跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订，在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描：2026-11-16 01:34 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 05:03 — 2026-11-16 05:03（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-16 01:34最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

论文修订列表

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 6,729 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33（北京时间）
版本更新 · v4arXiv:2307.06090

Can Large Language Models Aid in Annotating Speech Emotional Data? Uncovering New Frontiers

Siddique Latif, Muhammad Usama, Mohammad Ibrahim Malik, Björn W. Schuller

原文摘要

Despite recent advancements in speech emotion recognition (SER) models, state-of-the-art deep learning (DL) approaches face the challenge of the limited availability of annotated data. Large language models (LLMs) have revolutionised our understanding of natural language, introducing emergent properties that broaden comprehension in language, speech, and vision. This paper examines the potential of LLMs to annotate abundant speech data, aiming to enhance the state-of-the-art in SER. We evaluate this capability across various settings using publicly available speech emotion classification datasets. Leveraging ChatGPT, we experimentally demonstrate the promising role of LLMs in speech emotion data annotation. Our evaluation encompasses single-shot and few-shots scenarios, revealing performance variability in SER. Notably, we achieve improved results through data augmentation, incorporating ChatGPT-annotated samples into existing datasets. Our work uncovers new frontiers in speech emotion classification, highlighting the increasing significance of LLMs in this field moving forward.

cs.SD · eess.AS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.16933

A Unified Taxonomy and Evaluation Framework for Distributional Shifts in Reinforcement Learning

Ardianto Wibowo, Paulo E Santos, Amer Baghdadi, Matthew Stephenson, Karl Sammut, Jean-Philippe Diguet

原文摘要

Distributional shift in reinforcement learning (RL) is defined inconsistently across the literature, and it is studied alongside out-of-distribution (OOD) generalization and non-stationarity without a clear account of how the three terms are related. Methods are also often described as robust after evaluation under only a few particular changes, leaving the scope of such claims unclear. We develop a unified taxonomy that brings the three terms under one definition of distributional shift. We factorize the joint distribution of a one-step interaction into five components, each produced by its own generating function: initial-state distribution, observation mechanism, policy implementation (distinct from the policy being optimized), transition dynamics, and reward mechanism. A shift is specified by what changes (the changed components) and when it changes (the interaction regime: OOD, non-stationary, or combined), while changes in interaction data and performance are treated as observed effects. We complement the taxonomy with an evaluation framework that measures immediate generalization and subsequent adaptation, summarizing adaptation in a shift adaptation score (SAS). Published benchmark results, controlled Gridworld experiments with DQN, A2C, and PPO, and a mapping of selected studies show that method responses and rankings vary with the shifted component, and that existing evaluations cover only some components. Robustness claims should therefore be bounded by the components and regimes evaluated, since strong performance under one shift does not establish robustness under others. Identifying an unknown component-level source from observed interaction data remains a direction for future research.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.19882

Multimodal Concept Bottleneck Models

Tongqing Shi, Ge Yan, Tuomas Oikarinen, Tsui-Wei Weng

原文摘要

Concept Bottleneck Models (CBMs) enhance the interpretability of deep neural networks by aligning the features extracted from images with human-interpretable concepts. However, conventional CBMs typically use a linear classifier that maps concept activations to a fixed set of predefined classes, limiting their flexibility in open-vocabulary settings. In this paper, we propose Multimodal Concept Bottleneck Model (MM-CBM) to address these issues and extend CBMs into CLIP structure. MM-CBM utilizes dual Concept Bottleneck Layers (CBLs) to align both the image and text embeddings into interpretable features. This allows us to perform new vision tasks like zero-shot classification or image retrieval in an interpretable way. Compared to existing methods, MM-CBM achieves 23.28% accuracy improvement on average across four standard benchmarks. Our method maintains competitive performance compared with black-box CLIP model while offering interpretability. Under classification tasks, MM-CBM's accuracy is on average 3.94% lower than CLIP in the target-dataset adaptation setting and 9.84% in the zero-shot transfer setting. Under image-text retrieval tasks, it achieves an average gap of 2.48% for image retrieval and 9.22% for text retrieval.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.00249

SANEval: Open-Vocabulary Compositional Benchmarks with Failure-mode Diagnosis

Rishav Pramanik, Ian E. Nielsen, Jeff Smith, Saurav Pandit, Ravi P. Ramachandran, Zhaozheng Yin

原文摘要

Text-to-image (T2I) models struggle with compositional prompts requiring multiple objects, bound attributes, accurate counts, or spatial relations. Existing benchmarks face limits from fixed detector vocabularies, aggregated scores, and varying human-validation protocols. We introduce SANEval (Spatial, Attribute, and Numeracy Evaluation), an open-vocabulary compositional benchmark with two key contributions: (i) a public dataset of ~5,250 prompts paired with images from six state-of-the-art T2I models, split into algorithmically generated Simple and fully human-written Hard partitions across five compositional tasks, and (ii) a modular evaluation pipeline combining an LLM prompt parser, an open-vocabulary detector with LLM synonym expansion, and scorers for attribute binding, spatial relations, and numeracy. Each scorer emits numerical scores and diagnostic feedback for missing, extra, or mis-bound elements. Validated against human ratings (n = 500), SANEval achieves positive Pearson correlations across all categories (overall r = 0.222), outperforming CompBench++ (-0.016) and GenEval (-0.030). A manual audit of 24,012 detections shows 96.58% precision, with ablation confirming that synonym expansion is critical to pipeline performance. Dataset: [https://huggingface.co/datasets/saneval/saneval-release](https://huggingface.co/datasets/saneval/saneval-release). Pipeline: [https://github.com/nielseni6/saneval](https://github.com/nielseni6/saneval).

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2310.11531

Informed Posterior Sampling: More Efficient Online Learning with Few Offline Demonstrations in Average-Reward MDPs

Dengwang Tang, Dongze Ye, Botao Hao, Rahul Jain, Zheng Wen

原文摘要

We study efficient online reinforcement learning in the infinite horizon setting when there is an offline dataset to start with. We assume that the offline dataset is generated by an expert but with an unknown level of competence, i.e., it is not perfect and not necessarily using the optimal policy. We show that if the learning agent models the behavioral policy (parameterized by a competence parameter) used by the expert, it can do substantially better in terms of minimizing cumulative regret than if it does not do that. We establish an upper bound on regret of the exact informed PSRL (iPSRL) algorithm that scales as $\widetilde{\mathcal{O}}(\sqrt{T})$. This requires a novel prior-dependent regret analysis of Bayesian online learning algorithms for the infinite horizon setting. We then propose the informed RLSVI (iRLSVI) algorithm to efficiently approximate the iPSRL algorithm. Empirical results show that small offline expert datasets are sufficient for iRLSVI to outperform online-only algorithms on hard exploration domains.

cs.LG · cs.AI · eess.SY · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.24274

A lift for input-convex neural net training

Ali Siahkoohi

原文摘要

Input-convex neural nets parametrize the convex potentials of density models and transport maps, and their convexity requires the inter-layer weights to be non-negative. Projected gradient descent enforces this by projecting after each step, and due to mini-batch noise the boundary is re-crossed indefinitely, which leads to an active set the projection never identifies. The differentiable alternative, direct softplus, optimizes a free latent weight through a softplus positivity map. Where that latent weight is well below zero, the derivative of the map is exponentially small and scales down both the gradient and its noise. We call this region the shoulder, and a weight that reaches it therefore barely moves and stays for an exponentially long time. We propose the lift, which replaces the free latent weight by a learnable slack plus the output of a hypernetwork that reads a permutation-invariant summary of the training batch. The latent weight then varies with the same batch that forms the gradient, so the two are coupled. We show that this coupling adds a term to the variance of the update at first order, and that the slack, the batch dependence, and the shared batch are each needed for it. Where the coupling aligns positively with the loss curvature, a weight on the shoulder crosses the barriers of the loss sooner under the lift than under direct softplus, also under preconditioned stochastic gradient descent. We compare the lift with the two existing methods on several applications. Where a constrained weight of direct softplus reaches the shoulder, the lift fits the target more closely than direct softplus and reaches the same reconstruction about three times sooner. Where almost none reaches it, the methods agree.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.19215

Not all uncertainty is alike: volatility, stochasticity, and exploration

Payam Piray

原文摘要

Adaptive decision-making in biological and artificial intelligence requires balancing the exploitation of known outcomes with the exploration of uncertain alternatives. Although prior work suggests that uncertainty generally promotes exploration, it has typically treated distinct sources of environmental uncertainty as equivalent. We consider environments with latent reward states that drift over time (volatility) and are observed through noisy outcomes (stochasticity). Both of them increase posterior uncertainty, yet we show they drive optimal exploration in opposite directions: volatility enhances it, stochasticity suppresses it. We establish this asymmetry formally by extending the Gittins index framework to Gaussian state-space bandits with latent dynamics. We further derive Cause-Aware Uncertainty-Sensitive Exploration (CAUSE), a closed-form exploration bonus obtained via control-as-inference that inherits the same monotonicities. CAUSE matches or exceeds both standard exploration strategies and numerically computed index policies in environments with heterogeneous noise structure. Learning and exploration are governed by the same noise-inference asymmetry, and the framework predicts that pathological noise inference misallocates exploration in an axis-specific way, with implications for computational accounts of psychiatric conditions.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.23968

IMPULSE: Push First, Then Predict in V-JEPA 2 Feature Space

Tingan Jin, Chung-Hsien Chou

原文摘要

Latent world models such as V-JEPA 2 forecast in the feature space of a video encoder, but one look at an object does not reveal how hard it is to rotate, how much it bounces or how much it slides. People find out by trying: a few pokes reveal how an object responds. IMPULSE, named after the impulse response it infers, gives a predictor in frozen V-JEPA 2 feature space the same ability. A Bayesian contact memory summarizes three short calibration pushes, a predicted object pose carries it into the predictor, and a lightweight random-Fourier pose head lets the predictor use the pose. On 512 fresh objects, in a pre-specified held-out confirmation with models sealed before the data existed, the memory lowers the 1-second feature-forecast error by 11.6-12.8% relative to the same predictor without experience, for all 8 training seeds, with a 95% seed-and-object interval excluding zero. The gain also holds for 128 objects with out-of-range physics (11.7-14.0%), and the full extension beats a plain predictor by 15.5-16.6%. An information-ladder argument, exact for ideal predictors, shows that physics reaches the features only through motion, so we measure how much the pathway lets pose help. On fresh objects, the Fourier head roughly triples the gain of a perfect memory over plain pose tokens (2.8-3.2 times). Raw push measurements fed through the same pathway give a similar gain, so the Bayesian summary is not required; it condenses the trials into eight interpretable numbers. The gain is absent at contact onset and grows afterwards.

cs.CV · cs.LG · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.19227

Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models

Tobias Braun, Jonas Henry Grebe, Hossein Shakibania, Anna Rohrbach, Marcus Rohrbach

原文摘要

Unified autoregressive models (UAMs) are transformer models that generate text as well as image tokens within a single autoregressive pass. Shared parameters and a multimodal vocabulary simplify the training pipeline and facilitate flexible multimodal generation, yet might introduce new vulnerabilities. In particular, we are the first to show that this unified architecture enables multimodal backdoor attacks, where a trigger can propagate malicious effects across multiple output modalities. Specifically, we present the Token by Token Backdoor Attack (ToBAC), the first backdoor attack targeting UAMs, exploring both data-based and model-based poisoning strategies. We demonstrate that inconspicuous characters or even common words can be transformed into triggers that elicit harmful behavior in autoregressive image generation. ToBAC can jointly manipulate visual outputs and accompanying text, increasing the perceived authenticity of fabricated content. With model access, ToBAC enables attacks on the Liquid model in which a subtle word (e.g., "cool") induces modality-aligned brand promotion or ideological influence in 55% of generations. Without model access, ToBAC can be induced through data poisoning, achieving an average success rate of 63.1% against JanusPro. Our code is available at https://github.com/multimodal-ai-lab/ToBAC.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33143

Learning Pathology-Sensitive Representations for Unsupervised Retinal OCT Anomaly Detection

Tania Haghighi, Sina Gholami, Behafarin Emam, Jennifer I Lim, Theodore Leng, Atalie C Thompson, Hamed Tabkhi, Minhaj Nur Alam

原文摘要

Deep learning approaches for retinal optical coherence tomography (OCT) predominantly rely on predefined disease categories, limiting their ability to detect rare or previously unseen abnormalities. While visual foundation models provide transferable representations, their effectiveness in identifying pathological deviations from normal retinal anatomy remains insufficiently understood. In this work, we introduce an unsupervised framework for retinal OCT anomaly detection and localization that adapts pretrained visual representations to normal retinal anatomy through anatomy-aware reconstruction and contrastive triplet learning guided by synthetic structural perturbations, without requiring disease-specific annotations. We systematically investigate the influence of pretraining strategies, anatomy-aware representation adaptation, and anomaly scoring mechanisms on the detection and localization of unseen retinal abnormalities. Our findings demonstrate that adapting pretrained representations to normal retinal structure improves anomaly sensitivity, while pixel-space reconstruction errors and feature-space deviations provide complementary signals for identifying pathological changes. These findings underscore the importance of anatomy-aware representation learning and offer insights into developing generalizable retinal anomaly detection frameworks beyond predefined disease categories.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.32038

Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision

Zifan Carl Guo, Laura Ruis, Jacob Andreas, Belinda Z. Li

原文摘要

When does training language models (LMs) to generate explanations of their predictions yield faithful introspection, rather than superficial imitation? We study LMs trained to explain which features of their inputs influenced their behavior, using models' counterfactual behavior on modified inputs as supervision. Surprisingly, we find that LMs trained on fixed counterfactual explanations derived from their earlier checkpoints, or even from behaviorally similar models in different families, frequently produce explanations more faithful to their own current behaviors than to those of their training targets. This "introspective" coupling between LM explanations and behaviors occurs when training explanations remain sufficiently correlated with current behaviors over the course of training, even as behaviors themselves shift. We also show that introspective coupling tracks behavior shifts: when explanation training is provided concurrently with other post-training objectives, explanations change to match without requiring updated supervision. This phenomenon appears in multiple tasks, including sycophancy and refusal, and is robust to label noise. Overall, our results show that even fixed datasets of counterfactual explanations can provide scalable and generalizable post-training signal for introspection.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.16861

MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation

Abhay Deshpande, Maya Guru, Rose Hendrix, Snehal Jauhri, Ainaz Eftekhar, Rohun Tripathi, Max Argus, Jordi Salvador 等 26 位作者

原文摘要

A prevailing view in robot learning is that simulation alone is not enough; effective sim-to-real transfer is widely believed to require at least some real-world data collection or task-specific fine-tuning to bridge the gap between simulated and physical environments. We challenge that assumption. With sufficiently large-scale and diverse simulated synthetic training data, we show that zero-shot transfer to the real world is not only possible, but effective for both static and mobile manipulation. We introduce MolmoBot-Engine, a fully open-source pipeline for procedural data generation across robots, tasks, and diverse simulated environments in MolmoSpaces. With it, we release MolmoBot-Data, a dataset of 1.7 million expert trajectories for articulated object manipulation and pick-and-place tasks. We train three policy classes: MolmoBot, a Molmo2-based multi-frame vision-language model with a flow-matching action head; MolmoBot-Pi0, which replicates the $π_0$ architecture to enable direct comparison; and MolmoBot-SPOC, a lightweight policy suitable for edge deployment and amenable to RL fine-tuning. We evaluate on two robotic platforms: the Franka FR3 for tabletop manipulation tasks and the Rainbow Robotics RB-Y1 mobile manipulator for door opening, drawer manipulation, cabinet interaction, and mobile pick-and-place. Without any real-world fine-tuning, our policies achieve zero-shot transfer to unseen objects and environments. On tabletop pick-and-place, MolmoBot achieves a success rate of 79.2% in real world evaluations across 4 settings, outperforming $π_{0.5}$ at 39.2%. Our results demonstrate that procedural environment generation combined with diverse articulated assets can produce robust manipulation policies that generalize broadly to the real world. Technical website: https://allenai.github.io/MolmoBot

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.15399

Breakeven complexity: A new perspective on neural partial differential equation solvers

Yijing Zhang, Nicholas Roberts, Tanya Marwah, Mikhail Khodak

原文摘要

Neural surrogate solvers of partial differential equations (PDEs) promise dramatic speedups over numerical methods, especially in scenarios requiring many solves. However, current accuracy-based evaluations do not fully consider two central issues: (1) neural solvers incur substantial up-front costs for data generation, training, and tuning; and (2) classical solvers can also generate low-fidelity solutions at a sufficiently low simulation cost. To explicitly account for these realities and fully incorporate end-to-end costs, we propose an evaluation framework centered on breakeven complexity, a metric that counts the forward solves before a learned solver is cost-effective relative to an error-equivalent traditional solver. To evaluate this measure, we apply scaling laws to determine how much training budget to allocate to data generation and discuss how to achieve smooth error-matching in diverse settings. We evaluate the breakeven complexity of multiple neural PDE solvers on three PDEs on 2D periodic domains from APEBench and a novel benchmark of flows past multiple obstacles generated by the GPU-native PyFR code. Among other findings, our results suggest that neural PDE solvers become more effective as problems get harder in terms of cost, dimension, rollout, physics regime (e.g. higher Reynolds number), etc.

cs.LG · cs.AI · math.NA · physics.comp-ph

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.30344

Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection

Xiaona Zhou, Muntasir Wahed, Tianjiao Yu, Constantin Brif, Ismini Lourentzou

原文摘要

Recent advances in Vision--Language Models (VLMs) have achieved impressive performance across many tasks, yet prior studies report unsatisfactory performance when applying large language or multimodal models to finding abnormal patterns in sequential data. Public anomaly detection benchmarks typically provide interval annotations but not natural-language rationales, making it difficult to fine-tune VLMs to produce grounded, interpretable decisions. To address this gap, we construct VisAnomBench, a curated benchmark built from public time-series datasets and augmented with high-quality anomaly explanations selected from multiple large VLMs using fine-grained, task-specific rewards. Through fine-tuning on this benchmark, we develop VisAnomReasoner, a parameter-efficient VLM for time-series anomaly detection. Results on VisAnomBench show that VisAnomReasoner achieves more accurate anomaly localization and consistently outperforms all baselines, with improvements of at least 21.23 and 23.87 percentage points in precision and F1, respectively. Additional experiments on the TSB-AD-U benchmark demonstrate strong cross-benchmark generalization, with VisAnomReasoner improving precision and F1 by 9.57 and 13.39 percentage points, respectively.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2602.12162

Amortized Molecular Optimization via Group Relative Policy Optimization

Muhammad bin Javaid, Hasham Hussain, Ashima Khanna-Reiter, Berke Kişin, Jonathan Pirnay, Alexander Mitsos, Dominik G. Grimm, Martin Grohe

原文摘要

In structurally constrained molecular optimization, state-of-the-art methods treat every new input structure as a separate instance, restarting an expensive oracle-driven search from scratch and scaling poorly to settings with many starting structures or expensive oracles. While amortized approaches that learn a transferable policy could in principle remove this bottleneck, existing methods struggle to generalize to diverse structural constraints at inference time. We present AMORTIX, a Graph Transformer model that natively supports such constraints, optimizing molecular structures in a single rollout with zero inference-time oracle calls. A central challenge for amortized training in this domain is that optimization difficulty varies drastically across starting structures. We address this by centering rewards within groups of completions that share the same starting structure. We evaluate on goal-directed scaffold decoration, including single- and multi-target kinase inhibitor design, and on a few-shot prodrug case study. AMORTIX outperforms both amortized baselines and search-based instance optimizers on kinase scaffold decoration, and ablations across 23 objectives show that group-relative centering improves over REINFORCE and PPO and is substantially more consistent across scaffold splits. The prodrug case study further demonstrates transfer of learned modification rules to unseen drug structures.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.10318

On the Approximability of Max-Cut on 3-Colorable Graphs and Graphs with Large Independent Sets

Suprovat Ghoshal, Neng Huang, Euiwoong Lee, Konstantin Makarychev, Yury Makarychev

原文摘要

Max-Cut is a classical graph-partitioning problem where given a graph $G = (V,E)$, the objective is to find a cut $(S,S^c)$ which maximizes the number of edges crossing the cut. In a seminal work, Goemans and Williamson gave an $α_{GW} \approx 0.87856$-factor approximation algorithm for the problem, which was later shown to be tight by the work of Khot, Kindler, Mossel, and O'Donnell. Since then, there has been a steady progress in understanding the approximability at even finer levels, and a fundamental goal in this context is to understand how the structure of the underlying graph affects the approximability of the Max-Cut problem. In this work, we investigate this question by exploring how the chromatic structure of a graph affects the Max-Cut problem. While it is well-known that Max-Cut can be solved perfectly and near-perfectly in $2$-colorable and almost $2$-colorable graphs in polynomial time, here we explore its approximability under much weaker structural conditions such as when the graph is $3$-colorable or contains a large independent set. Our main contributions in this context are as follows: 1. We show Max-Cut is $α_{GW}$-hard to approximate for $3$-colorable graphs. 2. We identify a natural threshold $α^*$ such that the following holds. Firstly, for graphs which contain an independent set of size up to $α^*$, Max-Cut continues to be $α_{GW}$-factor hard to approximate. Furthermore, for any graph that contains an independent set of size $> α^*$, there exists an efficient $>α_{GW}$-approximation algorithm for Max-Cut. Our hardness results are derived using various analytical tools and novel variants of the Majority-Is-Stablest theorem, which might be of independent interest. Our algorithmic results are based on a novel SDP relaxation, which is then rounded and analyzed using interval arithmetic.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.30450

Same Beliefs, Different Policies: Learning Reusable Representations for Early Stopping in LLM Reasoning

Jingwei Ni, Dmitry Abulkhanov, Vladislav Smirnov, Markus Leippold, Elliott Ash, Timothy Baldwin, Artem Shelmanov, Mrinmaya Sachan

原文摘要

Reasoning LLMs often continue reasoning after reaching a correct answer, wasting computation and sometimes replacing it with an incorrect one. Deciding when to stop is a metareasoning problem: the model must weigh what further reasoning could achieve against its cost, given what it can already answer. Direct utility training learns a stopping representation at a chosen token price; supporting new prices can require additional controller training. We introduce BELT (BELief-based Termination), which separates outcome prediction from stopping control. It learns beliefs about current and future answers from a frozen LLM's hidden states, then fits a linear stopping policy on the frozen features. The prediction targets are independent of token price, so one probe supports different accuracy-cost trade-offs through CPU policy refitting or threshold adjustment. Averaged over five out-of-distribution (OOD) math benchmarks, BELT reduces generated tokens by 41% on Qwen3-1.7B and 51% on OLMo-3-7B-Think without loss of accuracy. The same math-trained BELT transfers to coding and agentic tasks without training on code or agentic data. In all three domains, its accuracy-cost trade-offs are competitive with or better than those of end-to-end controllers. On OLMo3, its probe has 21.2x fewer parameters than one checkpoint of the strongest baseline, OS-Pruner, and needs 55x fewer training GPU-hours than OS-Pruner's five price-specific checkpoints.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2412.01753

Human-Machine Interfaces for Subsea Telerobotics: From Soda-straw to Natural Language Interactions

Adnan Abdullah, David Blow, Ruo Chen, Thanakon Uthai, Eric Jing Du, Md Jahidul Islam

原文摘要

This review explores the evolution of human-machine interfaces (HMIs) in subsea telerobotics, charting the progression from traditional first-person "soda-straw" consoles-- characterized by narrow field-of-view camera feeds-- to contemporary interfaces leveraging gesture recognition, virtual reality, and natural language processing. The review makes three key contributions. First, we introduce a structured framework that analyzes subsea HMIs through three interrelated aspects: operator experience, robotic autonomy, and bidirectional human-machine communication. Second, using these aspects, we compare visual, haptic, extended-reality, gesture, and natural-language interfaces; examine the progression from direct teleoperation to shared autonomy; and assess the distinct roles of simulators and digital twins in training, prototyping, and mission support. Third, we synthesize the reported evidence to distinguish established industrial tools, selectively deployed technologies, and research-stage capabilities, while identifying limitations in interoperability, communication reliability, immersive feedback, and field validation. From this synthesis, we outline standardization needs and research directions for hydrodynamic feedback, latency-aware shared autonomy, grounded language interaction, and real-to-simulation transfer. The report concludes by identifying open research questions and proposing a roadmap toward more intelligent and intuitive subsea HMI systems.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.00775

VOIM: Training-Free Open-Vocabulary 3D Instance Mapping for RGB-D and Monocular SLAM

Sangmin Song, Sarath Kodagoda, Marc G. Carmichael, Karthick Thiyagarajan, Amal Gunatilake, Kelly Prentice, Jodi Martin

原文摘要

Robots that act on everyday language requests need maps that record what each object is and where it is. Existing open-vocabulary 3D mapping systems usually require a depth sensor and commit to each object the first time they see it, when the evidence is weakest. We present VOIM, a training-free system that builds open-vocabulary 3D instance maps from RGB-D or from monocular RGB video alone. VOIM accumulates soft label evidence from frozen, off-the-shelf perception models in every voxel across views, and decides labels and object instances only after that evidence has built up. On ScanNet++, VOIM achieves the highest present-class mIoU among the compared methods, 10 points above the strongest baseline. From monocular video alone, VOIM also exceeds HOV-SG and ConceptGraphs run with depth and ground-truth poses. We also conduct real-robot navigation experiments on a quadruped to show that VOIM maps are usable in the real world.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.09073

Latent World Models with Monotone Planning Costs for Image-Goal Navigation

Amirhosein Chahe, Siwei Cai, Lifeng Zhou

原文摘要

Image-goal navigation with latent world models requires not only accurate future prediction, but also a planning cost that reliably ranks candidate action sequences. We define the cost as the cosine distance between the predicted future embedding and the goal embedding, and show that poor cost ordering can mislead sampling-based planners such as Cross-Entropy Method (CEM). To address this, we propose a latent world model built on a frozen DINO-family encoder and train it with two complementary objectives. An autoregressive rollout loss reduces the gap between training and multi-step planning rollouts, while a Monotone Cost Ranking (MCR) loss directly encourages increasingly perturbed action sequences to receive higher planning costs. We also study InfoNCE-based action-contrastive training and find that temporal permutation negatives distort the latent geometry and degrade planning performance. On the GNM navigation dataset, our method outperforms Navigation World Models (NWM), DINO-WM, OmniVLA, and NoMaD, achieving state-of-the-art image-goal navigation performance while reducing orientation error by $2.7\times$ over the same-encoder DINO WM baseline. We also deploy the model zero-shot on a physical robot, where it follows goal-directed paths in unseen indoor and outdoor environments.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.08612

Facial Expression Recognition in the Deep Learning Era: A Systematic Multi-Criteria Review of Methods, Models, Datasets, Performance, Challenges, and Future Research Directions

Spyridon Georgiou, Aggelos Psiris, Spyridon Evangelatos, Thomas Lagkas, Vasileios Argyriou, Panagiotis Sarigiannidis, Iraklis Varlamis, Georgios Th. Papadopoulos

原文摘要

Facial Expression Recognition (FER) has advanced rapidly over the last decade, driven by the shift from handcrafted descriptors and shallow classifiers to deep convolutional, attention-based, vision-language, and foundation-model architectures, and by the parallel growth of large-scale in-the-wild benchmarks spanning categorical, dimensional, compound, micro-expression, Action Unit (AU), and intensity-estimation tasks. Yet the deep learning-based FER landscape has so far been reviewed only along narrow task-, architecture-, or application-specific axes, leaving a holistic, systematically organized account of its recent advances missing. This survey addresses that gap with a comprehensive review of recent deep learning-based FER, explicitly linked to the wider Facial Affect Recognition (FAR) domain. Its main contributions are: a) A description of FER's evolution into five distinct phases, from handcrafted features and classical machine learning to attention-based, vision-language, and foundation-model approaches, with the key milestone works of each, b) A multi-criteria taxonomy analyzing the literature along seven complementary axes: recognition task, input modality, face pre-processing pipeline, network architecture, learning strategy, acquisition setting, and application domain, c) A per-criterion comparative analysis, with critical insights into the strengths and limitations of each category under in-the-wild conditions, d) A task-organized review of public FER datasets, with their annotation schemes, modalities, and evaluation protocols, e) A compilation of performance metrics and a per-task quantitative comparison of representative state-of-the-art methods on widely adopted benchmarks, and f) A discussion of current challenges and promising future directions.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2607.08837

Prompt Driven Exploration: Language as an Exploration Space for VLA Reinforcement Learning

Sunshine Jiang, John Marangola, David Zhang, Raghuram Kowdeed, Ruiyang Luo, Nitish Dashora, Richard Li, Pulkit Agrawal 等 9 位作者

原文摘要

Exploration is essential to reinforcement learning (RL) since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject stochasticity in the action space, but such jitter only yields rollouts close to the original action distribution. Escaping a weak policy often requires global perturbations that action noise cannot produce. Large language models (LLMs) and vision-language-action (VLA) models offer a pathway: they condition the policy on a natural language prompt, and since the rollout follows from it, modifying the prompt induces global changes. The challenge is finding prompts that induce useful global changes. With a weak policy that rarely succeeds, reward is too sparse to select on. Our idea is to refine prompts from the rollouts themselves: a vision-language model (VLM) reasons over the rollout video, diagnoses how the policy responded, and rewrites the prompt to elicit better behavior next time. Sampling a prompt and holding it fixed throughout a rollout provides episode-level commitment, analogous to posterior-sampling exploration. We call this strategy Prompt Driven Exploration (PDE). Across manipulation and reasoning tasks, PDE enables RL to learn successful policies even from zero-reward starts, and improves sample efficiency more broadly. Our website is available at https://xinyunsunshine.github.io/prompt-rl.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.14404

Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Traces

William L. Tong, Ege Cakar, Cengiz Pehlevan

原文摘要

Recent years have witnessed meteoric progress in reasoning models: neural networks that generate intermediate reasoning traces (RTs) before producing a final output. Despite the rapid advancement, our understanding of how RTs support reasoning, and where this paradigm fails, remain incomplete. To promote greater clarity, we introduce PITA: a novel large-scale dataset of over 23 million statements in propositional logic and their corresponding proofs. As a benchmark for robust reasoning, we focus on length generalization: if a model is trained to determine truth or falsity on statements with proofs up to fixed length, how well does it generalize to statements requiring longer proofs? We propose notions of (1) task depth and (2) task breadth, which measure respectively (1) the number of proof steps required to solve a proposition and (2) the number of unique propositions within a task family. We vary these quantities across subsets of PITA, and find that RT models generalize well on relatively broad and shallow subsets, while deteriorating on relatively narrow and deep subsets compared to non-RT baselines. As a controlled point of comparison, we study a separate, tractable transitive inference task that exhibits qualitatively similar behavior. Our accompanying theory explains the scalings observed in this simpler setting, suggesting one mechanism by which breadth can favor RT models while depth can expose long-context weaknesses. Our findings suggest salient benefits and limitations of proof-like reasoning traces in controlled length-generalization settings.

cs.AI · cs.LG · cs.NE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2510.11361

A protocol to reduce worst-case latency in deflection-based on-chip networks

Leandro Soares Indrusiak

原文摘要

We present a novel protocol that reduces worst-case packet latency in deflection-based on-chip interconnect networks. It enforces the deflection of the header of a packet but not its payload, resulting in a reduction in overall network traffic and, more importantly, worst-case packet latency due to decreased pre-injection latency.

cs.NI · cs.PF

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.04273

Integrated Imputation-Classification for Supervised Learning with Missing Data

Yue Liu, Ben Liang, Ali Tizghadam, Ilijc Albanese

原文摘要

We study supervised classification problems with missing feature values. Existing approaches often decouple imputation from classification, producing imputations that may be plausible but uninformative for prediction. Instead, we propose the Integrated Imputation and Classification Network (IICN), which jointly trains an imputer and an ${(n{+}1)}$-class discriminator adversarially with a single class-supervised objective, where the discriminator learns to distinguish among the $n$ true classes and an additional ``imputed'' class. We prove that it admits a global optimum where the imputer and discriminator together implement marginalization over missing coordinates and yield a Bayes-optimal classifier. We evaluate IICN on FashionMNIST, CIFAR-10, and tabular datasets with naturally occurring missingness. IICN outperforms classical impute-then-classify pipelines and recent generative baselines, showing strong robustness and accuracy in challenging settings.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.26705

When are bosonic Gaussian states classical to learn?

Senrui Chen, Antonio Anna Mele, Francesco Anna Mele, John Preskill

原文摘要

A fundamental question in physics is: When does classical behavior emerge from quantum systems? Bosonic Gaussian states provide a natural setting to explore this quantum-classical boundary, as they capture both the classical field behavior and the intrinsic quantum nature of light. Here, we address this problem from a learning-theoretic perspective by asking: When are bosonic Gaussian states classical to learn? That is, under what conditions (if any) can an n-mode bosonic Gaussian state be learned with as few samples, and with operations as simple, as are needed to learn a classical 2n-variate Gaussian distribution? We establish a smooth crossover in learnability governed by the state's thermal fluctuations: - Cold Gaussian states are non-classical to learn: When the covariance matrix satisfies $Σ\le(\frac12+O(\frac1n))I$, i.e. close to the vacuum covariance, tomography under single-copy (i.e., non-entangled) measurements fundamentally requires $Ω(n^3)$ copies, strictly exceeding the sample complexity $Θ(n^2)$ of learning classical Gaussian distributions. We show that this hardness persists even when few-copy entangled measurements are allowed. - Warm Gaussian states are classical to learn: When thermal fluctuations exceed the vacuum noise, parameterized by $Σ\ge(\frac12+ν)I$ for any parameter $ν>0$, we prove that single-copy tomography requires $N=Θ\left(n^2\min(n,1+ν^{-1})\right)$ copies. This bound is tight and is achieved by simple, non-adaptive, unentangled heterodyne measurements. Crucially, for $ν=Ω(1)$, the sample complexity drops to $Θ(n^2)$, matching the classical case. Our results tightly characterize a quantum-to-classical crossover in the learnability of bosonic Gaussian states, reveal a novel connection between fundamental physics and statistical learning theory, and have implications for real-world sensing experiments.

quant-ph · cs.IT · cs.LG · math-ph

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2609.17989

Whom Do AI Agents Serve? Role-Induced Sponsorship Bias in Decision Models and Generative LLMs

Davood Wadi, Yu Ma

原文摘要

Consumers increasingly delegate product search to AI shopping agents powered by generative large language models (LLMs) or non-generative decision models. Because retail platforms monetize through sponsored listings that consumers typically discount, we examine whether an AI agent's evaluation of sponsored listings depends on who delegates it. Across six LLMs and six decision models in Study 1, consumer-delegated agents penalize sponsored listings, whereas naming a booking platform as principal significantly attenuates this sponsorship penalty without instructions to favor advertisers. This sponsorship bias replicates across prompt wordings and LLM reasoning efforts and operates through reduced pre-choice skepticism in LLMs. In Study 2, attributing the paid placement to the platform amplifies sponsorship bias across both model families, and stricter disclosure wording ("Sponsored" vs. "Promoted") fails to eliminate it. In Study 3, prompt-level mitigation removes platform leniency but can over-correct the sponsorship penalty, whereas consumer-aligned fine-tuning eliminates sponsorship bias and better preserves baseline preferences.

econ.GN · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.14343

Nearest-Neighbor Radii under Dependent Sampling

Yuanyuan Gao, Yilong Hou, Zhexiao Lin

原文摘要

Nearest-neighbor methods are fundamental to classical and modern machine learning, yet their geometric properties are typically analyzed under independent sampling. In this paper, we study the nearest-neighbor radii under dependent sampling. We consider strong mixing dependent observations and ask whether dependence changes the scale of nearest-neighbor neighborhoods. We establish distribution-free almost sure convergence under polynomial mixing and sharp non-asymptotic moment bounds under geometric mixing. The moment bounds depend on the local intrinsic dimension rather than the ambient dimension, making the results applicable to high-dimensional data supported on lower-dimensional manifolds. Synthetic experiments and real-world time-series benchmarks illustrate the theory, showing that nearest-neighbor geometry remains informative under dependent sampling.

cs.LG · math.ST · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.08577

Self-Distilling Generative Adversarial Networks

Antoni Nowinowski, Krzysztof Krawiec

原文摘要

In modern GANs, maintaining an Exponential Moving Average (EMA) of the generator's weights is a standard practice, as such an averaged model consistently outperforms the actively trained generator. However, the EMA generator is used for final deployment only and does not influence the training process. To address this missed opportunity, we introduce Self-Distilled GAN (SD-GAN) that employs the EMA generator as a teacher to guide the active generator (student) via perceptual loss. We prove the local asymptotic stability of SD-GAN in the simplified continuous-time Dirac-GAN setting and show that it dampens the parasitic cycling behavior that plagues conventional GANs. Empirical evaluations across established architectures and datasets demonstrate that SD-GAN improves the final image quality on several metrics (FID and random-FID in particular), stabilizes the optimization trajectory and provides additional learning guidance that is not trivially correlated with the conventional adversarial loss. It also proves effective for fine-tuning pretrained GAN models.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.01571

Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness

Aria Masoomi, Mahsa Bazzaz, Adel Javanmard, Vahab Mirrokni

原文摘要

Chain-of-thought (CoT) reasoning enables large language models (LLMs) to solve complex problems by generating intermediate reasoning steps. While much attention has been paid to the length and content of these reasoning chains, far less is known about their internal geometry. We study the geometry of CoT trajectories in the hidden state space of transformer models, formalizing each reasoning chain as a discrete curve in $\mathbb{R}^d$ and characterizing it through spectral, positional, and kinematic geometric functionals. We introduce the effective dimension $d_ρ$ as a measure of trajectory complexity and empirically show that harder tasks exhibit greater effective dimension. Lastly, we explore how kinematic features of the trajectory, mean position, positional dispersion, initial and final hidden states, mean velocity, mean speed, and speed dispersion, can be used to predict solution correctness before generation is complete, and may inform future early-stopping strategies. Experimentally, on 86 mathematical reasoning problems from the MATH500 dataset and three Qwen2.5 model scales (0.5B, 1.5B, and 7B), $d_ρ$ achieves difficulty-prediction AUROC of $0.90$, $0.94$, and $0.96$, respectively. Seven kinematic and positional features predict correctness from only the first $20\%$ of generated tokens, with AUROC between $0.77$ and $0.88$ across scales. These correctness signatures transfer across held-out questions, establishing that the shape of a model's internal reasoning trajectory is a principled window into both task hardness and solution quality.

cs.LG

查看论文
arXiv ↗PDF ↗