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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 05:52 — 2026-11-22 05:52(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

论文修订列表

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 8,992 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
版本更新 · v2arXiv:2606.11087

Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning

Zhiyuan Zhou, Andy Peng, Charles Xu, Qiyang Li, Jost Tobias Springenberg, Kevin Frans, Sergey Levine

原文摘要

Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control. While they are known to scale stably in the supervised imitation learning setting, incorporating them into reinforcement learning (RL) pipelines for policy improvement has proven more difficult. It often requires specialized training objectives or backpropagating through denoising processes, which cause well-known issues with stability and affect scalability. In this paper we study the question of whether simple policy improvement schemes at test time alone, leaving stable supervised policy training intact, can be a competitive alternative which sidesteps these issues. To this end, we propose QGF (Q-Guided Flow), an RL algorithm that performs policy optimization entirely at test time. QGF works by pre-training both a reference flow policy (via a standard behavioral cloning objective) and a value function critic and, at test time, using the value gradient to guide the reference policy to generate higher-value actions without any additional policy learning. Empirically, QGF outperforms prior test-time RL methods on single-task and goal-conditioned offline RL benchmarks with high-dimensional action spaces, and is competitive with state-of-the-art training-time algorithms while being much cheaper to run. Moreover, it exhibits favorable scaling with model size by avoiding the instability of actor-critic training, offering a practical and effective alternative RL algorithm with expressive policies.

cs.LG · cs.AI

版本更新 · v2arXiv:2610.34662

StreamVibe: Proactive Video Agents for Evolving User Intent

Chengzhi Liu, Yuxiang Lai, Yuzhe Yang, Yanqing Liu, Jiheng Hou, Yue Cao, Haonan Wang, Ruixi Fan 等 16 位作者

原文摘要

Vision-language models are shifting from offline passive understanding toward online proactive interaction. However, prevailing methods largely rely on explicit requests while overlooking implicit user intents (e.g., "where should I click next?" when a user is navigating a website) and fail to continuously update their understanding as user intents evolve. These limitations make them less suitable for intent-aware interaction in real-world scenarios. To address these challenges, we introduce StreamVibe-Bench, a new benchmark that serves as a testbed for user intent understanding and interaction, comprising 4.1K evaluation samples and 85K training samples spanning explicit, implicit, and dynamic intents. Building on this benchmark, we develop StreamVibe-VL, a streaming proactive model that infers implicit user intents from continuous observations and dynamically adapts its interactions as these intents evolve. We further introduce StreamVibe-Harness, which maintains user intents as persistent states with flexible lifecycles through hierarchical memory, enabling it to track the latest user intents and environmental states. Our experiments reveal three key findings: (i) StreamVibe-VL preserves strong general video understanding capabilities while improving response timing and answer quality by 10.7% over existing baselines; (ii) existing proactive models remain limited in understanding user intents and determining when to respond, especially under implicit and dynamic intents; and (iii) StreamVibe-Harness further improves response consistency and adaptation during sustained interactions, resulting in a 12.3% gain in proactive interaction performance.

cs.CV

版本更新 · v2arXiv:2506.23532

GViT: Representing Images as Gaussians for Visual Recognition

Jefferson Hernandez, Ruozhen He, Guha Balakrishnan, Alexander C. Berg, Vicente Ordonez

原文摘要

We introduce GViT, a supervised classification framework that uses patch-conditioned 2D Gaussian primitives as input tokens for ViT backbones. A ViT-S-sized encoder predicts each primitive's position, scale, orientation, color, and opacity in one forward pass. The same parameters are constrained to reconstruct the image through a differentiable renderer, as well as serve as classifier inputs. During training, classifier-gradient guidance shapes primitive geometry and appearance under an image reconstruction constraint. On ImageNet-1K, GViT-B achieves 76.9% top-1 accuracy, compared with 79.8% for ViT-B/16 trained with the same recipe. Gaussian tokens also provide explicit spatial support for explanation maps. Grad-CAM over Gaussians improves on patch-based Grad-CAM in segmentation and token-deletion probes, while other probe comparisons are comparable to a ViT. A covariance-based foreground diagnostic on the PASCAL VOC segmentation task further measures the geometry learned through supervised guidance. These results establish the feasibility of recognition from renderable Gaussian parameters and characterize how task supervision shapes this inspectable representation.

cs.CV · cs.LG

版本更新 · v2arXiv:2604.19909

Finite-Length Empirical Comparison of Polar, PAC, and Invertible-Extractor Secrecy Codes over the Wiretap BSC

Jaswanthi Mandalapu, Tyler Kann, Andrew Thangaraj, Matthieu R. Bloch

原文摘要

We compare three secrecy-coding schemes for the degraded wiretap binary symmetric channel (BSC) in the finite-blocklength regime: (i) polar wiretap coset codes, (ii) PAC codes used as wiretap coset codes, and (iii) the invertible-extractor (IE) framework of Bellare--Tessaro. Our comparison is empirical and uses a common semantic-secrecy metric (distinguishing advantage). For polar coset codes, we compute Eve's polarized bit-channel capacities (via the Tal--Vardy construction) to obtain explicit finite-length upper bounds on mutual-information leakage, yielding strong secrecy bounds. For PAC coset codes, we prove that Eve's synthesized bit-channels are equivalent to those of polar codes (up to a permutation), so the same leakage bounds apply; we then convert these strong-secrecy bounds into semantic-secrecy guarantees for symmetric wiretap channels. For the IE scheme, we use the closed-form semantic-secrecy bounds already established. Finally, we report finite-length results that jointly characterize (a) semantic-secrecy guarantees against Eve and (b) frame-error-rate performance at Bob. Our simulations indicate that Polar and PAC codes exhibit comparable reliability performance under the considered finite-length settings, while PAC codes retain the same secrecy bounds as Polar codes. More broadly, our results highlight that non-universal designs of wiretap codes provide tighter secrecy guarantees than universal design based on invertible extractors.

cs.IT · eess.SP

版本更新 · v2arXiv:2609.34481

CARDAMOM: A Micro-Dialectal Arabic Speech Dataset for ASR

Bashar Talafha, Samar M. Magdy, Aisha Alansari, Alaa Alkhawaldeh, Abdurrahman Juma, Sharaf Makahleh, Nour Gamal, Omar Attia 等 39 位作者

原文摘要

We present Cardamom, a micro-dialectal Arabic speech dataset designed to support fine-grained evaluation and adaptation of automatic speech recognition (ASR) systems. Community-curated by native speakers familiar with the represented varieties, Cardamom contains approximately 40 hours of transcribed YouTube speech spanning 21 micro-dialects across Egypt, Jordan, Lebanon, Mauritania, Palestine, and Saudi Arabia. Each segment is annotated with one or more operational micro-dialect labels, code-switching information, and utterance-level perceived gender, enabling analysis of sub-country variation that is obscured by conventional country-level labels. We describe the collection and annotation process, motivate the micro-dialect inventory linguistically, and benchmark four multilingual ASR systems in zero-shot and adapted settings. The strongest zero-shot system obtains 43.47% aggregate WER, with particularly high error rates on Mauritanian and Lebanese varieties; adaptation on Cardamom reduces its WER to 35.21%. Audio-based identification experiments further highlight the difficulty of fine-grained micro-dialect recognition: across three training seeds, a dedicated classifier obtains 46.85% accuracy and 31.95% F1. Cardamom provides a resource for studying localized dialectal variation and developing Arabic speech systems with broader regional coverage.

cs.CL

版本更新 · v2arXiv:2610.32883

When Should I Trust This? Designing and Evaluating Factuality Indicators for LLM-based Chatbots

Greta Warren, Christine M. Lehane, Jessica Heal, Sila Eser, Denise M. Leto, Isabelle Augenstein

原文摘要

Generative AI systems increasingly mediate how people seek information, yet communicating AI factuality to laypeople remains challenging. Through a mixed-methods investigation involving interviews (N=8), a survey (N=1,000), and an experiment (N=5,151), we examine how people evaluate AI-generated information for gardening, mathematical, and medical queries, and how factuality indicators (confidence and sources) shape perceptions. Our interviews and survey show people selectively verify AI responses using external and AI-provided evidence, moderated by contextual factors. Although confidence-indicators affected trust and accuracy perceptions, people hold diverse, ambiguous interpretations of AI confidence. Sources were viewed as crucial, yet users raised concerns about source reliability and verification effort. Our experiment showed that confidence and source-based indicators influenced initial perceptions, but effects disappeared once participants learned the response's correctness. Medical queries elicited skepticism regardless of indicator. Findings motivate helping users interpret model confidence and integrating source information into the interface to support calibrated trust in AI-supported information-seeking.

cs.HC

版本更新 · v3arXiv:2609.03930

Fixed Suffix Dependency Ratio: Quantifying the Dual-Track Mechanism of Gender Assignment in Latvian Loanwords

Yelingyun Zhang

原文摘要

Existing research has repeatedly observed the tendency for English loanwords to cluster in the masculine gender across different recipient languages, yet the origin of this pattern remains difficult to determine, as fixed morphological rules and default assignments are frequently analysed together. This study proposes the Fixed Suffix Dependency Ratio (FSDR) to quantify the degree of reliance on fixed derivational suffixes across different genders, and to distinguish between morphological anchoring and free-choice in distribution. By examining 1,832 Latvian noun lemma types, the results reveal a significant FSDR asymmetry within the loanword system: feminine loanwords rely significantly more on fixed derivational suffixes, while masculine loanwords are more concentrated in the free-choice zone. This pattern exhibits loanword specificity and has become more pronounced in contemporary usage. FSDR therefore provides a quantitative framework for testing default gender and shows how masculine default can be activated and reinforced under language contact.

cs.CL

版本更新 · v3arXiv:2412.05126

Robust and efficient enriched representation with intrinsic neuronal heterogeneity

Arash Golmohammadi, Jannik Luboeinski, Christian Tetzlaff

原文摘要

Heterogeneity is a ubiquitous property of many biological systems with profound computational implications. Integrating this heterogeneity into artificial computing systems has recently gained attention. While optimizing neuronal and synaptic heterogeneity for a specific task can achieve state-of-the-art performance, such top-down optimization is biologically implausible, prone to catastrophic forgetting, and both data- and energy-intensive. In contrast, biological organisms possess inherent, task-unspecific, stable heterogeneity and can perform many tasks with minimal metabolic cost. Inspired by this, we study task-agnostic heterogeneity in recurrent neural networks solving hundreds of diverse temporal tasks. Heterogeneity is introduced as intrinsic disorder in neuronal membrane time constants. Our results show that intrinsic heterogeneity markedly improves overall performance and robustness in both rate- and spike-coded networks. Small heterogeneous networks, even without recurrence, match the performance of large, highly recurrent, homogeneous networks at a fraction of the cost and complexity. We suggest that, despite being task-agnostic, heterogeneity enhances representational capacity by diversifying neuronal responses, demonstrated on two machine-learning and one neuroscience benchmark. Our work highlights the utility of intrinsic task-agnostic heterogeneity for versatile, energy-efficient computing--a highly relevant property for the neuromorphic community, where device-to-device variability could be exploited to offset limited training budgets and architectural constraints.

cs.LG · cs.NE

版本更新 · v2arXiv:2609.25633

Robust, Estimator-Agnostic Dynamic 3DGS Compression

Chenjunjie Wang, Zixi Huang, Yao Wang, Jona Ballé

原文摘要

Dynamic 3D Gaussian splats (3DGS) model time-varying scenes using a separate Gaussian set per frame. While neighboring video frames are highly correlated due to smooth motion, Gaussian representations retain this correlation to varying degrees, depending on whether the estimator tracks them across time. Some 3DGS compression methods integrate the estimation to exploit temporal redundancy; here, we focus on robust compression regardless of the estimator. We concatenate groups of frames into one Gaussian set, augment each Gaussian with a frame index, and pass it to a static (i.e., non-temporal) 3DGS codec, converting temporal redundancy into spatial redundancy. Concatenated sets are spatially partitioned to limit memory. Our technique requires neither a motion model nor knowledge of the training method. Averaged over six N3DV sequences, all six static codecs achieve gains on tracked sets (-42.0% to -71.8% BD-rate) over per-frame coding. On untracked sets, all codecs except HGSC, which appears incompatible with our technique, remain competitive with per-frame coding (-3.5% to +5.0%). We further replace D-FCGS's I-frame coding with our technique while retaining its P-frame coding, yielding an overall BD-rate of -46.2%. We propose to visualize "trackedness" using an inter-frame similarity metric. The project is available at https://wcjj1236.github.io/d3dgs-benchmark.

eess.IV · cs.CV

版本更新 · v2arXiv:2606.04284

Interpretability Is Not Just a Tax: Sparsity and Diversity Yield Legible and Composable Reward Experts for Personalization

Yifan Wang, Jinyi Mu, Mayank Jobanputra, Yu Wang, Ji-Ung Lee, Soyoung Oh, Isabel Valera, Vera Demberg

原文摘要

Preference modeling aims to capture heterogeneous human values and increasingly relies on learning latent components to represent this variation without fine-grained supervision. What these components actually represent, however, is rarely examined. We audit Mixture-of-Experts (MoE) reward models along three rungs---semantic coherence, functional correspondence, and composability---in controlled and real-world settings, holding the architecture and training data fixed so that differences isolate the effect of the training objective. Our diagnosis is that the components conventional MoE reward models learn are entangled, which limits not only interpretability but also the personalization such models are built for. The entanglement is not intrinsic to the architecture but a property of the training objective: off-the-shelf sparsity and diversity regularizers already substantially reduce it. The resulting configuration, which we call sparse MoE, recovers all underlying semantic categories without domain supervision in a controlled setting, reaching 84.8% expert purity against 60.8% for conventional MoE; on real-world data its experts admit human-interpretable task- and domain-level descriptions aligned with their functional strengths. Targeted interventions on routing weights produce predictable preference changes, showing that these interpretations are behaviorally grounded rather than merely descriptive. Crucially, the disentanglement induced by this objective also makes the experts composable: lightweight router updates yield a 25.81-point improvement in few-shot personalization with 50 examples, roughly 2.7 times the gain of the identical architecture and adaptation procedure applied to entangled experts. Together, these results show that MoE reward models can learn interpretable expert structure, and that the same structure can substantially improve personalization.

cs.LG · cs.AI · cs.CL

版本更新 · v2arXiv:2512.17281

LibriVAD: A Scalable Open Dataset with Deep Learning Benchmarks for Robust Voice Activity Detection

Ioannis Stylianou, Achintya kr. Sarkar, Nauman Dawalatabad, James Glass, Zheng-Hua Tan

原文摘要

Robust Voice Activity Detection (VAD) remains a challenging task, especially under noisy, diverse, and unseen acoustic conditions. Beyond algorithmic development, a key limitation in advancing VAD research is the lack of large-scale, systematically controlled, and publicly available datasets. To address this, we introduce \textbf{LibriVAD} -- a scalable open-source dataset derived from LibriSpeech and augmented with diverse real-world and synthetic noise sources. LibriVAD enables systematic control over speech-to-noise ratio, silence-to-speech ratio (SSR), and noise diversity, and is released in three sizes (15 GB, 150 GB, and 1.5 TB) with two variants (LibriVAD-NonConcat and LibriVAD-Concat) to support different experimental setups. We benchmark multiple feature-model combinations, including waveform, Mel-Frequency Cepstral Coefficients (MFCC), and Gammatone filter bank cepstral coefficients, and introduce the Vision Transformer (ViT) architecture for VAD. Our experiments show that ViT with MFCC features consistently outperforms established VAD models such as boosted deep neural network and convolutional long short-term memory deep neural network across seen, unseen, and out-of-distribution (OOD) conditions, including evaluation on the real-world VOiCES dataset. We further analyze the impact of dataset size and SSR on model generalization. Experimental results show that scaling the dataset size from small-scale to medium- or large-scale noticeably and consistently improves VAD performance under OOD conditions, while appropriately balancing SSR enhances OOD performance in the small-scale setting. All datasets, trained models, and code are publicly available to foster reproducibility and accelerate progress in VAD research.

cs.SD · cs.LG

版本更新 · v2arXiv:2609.06242

Task-Oriented Semantic Communication for Hazard Warning and Remote Operation in Connected Vehicle Platoons

S M Sabit Bananee, Shahriar Hasan, Muhammad Mahbub Alam, Nafiul Rashid

原文摘要

Connected and automated vehicle platoons require reliable dissemination of task-relevant hazard information to enable appropriate downstream responses, with unresolved situations additionally requiring remote human intervention. However, the limited channel bandwidth of V2X communication makes high-volume sensor data transmission challenging, motivating the exchange of only task-relevant information rather than raw sensor data. This paper proposes an integrated semantic and task-oriented communication framework for cooperative hazard response and remote operation in automated vehicle platoons. The framework combines onboard instance segmentation and monocular depth estimation for task-oriented hazard decision-making with Stable Diffusion Variational Autoencoder (SD-VAE)-based semantic scene compression. Task-relevant hazard information and the compact semantic representation are jointly disseminated through a broadcast-based Emergency Semantic Message (ESM) over the existing V2X protocol stack. Evaluation demonstrates that SD-VAE consistently outperforms JPEG and JPEG 2000 on task-relevant reconstruction metrics, exhibiting graceful degradation rather than a sharp cliff effect under low-SINR conditions, demonstrating its feasibility for remote scene reconstruction when human intervention is required. Moreover, an extensive campaign of 7,290 simulation runs shows a low overall inter-vehicle collision rate of 0.99%, with collisions occurring mainly under extreme high-speed and short-gap conditions.

cs.NI · cs.CV

版本更新 · v3arXiv:2602.10081

Anagent For Enhancing Scientific Table & Figure Analysis

Xuehang Guo, Zhiyong Lu, Tom Hope, Qingyun Wang

原文摘要

In scientific research, analysis requires accurately interpreting complex multimodal knowledge, integrating evidence from different sources, and drawing inferences grounded in domain-specific knowledge. However, current artificial intelligence (AI) systems struggle to consistently demonstrate such capabilities. The complexity and variability of scientific tables and figures, combined with heterogeneous structures and long-context requirements, pose fundamental obstacles to scientific table \& figure analysis. To quantify these challenges, we introduce AnaBench, a large-scale benchmark featuring $63,178$ instances from nine scientific domains, systematically categorized along seven complexity dimensions. To tackle these challenges, we propose Anagent, a multi-agent framework for enhanced scientific table \& figure analysis through four specialized agents: Planner decomposes tasks into actionable subtasks, Expert retrieves task-specific information through targeted tool execution, Solver synthesizes information to generate coherent analysis, and Critic performs iterative refinement through five-dimensional quality assessment. We further develop modular training strategies that leverage supervised finetuning and specialized reinforcement learning to optimize individual capabilities while maintaining effective collaboration. Comprehensive evaluation across 170 subdomains demonstrates that Anagent achieves substantial improvements, up to $\uparrow 13.43\%$ in training-free settings and $\uparrow 42.12\%$ with finetuning, while revealing that task-oriented reasoning and context-aware problem-solving are essential for high-quality scientific table \& figure analysis. Our project page: https://xhguo7.github.io/Anagent/.

cs.CL · cs.AI

版本更新 · v2arXiv:2608.06352

CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks

Fanzhe Meng, Guoxin Chen, Jiale Zhao, Shuang Sun, Yuzhi Lin, Wayne Xin Zhao, Ruihua Song, Ji-Rong Wen 等 9 位作者

原文摘要

Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning. Executable validation establishes feasibility, yet does not reveal how a task behaves relative to a given solver setting. In this paper, we present CalibForge, an autonomous terminal-task synthesis system that uses verified solver behavior to revise candidate tasks through adversarial solver calibration. Multi-solver calibration targets disagreement within a heterogeneous solver pool, whereas contrastive solver calibration targets a designated strong-pass/weak-fail relation; both operationalize a solver-relative learnable zone anchored in demonstrated solvability. Using CalibForge, we construct 5,431 calibrated terminal tasks. Our ablations show that both strategies yield more effective supervision than authoring and validation alone or ordinary single-solver feedback. Models trained on the full collection achieve 31.84% and 47.57% on Terminal-Bench 2.1. The largest improvements over the corresponding base model reach 23.97 percentage points on Terminal-Bench 2.1, 26.54 points on SWE-bench Pro, and 30.04 points on Doc2Repo. Together, these results support solver-relative learnability as a practical target for constructing effective and transferable agent training data.

cs.LG · cs.CL

版本更新 · v2arXiv:2610.12113

A Geometric Approach to Soft Actor-Critic with Zonotopes for Locomotion Learning

Panagiotis Roditis, Panagiotis P. Filntisis, Petros Maragos

原文摘要

Actor--critic methods in reinforcement learning control overestimation bias by taking the minimum of two critics. This uses the same aggregation rule everywhere, regardless of how the critics disagree. We propose Geometric Zonotope Soft Actor-Critic (GeZo-SAC), which uses auxiliary geometric representations to adapt critic pessimism to the state and action. Alongside its scalar value, each critic predicts a set of generators defining a zonotope. Probing this zonotope along sampled directions provides a geometric width, subtracted from each critic value as a pessimistic offset, and a measure of disagreement between the two critics, aggregated with log-sum-exp as a smooth approximation to the tropical (max-plus) addition. This disagreement controls how the critics are combined, moving from a width-weighted average toward the usual minimum as disagreement increases. At inference, the deployed policy is an unmodified SAC actor, since the generators are used only on the critic side during training. Across four MuJoCo-v5 locomotion benchmarks and six off-policy baselines, GeZo-SAC achieves the highest mean return on Ant-v5 and Hopper-v5 and remains competitive with other methods on the remaining tasks. Our analysis further shows that GeZo-SAC achieves the lowest average actuator work and action effort per metre among the evaluated methods, while maintaining near-zero measured overestimation frequency across all four environments.

cs.LG · cs.AI

版本更新 · v2arXiv:2608.10329

Who Gets Heeded? An Obligation-Level Audit of Responsiveness in EPA Rulemaking

Jianing Fan, Yue Yao

原文摘要

Notice-and-comment rulemaking gives any affected party the same formal right to influence federal regulation, but formal access is not substantive capacity to shape rule text. Existing measurement strategies operate at the rule or aggregate-corpus level, too coarse to capture the discrete regulatory obligations where commenters seek change. We introduce obligation-level responsiveness auditing, an auditable, AI-assisted framework for measuring whether public-comment engagement co-occurs with changes to specific regulatory obligations. The framework extracts proposed and final-rule obligations, matches comments to the obligations they address, and classifies proposed-to-final outcomes; we test each of these AI-assisted components against blind human judgment. We apply the framework to 70,075 comments across 36 EPA anchor rulemakings, drawn from a corpus of 786,197 comments across 6,145 dockets from 2010-2022. Three descriptive findings emerge. First, engagement is associated with revision across rulemakings, but not clearly within the same rulemaking. Second, support-versus-opposition direction does not clearly differentiate outcomes, an informative null inconsistent with simple preference aggregation. Third, under a permissive reconstruction of commenter type, organizational-majority engagement concentrates in editorial-refinement rather than substantive-modification outcomes across rulemakings. A blind human audit of the outcome labels behind this finding preserves it under corrected labels and reveals that text-similarity methods are insufficient for distinguishing editorial from substantive regulatory change. Together, these findings locate the equity asymmetry upstream of agency response: in which rulemakings and obligations different commenter populations have the capacity to identify, interpret, and contest. Obligation-level auditing makes this upstream inequity visible.

cs.CY · cs.CL

版本更新 · v2arXiv:2610.02260

MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching

Yesom Park, Kelvin Kan, Qifan Chen, Thomas Flynn, Hayden Schaeffer, Xihaier Luo

原文摘要

Flow matching models excel at generative modeling, and many downstream applications require their samples to satisfy prescribed constraints, such as observed measurements and physical laws. However, existing constrained samplers often face a trade-off: \textit{enforcing constraints can substantially displace samples from the pretrained data distribution}. To address this trade-off, we introduce \textbf{MintFlow}, a training-free constrained sampling framework that formulates constraint enforcement as a minimal intervention on the pretrained flow trajectory. MintFlow seeks the minimal perturbation of an intermediate flow state such that its subsequent evolution under the pretrained flow field satisfies the target constraint. By minimally perturbing the flow state while keeping the pretrained flow field unchanged, MintFlow enforces the constraint while minimizing unnecessary deviation from the pretrained distribution. An adjoint formulation yields a closed-form expression for this perturbation, eliminating expensive iterative optimization. Furthermore, MintFlow adaptively selects the intervention time to balance the required perturbation magnitude with its amplification by the remaining flow. Across a range of tasks in generative vision and physical system modeling, MintFlow achieves competitive constraint satisfaction while preserving the pretrained generative distribution substantially better than state-of-the-art constrained methods.

cs.AI

版本更新 · v2arXiv:2607.25276

FunnelAL: Retrieve-then-Rank Active Learning for Single-Class Discovery

Reihaneh Rostami, Brian Goodwin

原文摘要

We present FunnelAL, a retrieve-then-rank active learning system for single-class discovery, which adapts the multi-stage funnel architecture of industrial recommender systems to data annotation. Starting from one positive and one negative example, FunnelAL repeats three stages: (1) embedding-based retrieval that narrows the corpus to a candidate set, (2) a ranking stage that exploits a learned ranker (RankNet) and, once batch precision falls, mixes in committee-based exploration (QBC), and (3) the annotator's labels, which refine both stages for the next round. We evaluate on five datasets, three benchmarks and two large corpora of up to 2.7 million images, each with two different pretrained encoders, DINOv2 and CLIP. With clean labels and DINOv2, FunnelAL has the best mean rank over the five datasets, and with CLIP it shares the best rank with its ablation Funnel-RankNet. On the three benchmarks it discovers positives significantly faster than the classical and uncertainty-based baselines and than PF-MA, and no significant difference from PF-MA's final F1 was detected. With DINOv2, no significant difference from SEALS's active-search mode (most-likely-positive selection) was detected on most datasets. With CLIP, FunnelAL discovers significantly faster than it on three of the five. On iNaturalist's working set of 2.15 million images FunnelAL selects eight times faster than the neighborhood baselines as we implemented them (SEALS in both its modes and AnchorAL, which select only among the nearest neighbors of labeled items). There, PF-MA and uncertainty sampling, which label items near the decision boundary across the whole pool, reach a higher F1 under our evaluation protocol. Under 10% annotator label noise it has a higher F1 than every baseline on three of the five datasets with DINOv2 and on all five with CLIP, and SEALS's active-search mode is more robust at higher rates.

cs.CV · cs.IR · cs.LG

版本更新 · v2arXiv:2610.20906

Task-Centric Multimodal Learning for Cognitive Impairment Detection

Sankalp Vaish, Rishank Singh, Sumukh Veeramalla, Caroline Summerour, John A. Batsis, Xiaohui Liang

原文摘要

Dementia affects millions of older adults worldwide, yet early detection remains difficult outside clinical settings. Traditional models primarily rely on text or voice-based responses, capturing only a limited view of human cognition despite the inherently multimodal nature of human expression. This work proposes a contactless, multimodal screening framework that leverages video, audio, and text signals collected during structured voice-based interactions with Amazon Alexa. By incorporating these modalities, our approach captures a more holistic representation of human behavior encompassing speech patterns, vocal characteristics, facial expressions, and linguistic structure, which may enable more accurate detection of cognitive decline. Different participants completed three conversational tasks designed to probe spontaneous speech, comprehension, and recall. We pursued three objectives: (1) evaluate which of the three Alexa tasks provides the most informative cognitive signals, (2) compare the effectiveness of unimodal models, and (3) assess the benefits of multimodal fusion models. Task-level analysis shows that the video model achieves its best performance on Command-Reading, with an accuracy of 0.65 (AUC 0.69), while the audio model performs best on Question-Answering, reaching an accuracy of 0.67 (AUC 0.73). In contrast, the multimodal model demonstrates consistently stable performance across tasks, achieving an accuracy of 0.76 (AUC 0.75) on Command-Reading and 0.76 (AUC 0.73) on Question-Answering. These findings demonstrate that multimodal behavioral cues captured through naturalistic interactions can reliably distinguish MCI from healthy aging, highlighting the limitations of traditional diagnostic paradigms and supporting the shift toward multimodal, real-world cognitive assessment frameworks.

cs.LG · cs.CL

版本更新 · v2arXiv:2606.06492

Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution

Liliana Hotsko, Yinxi Li, Yuntian Deng, Pengyu Nie

原文摘要

Code language models need repository-level context to resolve imports, APIs, and project conventions. Existing methods inject this knowledge as long inputs (retrieved through RAG or dependency analysis) or through per-repository fine-tuning and LoRA---costly at repository scale and brittle to evolving codebases. We introduce Code2LoRA, a hypernetwork framework that generates repository-specific LoRA adapters, effectively injecting repository knowledge with zero inference-time token overhead. Code2LoRA supports two usage scenarios: Code2LoRA-Static converts a single repository snapshot into an adapter, suitable for comprehension of stable codebases; while Code2LoRA-Evo maintains an adapter backed by a GRU hidden state updated per code diff, suitable for active development of evolving codebases. To evaluate Code2LoRA against parameter-efficient fine-tuning baselines, we build RepoPeftBench, a benchmark of 604 Python repositories with two tracks: a static track with 40K training and 12K test assertion-completion tasks, and an evolution track with 215K commit-derived training and 87K commit-derived test tasks. On the static track, Code2LoRA-Static achieves 63.8% cross-repo and 66.2% in-repo exact match, matching the per-repository LoRA upper bound; on the evolution track, Code2LoRA-Evo achieves 60.3% cross-repo exact match (+5.2 pp over a single shared LoRA). Code2LoRA's code can be found at https://anonymous.4open.science/r/code2lora-6857; the model checkpoints and RepoPeftBench datasets can be found at https://huggingface.co/code2lora.

cs.SE · cs.AI · cs.CL

版本更新 · v2arXiv:2410.21024

Breccia and basalt classification of thin sections of Apollo rocks with deep learning

Freja Thoresen, Aidan Cowley, Romeo Haak, Jonas Lewe, Clara Moriceau, Piotr Knapczyk, Victoria S. Engelschiøn

原文摘要

Human exploration of the moon is expected to resume in the next decade, following the last such activities in the Apollo programme time. One of the major objectives of returning to the Moon is to continue retrieving geological samples, with a focus on collecting high-quality specimens to maximize scientific return. Tools that assist astronauts in making informed decisions about sample collection activities can maximize the scientific value of future lunar missions. A lunar rock classifier is a tool that can potentially provide the necessary information for astronauts to analyze lunar rock samples, allowing them to augment in-situ value identification of samples. Towards demonstrating the value of such a tool, in this paper, we introduce a framework for classifying rock types in thin sections of lunar rocks. We leverage the vast collection of petrographic thin-section images from the Apollo missions, captured under plane-polarized light (PPL), cross-polarised light (XPL), and reflected light at varying magnifications. Advanced machine learning methods, including contrastive learning, are applied to analyze these images and extract meaningful features. The contrastive learning approach fine-tunes a pre-trained Inception-Resnet-v2 network with the SimCLR loss function. The fine-tuned Inception-Resnet-v2 network can then extract essential features effectively from the thin-section images of Apollo rocks. A simple binary classifier is trained using transfer learning from the fine-tuned Inception-ResNet-v2 to 98.44\% ($\pm$1.47) accuracy in separating breccias from basalts.

astro-ph.EP · astro-ph.IM · cs.LG

版本更新 · v2arXiv:2610.03445

Corrupted but Correct: Why Vision-Language Models Lie to Themselves Internally

Arun Josephraj Arokiaraj, Chenyi Huang, Zekun Wu, Adriano Koshiyama

原文摘要

A targeted adversarial perturbation can drive a vision-language model's (VLM's) teacher-forced training loss for a fixed target caption to near zero, yet the same model, allowed to generate freely, produces the original, correct description with no trace of the target. We call this dissociation the train/inference gap, and give it a precise mechanistic account on Qwen2.5-VL-7B-Instruct using a controlled two-stage PGD attack on 200 held-out COCO images. First, we show that image-level pixel statistics, including a correctly re-implemented, texture-based attackability measure from the CNN robustness literature, have essentially no predictive power over which images are corrupted (best predictor r=-0.050, p=0.484; ridge regression R^2=0.069). Second, using the logit lens, we localise the gap to a single autoregressive step: the rank of the target token, conditioned on the correct first token already being generated, is fixed at exactly 3,488 out of 152,064 vocabulary entries for every image and every condition, with zero variance. Third, tracking target-token rank across all 28 LLM decoder layers reveals that the visual encoder corrupts every image's representation by a comparable margin regardless of eventual outcome, but the language model decoder then differentially arbitrates: amplifying the corrupted signal for susceptible images and actively suppressing it, past its clean-image baseline, for resistant ones (p<0.001, rank-biserial r=0.579). A linear probe on the merger hidden state separates these two outcomes with AUC=0.858, though we flag a circularity concern in this estimate. Together these results argue that adversarial robustness in autoregressive VLMs is substantially a property of the language decoder's prior, not the visual encoder, with direct implications for where faithfulness evaluations and defenses for deployed VLM systems should be targeted.

cs.CV · cs.AI

版本更新 · v2arXiv:2607.18220

Approximate Envy-Freeness and Pareto Optimality Beyond Additivity

Harish Chandramouleeswaran, Prajakta Nimbhorkar

原文摘要

We study the compatibility of envy-freeness up to one good (EF1) and Pareto optimality (PO) beyond additive valuations. For two agents with monotone submodular valuations, we prove that a $2/3$-EF1+PO allocation always exists, while for every $α>3/4$, an $α$-EF1+PO allocation may fail to exist even for unweighted coverage valuations. A six-good EF1+PO counterexample resolves the longstanding exact existence question negatively. Exact EF1+PO does exist when one agent has a monotone submodular valuation and the remaining agents have identical additive valuations. For two agents, we also establish tight EF$k$+PO item thresholds of $4k+1$, $2k+1$, and $3k+1$ for two submodular agents, two subadditive agents, and one subadditive and one additive agent, respectively. Finally, deciding whether an EF$k$+PO allocation exists is NP-hard for every fixed integer $k\ge1$, even for three agents with unweighted coverage valuations, one of whom has an additive valuation.

cs.GT · cs.DS

版本更新 · v2arXiv:2603.11137

Scaling Reasoning Efficiently via Relaxed On-Policy Distillation

Jongwoo Ko, Sara Abdali, Young Jin Kim, Tianyi Chen, Pashmina Cameron

原文摘要

On-policy distillation (OPD) is a promising approach for transferring reasoning capabilities to capacity-constrained models, yet sampled-token OPD often suffers from entropy collapse and negative transfer. We identify uniform credit allocation as a key bottleneck: existing objectives obtain dense teacher feedback on student-generated trajectories, but apply it uniformly across sampled tokens despite highly heterogeneous token-level signals. Most tokens carry redundant near-zero credit, while rare heavy-tailed negative credits can dominate updates and prematurely suppress plausible reasoning trajectories. We introduce REOPOLD (Relaxed On-Policy Distillation), a framework that relaxes this uniform assignment by controlling where teacher feedback is applied, how strongly it affects the update, and when the allocation rule changes during training. Across diverse reasoning tasks, REOPOLD improves sampled-token OPD over recent post-training baselines with up to 12x higher sample efficiency, and extends to cross-vocabulary distillation, self-distillation, and test-time scaling.

cs.LG · cs.CL

版本更新 · v2arXiv:2509.05512HF 社区推荐

Quaternion Approximate Networks for Enhanced Image Classification and Oriented Object Detection

Bryce Grant, Peng Wang

原文摘要

This paper introduces Quaternion Approximate Networks (QUAN), a novel deep learning framework that leverages quaternion algebra for rotation equivariant image classification and object detection. Unlike conventional quaternion neural networks attempting to operate entirely in the quaternion domain, QUAN approximates quaternion convolution through Hamilton product decomposition using real-valued operations. This approach preserves geometric properties while enabling efficient implementation with custom CUDA kernels. We introduce Independent Quaternion Batch Normalization (IQBN) for training stability and extend quaternion operations to spatial attention mechanisms. QUAN is evaluated on image classification (CIFAR-10/100, ImageNet), object detection (COCO, DOTA), and robotic perception tasks. In classification tasks, QUAN achieves higher accuracy with fewer parameters and faster convergence compared to existing convolution and quaternion-based models. For objection detection, QUAN demonstrates improved parameter efficiency and rotation handling over standard Convolutional Neural Networks (CNNs) while establishing the SOTA for quaternion CNNs in this downstream task. These results highlight its potential for deployment in resource-constrained robotic systems requiring rotation-aware perception and application in other domains. Code: https://cwru-aism.github.io/ QUANpaper/

cs.CV · cs.RO

版本更新 · v3arXiv:2601.16152

Referential Regimes: Transformation-Based Identity Profiles for Neutral Substrates

Denise M. Case

原文摘要

Data systems operating under persistent legal, institutional, and analytic disagreement require shared reference without presupposing agreement about interpretation. This paper investigates identity preservation under transformation, building on the conditional neutrality result of Neutral Substrates (arXiv:2601.14271). We pair candidate identity bases with families of record transformations and classify each family as preserving, breaking, neutral, or inapplicable for a basis. Using invariant-defined identity bases and explicit effect models, we derive and certify six classification cells in Lean 4 for scope decomposition, rule refinement, and forking. The derivations show how classifications depend on field granularity, admissible transformation steps, and explicit continuity warrants. We also characterize the identity relations generated by invariant-preserving steps. Two bases generate equal relations exactly when they agree on the preservation of every admissible step in a shared comparison domain, and a single separating step witnesses a difference. The formalization makes identity claims auditable, provides testable conditions for systems that transform records, and exposes the assumptions behind each classification. The results are conditional on the declared bases, models, and warrants, whose adequacy for particular referents requires independent justification.

cs.LO · cs.AI

版本更新 · v2arXiv:2602.02491

New explanations and inference for least angle regression

Karl B. Gregory, Daniel J. Nordman

原文摘要

Efron et al. (2004) introduced least angle regression (LAR) as an algorithm for linear predictions, intended as an alternative to forward selection with connections to penalized regression. However, LAR has remained somewhat of a "black box," where some basic behavioral properties of LAR output are not well understood, including an appropriate termination point for the algorithm. We provide a novel framework for inference with LAR, which also allows LAR to be understood from new perspectives with several newly developed mathematical properties. The LAR algorithm at a data level can viewed as estimating a population counterpart "path" that organizes a response mean along regressor variables which are ordered according to a decreasing series of population "correlation" parameters; such parameters are shown to have meaningful interpretations for explaining variable contributions whereby zero correlations denote unimportant variables. In the output of LAR, estimates of all non-zero population correlations turn out to have independent normal distributions for use in inference, while estimates of zero-valued population correlations have a certain non-normal joint distribution. These properties help to provide a formal rule for stopping the LAR algorithm. While the standard bootstrap for regression can fail for LAR, a modified bootstrap provides a practical and formally justified tool for interpreting the entrance of variables and quantifying uncertainty in estimation. The LAR inference method is studied through simulation and illustrated with data examples.

math.ST · stat.ML

版本更新 · v3arXiv:2610.23284

Annotrace: A Workbench for Step-Level Annotation of Agent Traces

Chenyi Huang, Arun Josephraj Arokiaraj, Bin Wu, Sahan Bulathwela

原文摘要

Every study of why LLM agents fail begins by labelling traces by hand, and every such study builds its own throwaway tool. Observability platforms record agent traces but offer no structured labelling; annotation tools label text but have no notion of a step, a delegation or a tool call, leaving it unclear what the smallest unit of execution to label should be. Annotrace reads six trace formats, including OpenTelemetry GenAI, LangSmith and Langfuse, and turns each run into an ordered, nested list of steps. The annotator writes their own labelling codebook; a frontier model proposes a starting set from a sample of their own traces, answers first, and is asked exactly the questions the human is asked, making annotation a joint human-AI process. Annotrace measures agreement between any two annotators, human or AI. On a multi-agent question-answering corpus it reproduces a previous manual effort's 235 annotation units exactly, and two models labelling the same traces agree 91% of the time at $κ= 0.82$.

cs.AI · cs.CL · cs.HC · cs.MA

版本更新 · v2arXiv:2602.10156

STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations

Boyang Fu, Sameer Gabbita, George Dasoulas, Xiang Lin, Shanghua Gao, Xiaorui Su, Soumya Ghosh, Marinka Zitnik

原文摘要

Prediction of the transcriptional response of a cell to a genetic perturbation is a central problem in the computational modeling of gene regulation. Perturbations of the same gene can produce different transcriptional responses depending on the targeted locus, such as an alternative transcription start site or a distal regulatory element, and gene-level perturbation models represent these distinct interventions with a single gene identifier. We introduce STRAND, a generative model that encodes the regulatory DNA sequence at the perturbation locus and uses this encoding to parameterize a conditional transport process from control to perturbed single-cell states. Sequence conditioning enables zero-shot prediction for perturbation targets absent from training and supports locus-resolved inputs at 128 bp model resolution within a 524 kb sequence window. On CRISPRi screens in K562, Jurkat, and RPE1 cells, STRAND achieves the best average rank on few-shot and unseen-gene benchmarks, with gains of up to 33% in perturbation discrimination, and improves transfer to held-out cell lines by up to 0.12 in $Δ$Pearson. Ablation studies attribute these gains to sequence conditioning and to conditional transport. At the locus level, STRAND distinguishes alternative transcription start sites and validated regulatory elements that gene-identifier models represent as a single perturbation. STRAND is available at https://github.com/mims-harvard/STRAND.

q-bio.GN · cs.LG · q-bio.CB

版本更新 · v2arXiv:2510.13992

Optimizing Spectral Signature in Code Backdoor Detection

Quoc Hung Le, Thanh Le-Cong, Bach Le, Bowen Xu

原文摘要

As Large Language Models (LLMs) are increasingly integrated into software development workflows, they also become prime targets for adversarial attacks. Among these, backdoor attacks are a significant threat, allowing attackers to manipulate model outputs through hidden triggers embedded in training data. Detecting such backdoors remains a challenge, and one promising approach is the use of Spectral Signature defense methods that identify poisoned data by analyzing feature representations through eigenvectors. While some prior works have explored Spectral Signatures for backdoor detection in neural networks, recent studies suggest that these methods may not be optimally effective for code models. In this paper, we revisit the applicability of Spectral Signature-based defenses in the context of backdoor attacks on code models. We systematically evaluate their effectiveness under various attack scenarios and defense configurations, analyzing their strengths and limitations. We found that the widely used setting of Spectral Signature in code backdoor detection is often suboptimal. Hence, we explored the impact of different settings of the key factors. We discovered a new proxy metric that can more accurately estimate the actual performance of Spectral Signature without model retraining after the defense. Our findings contribute to a deeper understanding of the configurations of Spectral Signature defenses in securing code models and offer insights into potential improvements for future research.

cs.SE · cs.LG