation](<https://devfeed.tech/articles/classifier-guided-latent-diffusion-for-small-molecule-generation-135814.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17650>)

Author: Ali Forooghi, Luis Rueda, Alioune Ngom

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

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

Topics: [Computational Chemistry / Materials Science](<https://devfeed.tech/topics/computational-chemistry-materials-science.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [VAE](<https://devfeed.tech/topics/vae.md>)

Tags: [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [denoising](<https://devfeed.tech/tags/denoising.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [generation](<https://devfeed.tech/tags/generation.md>), [guidance](<https://devfeed.tech/tags/guidance.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [sampling](<https://devfeed.tech/tags/sampling.md>), [steering](<https://devfeed.tech/tags/steering.md>), [transformer](<https://devfeed.tech/tags/transformer.md>)

### AI overview

The paper proposes property-guided small-molecule generation by steering latent diffusion in frozen ChemBERTa embeddings with a differentiable property predictor. A Transformer decoder reconstructs SELFIES from the embeddings; generated strings are converted to SMILES and checked with RDKit. The reported evaluation considers validity, uniqueness, novelty and predicted scores for blood-brain barrier permeability and human β-secretase 1 inhibition. The abstract says results suggest the approach can produce valid, novel molecules with controllable property steering, but provides no quantitative results or further limitations.

### Source excerpt

arXiv:2611.17650v1 Announce Type: new Abstract: Diffusion models have emerged as a promising class of generative models for molecular design because of their ability to learn complex chemical distributions and support conditional or guided generation. In this work, we investigate a latent diffusion pipeline for property-guided small-molecule generation. The proposed framework represents canonicalized SMILES strings using a frozen ChemBERTa encoder, trains a Transformer-based decoder to reconstruct SELFIES strings from molecular latent embeddings, and learns an unconditional denoising diffusion model in the ChemBERTa latent space. To enable property-directed generation, a differentiable latent property predictor is used to guide the diffusion sampling process. Generated SELFIES strings are converted to SMILES, validated using RDKit, and evaluated using molecular validity, uniqueness, novelty, and predicted property scores. We study guidance toward two drug-relevant binary endpoints: blood--brain barrier permeability and inhibition of human $\beta$-secretase 1. The results suggest that latent diffusion over pretrained molecular embeddings can generate chemically valid and novel molecules while enabling controllable steering toward desired molecular properties.

## Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts

DevFeed: [Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts](<https://devfeed.tech/articles/disentangling-continuous-time-latent-dynamics-identifiability-of-latent-sdes-via-diffusion-shifts-135700.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.28228>)

Author: Yuanyuan Wang, Wenjie Wang, Haoxuan Li, Mingming Gong, Kun Zhang

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

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

Topics: [causality](<https://devfeed.tech/topics/causality.md>), [VAE](<https://devfeed.tech/topics/vae.md>)

Tags: [application](<https://devfeed.tech/tags/application.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [covariance](<https://devfeed.tech/tags/covariance.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [environment](<https://devfeed.tech/tags/environment.md>), [estimator](<https://devfeed.tech/tags/estimator.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [graph](<https://devfeed.tech/tags/graph.md>), [learning](<https://devfeed.tech/tags/learning.md>), [linear](<https://devfeed.tech/tags/linear.md>), [models](<https://devfeed.tech/tags/models.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [noise](<https://devfeed.tech/tags/noise.md>), [permutation](<https://devfeed.tech/tags/permutation.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [representation-learning](<https://devfeed.tech/tags/representation-learning.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [sde](<https://devfeed.tech/tags/sde.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>), [time](<https://devfeed.tech/tags/time.md>)

### AI overview

Environment-induced changes in diffusion covariance can identify latent coordinates in continuous-time additive-noise SDEs observed through an unknown nonlinear transformation. With two diagonal diffusion regimes whose coordinate-wise variance ratios are pairwise distinct, the coordinates are identifiable up to permutation, individual scaling, and a possible constant shift, without requiring sparse drift. The result is established first for linear Ornstein-Uhlenbeck systems and then extended to general additive-noise latent SDEs; under mild smoothness, the instantaneous drift-Jacobian causal graph is identifiable up to the same ambiguities. The authors propose a two-stage estimator for latent disentanglement and optional graph recovery. Synthetic experiments are reported to confirm the predicted identifiability boundary, alongside an application to Hardanger Bridge sensor trajectories.

### Source excerpt

arXiv:2606.28228v3 Announce Type: replace Abstract: Causal representation learning for time series has developed strong identifiability results in discrete-time latent causal models, but identifiability in continuous-time latent stochastic differential equation (SDE) models remains largely open. We address this gap using environment-induced shifts in diffusion covariance. We study additive-noise latent SDEs observed through an unknown nonlinear diffeomorphism, with shared drift but environment-specific diffusion covariance. We show that two diagonal diffusion regimes with pairwise distinct coordinate-wise variance ratios identify the latent coordinates up to permutation, coordinate-wise scaling, and a possible constant shift, without any sparsity assumption on the drift. We first prove this result for linear Ornstein-Uhlenbeck systems and then extend it to general additive-noise latent SDEs. Under mild smoothness, the instantaneous drift-Jacobian causal graph is identifiable up to the same permutation. We propose a two-stage estimator for latent disentanglement and optional graph recovery; experiments on synthetic systems confirm the predicted identifiability boundary, and an application to Hardanger Bridge monitoring data illustrates the approach on real sensor trajectories.

## Causal AI-Driven Secure mmWave Beam Alignment with Defensive Variational Autoencoders

DevFeed: [Causal AI-Driven Secure mmWave Beam Alignment with Defensive Variational Autoencoders](<https://devfeed.tech/articles/causal-ai-driven-secure-mmwave-beam-alignment-with-defensive-variational-autoencoders-135188.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18321>)

Author: Nasir Khan, Asmaa Abdallah, Abdulkadir Celik, Ahmed M. Eltawil, Sinem Coleri, Cicek Cavdar

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

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

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [VAE](<https://devfeed.tech/topics/vae.md>), [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>), [causality](<https://devfeed.tech/topics/causality.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [autoencoders](<https://devfeed.tech/tags/autoencoders.md>), [beam](<https://devfeed.tech/tags/beam.md>), [causal-ai](<https://devfeed.tech/tags/causal-ai.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [defensive](<https://devfeed.tech/tags/defensive.md>), [mmwave](<https://devfeed.tech/tags/mmwave.md>)

### AI overview

The proposed mmWave beam alignment framework combines causal feature selection with adversarial input defense. Its two-stage algorithm learns a Bayesian graph linking RSSI measurements to the optimal beam, then selects relevant inputs for the classifier. A defensive variational autoencoder (DVAE) reconstructs perturbed RSSI, with end-to-end classifier fine-tuning on those representations. In simulations, causal selection achieved accuracy comparable to conventional methods, at 829x lower per-sample computational cost than SHAP, and reduced beam sweeping by 59.4% versus conventional DL selection and 89.8% versus exhaustive search. The DVAE maintained 85% accuracy across perturbation bounds, preserved baseline performance on unperturbed inputs, and exceeded defensive distillation by 15-20% on average across attack scenarios.

### Source excerpt

arXiv:2611.18321v1 Announce Type: new Abstract: Efficient and secure beam alignment is essential for mmWave communication systems. However, existing deep learning (DL)-based beam alignment methods often neglect causal relationships between inputs and outputs, resulting in limited interpretability, poor generalization, and excessive beam sweeping. Moreover, these DL solutions are vulnerable to adversarial attacks, where small perturbations in received power measurements can mislead beam classifiers. To overcome these issues, we propose a causally-aware DL framework integrating causal discovery into beam alignment. A two-stage causal beam selection algorithm learns a Bayesian graph capturing dependencies between received signal strength indicators (RSSI) as inputs and the optimal beam index as the target variable, then uses it to select a minimal set of relevant input features for the DL classifier. To mitigate adversarial attacks, we introduce a defensive variational autoencoder (DVAE) that maps potentially perturbed inputs back to their clean versions. End-to-end fine-tuning of the downstream beam classifier on the DVAE-reconstructed RSSI representations further boosts prediction accuracy. Simulation results show that causal beam selection achieves accuracy comparable to conventional methods while providing an \(\mathbf{829\times}\) lower per-sample computational cost than SHAP (Shapley Additive Explanations), a widely used explainable AI (XAI)-based feature selection method. It further reduces beam-sweeping overhead by \(\mathbf{59.4\%}\) and \(\mathbf{89.8\%}\), compared to conventional DL-based beam selection and exhaustive search, respectively. The DVAE-based defense effectively denoises adversarial inputs, sustaining 85\% accuracy across different perturbation bounds, retains baseline performance on unperturbed RSSI inputs and surpasses defensive distillation defense scheme by 15--20\% on average under different attack scenarios.

## Reframing Video Inverse Tone Mapping as Blind Posterior Inference via Latent Luminance Supervision

DevFeed: [Reframing Video Inverse Tone Mapping as Blind Posterior Inference via Latent Luminance Supervision](<https://devfeed.tech/articles/reframing-video-inverse-tone-mapping-as-blind-posterior-inference-via-latent-luminance-supervision-132103.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.15146>)

Author: Hanwool Sul, Chang-Hoon Jeong, Kisung Shin, Bomseok Park, Donghoon Cha, Hansl von Kwon, DoHyung Ku, Byoung-Tak Zhang

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

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

Topics: [Color Grading](<https://devfeed.tech/topics/color-grading.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [VAE](<https://devfeed.tech/topics/vae.md>)

Tags: [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [clipping](<https://devfeed.tech/tags/clipping.md>), [computer-science](<https://devfeed.tech/tags/computer-science.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [decoding](<https://devfeed.tech/tags/decoding.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [error](<https://devfeed.tech/tags/error.md>), [generative](<https://devfeed.tech/tags/generative.md>), [hdr](<https://devfeed.tech/tags/hdr.md>), [high-dynamic-range](<https://devfeed.tech/tags/high-dynamic-range.md>), [inference](<https://devfeed.tech/tags/inference.md>), [mapping](<https://devfeed.tech/tags/mapping.md>), [sdr](<https://devfeed.tech/tags/sdr.md>), [supervision](<https://devfeed.tech/tags/supervision.md>), [training](<https://devfeed.tech/tags/training.md>), [video](<https://devfeed.tech/tags/video.md>), [visual-effects](<https://devfeed.tech/tags/visual-effects.md>)

### AI overview

Video inverse tone mapping must recover HDR from SDR without knowing the tone operator, and clipping erases radiance. The abstract reports that tested public generative-prior methods show systematic luminance bias in clipped content, with the bias direction changing by operator. The proposed approach treats recovery as posterior inference under an unknown operator: it reads log-luminance from a video-diffusion latent and applies an asymmetric loss to select a posterior expectile only where clipping leaves luminance unconstrained. Training SDR is synthesized using a family of tone operators. The authors report lower average luminance error, less variation across operators, and the best perceptual quality on three benchmarks; the excerpt gives no benchmark names or quantitative results.

### Source excerpt

arXiv:2611.15146v1 Announce Type: cross Abstract: High-dynamic-range (HDR) displays are now common, but most video content, such as archival footage, broadcast material, and the output of generative video models, exists only in standard dynamic range (SDR). The need is sharpest for generated video, which has no HDR master at all and is graded alongside live-action and visual-effects material finished in HDR. Converting SDR to HDR means undoing a tone-mapping operation that was never recorded, and clipping destroys the radiance wherever it acts, so HDR recovery is a blind inverse problem. Methods built on generative video priors fill clipped regions with plausible structure, but their reconstructions are systematically biased: in every public method we test, saturated content leans too bright or too dark, and the direction of the lean moves with the tone operator behind the input. We call this failure the luminance error, measure both its magnitude and its sign, and make it the focus of this work. Reframing ITM as posterior inference under an unknown operator locates the failure in two places and yields two corrections. A fixed affine functional of the video-diffusion latent reads log-luminance without decoding; on that coordinate an asymmetric loss selects an expectile of the posterior, applied only where clipping leaves luminance unconstrained. We also synthesize training SDR through an explicit family of tone operators, so the model marginalizes over what the observation cannot show. Trained this way, our luminance error stays flatter across operators and smaller on average than any public method, and the full system achieves the best perceptual quality on all three benchmarks.

## Helgason-Fourier Random Features for Scalable Hyperbolic Latent Variables

DevFeed: [Helgason-Fourier Random Features for Scalable Hyperbolic Latent Variables](<https://devfeed.tech/articles/helgason-fourier-random-features-for-scalable-hyperbolic-latent-variables-133121.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.16461>)

Author: Koshi Watanabe, Daichi Mochihashi, Hideitsu Hino, Takahiro Ogawa, Miki Haseyama

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

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

Topics: [VAE](<https://devfeed.tech/topics/vae.md>), [fourier analysis](<https://devfeed.tech/topics/fourier-analysis.md>), [Feature Engineering](<https://devfeed.tech/topics/feature-engineering.md>)

Tags: [approximation](<https://devfeed.tech/tags/approximation.md>), [best](<https://devfeed.tech/tags/best.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [features](<https://devfeed.tech/tags/features.md>), [kernels](<https://devfeed.tech/tags/kernels.md>), [lvm](<https://devfeed.tech/tags/lvm.md>), [map](<https://devfeed.tech/tags/map.md>), [metric](<https://devfeed.tech/tags/metric.md>), [random](<https://devfeed.tech/tags/random.md>), [scale](<https://devfeed.tech/tags/scale.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>), [variables](<https://devfeed.tech/tags/variables.md>)

### AI overview

Random Helgason-Fourier Features (RHFF) provide a finite-dimensional map for hyperbolic-space kernels, with a characterized frequency distribution that supports kernels such as Matérn and a proved uniform approximation error bound. The resulting RHFF-LVM avoids numerical quadrature, variational bounds, and auxiliary variables required by previous hyperbolic GP-LVMs. In reported evaluations, it recovered a synthetic tree's metric more faithfully than the baselines and achieved the best mean rank, with large gains on tree-structured atlases at Q=2. The authors also report fitting 500,000 points in 505 seconds, which they describe as the first non-parametric hyperbolic latent variable model at this scale.

### Source excerpt

arXiv:2611.16461v1 Announce Type: new Abstract: Hyperbolic geometry is well suited to embedding hierarchical data, capturing tree-like structure faithfully even in the low dimensions where Euclidean dimensionality reduction is severely constrained. We introduce Random Helgason--Fourier Features (RHFF), an explicit finite-dimensional feature map for kernels on hyperbolic space. We characterize the spectral density from which RHFF frequencies are drawn, allowing kernels such as the Mat\'ern family to be specified directly in the frequency domain. We also prove a uniform approximation error bound for RHFF. Building on this representation, we develop a hyperbolic latent variable model called RHFF-LVM, which requires no numerical quadrature, variational bounds or auxiliary variables unlike previous hyperbolic GP-LVMs. Our RHFF-LVM recovers the metric of a synthetic tree more faithfully than all baselines and attains the best mean rank, driven by large gains on tree-structured atlases at $Q\!=\!2$. Furthermore, it fits $5\times10^{5}$ points in $505$ seconds, making it the first non-parametric hyperbolic LVM to reach this scale.

[Next page](<https://devfeed.tech/topics/vae.md?cursor=WyIyMDI2LTExLTEzVDA1OjAwOjAwKzAwOjAwIiwgImRkNWEzMWE1LWI5MmQtNDk2YS05N2I4LTdhNzFlYTQwNzVmMyJd>)