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

+1084新增论文
+883其中 AI 相关
+130已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-18 19:45各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 01:37 — 2026-11-19 01:37(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:2026-11-18 04:28最近发现新增版本:2026-11-18 19:45库内论文最新更新时间:2026-11-18 08:00

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。

26,870 已收录论文22,374 AI 相关8,156 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 8,156 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v2arXiv:2605.06660

Verifier-Backed Hard Problem Generation for Mathematical Reasoning

Yuhang Lai, Jiazhan Feng, Yee Whye Teh, Ning Miao

原文摘要

Large Language Models (LLMs) demonstrate strong capability in solving scientific and mathematical problems, yet they struggle to produce valid and challenging novel problems -- an essential component for advancing LLM training and enabling autonomous scientific research. Existing problem generation approaches either depend on expensive human expert involvement or adopt naive self-play paradigms, which frequently yield invalid problems due to reward hacking. This work introduces VHG, a verifier-backed hard problem generation framework built upon three-party self-play. By integrating an independent verifier into the conventional setter-solver duality, our design constrains the setter's reward to be jointly determined by problem validity (evaluated by the verifier) and difficulty (assessed by the solver). We instantiate two verifier variants: a Hard symbolic verifier and a Soft LLM-based verifier, with evaluations conducted on indefinite integral tasks and general mathematical reasoning tasks. Experimental results show that VHG substantially outperforms all baseline methods by a clear margin. Our code is available at https://github.com/Miaow-Lab/VHG.

cs.LG · cs.AI · cs.CL

版本更新 · v4arXiv:2608.26086

TraceML: What Auto-Research Agents Miss in Long-Horizon ML Development

Jiarui Yan, Weiwei Sun, Sijie Li, Wenhan Li, Yiming Yang

原文摘要

Auto-research agents now run machine-learning development unattended for hours, revising data pipelines, models, and validation from their own feedback, yet on most competitions they still finish below strong human competitors. Outcome-based benchmarks record this gap but not its cause, because they grade the final submission and discard the development process behind it. We introduce TraceML, which pairs human and agent work on the same competitions under one version-level schema: 4,465 human Kaggle trajectories across 134 competitions, seven of which are also worked by two agent scaffolds, giving 430 paired human and 207 agent trajectories. Every code version carries its score, its timestamp, and labels for the action taken, its intent, the edit size, and the score effect. Read this way, the gap becomes concrete. Experts alternate data work, validation, model changes, and ensembling, and return to approaches they had set aside. Each agent scaffold instead collapses into a narrow loop: Codex spends its steps re-weighting ensembles and tuning submissions, MLEvolve mutates its model in place, and neither pivots at the human rate nor reopens abandoned work. A short planning prompt distilled from human practice moves the behaviors it names toward the human profile and lifts scores, but the effort profile stays agent-shaped: instruction closes only the part of the gap that reduces to instructions. We release the corpus, the schema, and the labeling models, together with an open-source toolkit that turns a run from any command-line agent into a TraceML trajectory and reads it against the human cohorts.

cs.LG · cs.AI

版本更新 · v2arXiv:2510.03224

Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles

Dong Lao, Yuxiang Zhang, Haniyeh Ehsani Oskouie, Yangchao Wu, Alex Wong, Stefano Soatto

原文摘要

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead to information loss, we propose to "combat noise with noise" by leveraging stochastic resonance to enhance robustness while minimizing information loss. Our approach introduces small translational perturbations to the input image, aligns the transformed feature embeddings, and aggregates them before mapping back to the original reference image. This can be expressed in a closed-form formula, which can be deployed on diverse existing network architectures without introducing additional network modules or fine-tuning for specific attack types. The resulting method is entirely training-free, architecture-agnostic, and attack-agnostic. Empirical results show state-of-the-art robustness on image classification and, for the first time, establish a generic test-time defense for dense prediction tasks, including stereo matching and optical flow, highlighting the method's versatility and practicality. Specifically, relative to clean (unperturbed) performance, our method recovers up to 68.1% of the accuracy loss on image classification, 71.9% on stereo matching, and 29.2% on optical flow under various types of adversarial attacks.

cs.CV · cs.AI · cs.LG

版本更新 · v2arXiv:2608.05174

Art in Humanity's Code

Benoit Baudry, Yogya Gamage, Nadia Gonzalez Fernandez, Lena MK, Roxana Pena Mendieta, Rafaela Souza Pinter, Stefano Zacchiroli

原文摘要

Artist-led open-source libraries such as Processing or openFrameworks have had a major impact on artists and designers who use code as a creative medium. In this work, we conduct the first large-scale empirical study of public code repositories that use these libraries. Our study dives into 1,613,571 code repositories collected from the Software Heritage archive. Combining quantitative and qualitative methods, we investigate the diversity of practices and practitioners in terms of code hosting, geographical distribution, characteristics of code-based creative works and the purposes of these works. Key findings include evidence of the worldwide presence of generative art and creative coding, as well as the adoption of these practices in both education and across creative industries. We illustrate these findings with concrete examples of repositories and contributor profiles around the globe, spanning the spectrum from university curricula to contemporary art. These results lay the groundwork for educators, researchers, and artists who investigate code and creative practices to foster sustained diversity in the construction of our digital world.

cs.CY · cs.SE

版本更新 · v2arXiv:2605.11289

Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning

Ege C. Kaya, Aliasghar Pourghani, Vijay Gupta, Abolfazl Hashemi

原文摘要

Average-reward reinforcement learning requires estimating the gain and a state-dependent bias, which solves the Poisson equation only up to an additive constant. Distributional analogues of the bias inherit this same ambiguity. We introduce a quotient-space formulation in which state-indexed laws are identified up to a common translation, together with a categorical parameterization that respects this symmetry. On this space, we define a projected average-reward distributional operator and show that it is well-defined, non-expansive in a coordinate Cramér metric, and admits fixed points. We interpret the projected fixed points through geometrically-stopped differential returns, whose categorical operators are contractive and whose fixed points converge in the Abel sense to a canonical fixed point of the projected undiscounted operator. We show that the means of the projected fixed points match the scalar bias up to an error caused by endpoint clipping of the categorical projections, and we bound this error. Finally, we establish almost-sure convergence and finite-iteration residual bounds for temporal-difference recursions with gain-centered rewards under i.i.d. and Markovian sampling. When the gain is unknown, we couple the recursion with an online gain estimator and prove the same guarantees under Markovian sampling, with a bound on the gain error.

cs.LG · math.OC

版本更新 · v2arXiv:2609.02789

ShikumiMiner: Mining Recurring Implementation Patterns in AI Codebases

Afsana Tasnim, Saif Uddin Mahmud, Md Erfan, Md Rayhanur Rahman

原文摘要

Large language models are paving the way towards innovation by understanding, analyzing, summarizing and generating content in the modern world. Currently there are thousands of LLM projects developed by engineers in open-source repositories. However, whether these LLM projects have underlying patterns or not remains a question. Exploring these underlying patterns will give new dimensions to the developers who aim to develop these LLM projects. In this paper, we propose ShikumiMiner, a static-analysis framework that combines Abstract Syntax Tree (AST) and Control Flow Graph (CFG) features to detect and compare recurring implementation patterns in C++ local LLM codebases. We analyze ten GitHub open-source repositories and classify functions into seven study-specific categories using a multi-label Random Forest model. Studying these patterns can provide useful insights for developers aiming to design LLM applications.

cs.SE

版本更新 · v3arXiv:2408.08812

TRAM: Test-Time Risk Adaptation with Mixture of Agents

Mohamad Chehade, Amrit Singh Bedi, Souradip Chakraborty, Amy Zhang, Hao Zhu

原文摘要

Deployed reinforcement learning agents often face safety requirements that are specified only after training: new hazard maps, revised risk thresholds, or behavioral alignment constraints. We study zero-update deployment-time adaptation in which a fixed library of risk-neutral source policies must be reused under a newly specified reward-risk tradeoff. We propose TRAM (Test-time Risk Adaptation with Mixture of Agents), a source-scored composition rule that evaluates each source under the target reward and an occupancy-based deployment risk, then selects actions using risk-adjusted source scores. Unlike training-time risk-sensitive methods tied to a fixed surrogate such as return variance, TRAM supports spatial barrier exposure, divergence to a reference behavior, and local volatility risks specified at test time. We make the surrogate nature of the method explicit: TRAM is not claimed to solve the full occupancy-control problem of the stitched policy, but it admits a measurable source-hull mismatch term connecting source-scored risk to realized risk. Experiments in gridworlds, MuJoCo Reacher, Safety-Gymnasium, and an inference-time LLM alignment setting show that TRAM improves deployment risk while preserving reward and requires no parameter updates at test time.

cs.LG

版本更新 · v3arXiv:2606.05487

VASTO: Simultaneous reconstruction of vascular geometry and blood flow from tomographic projections via differentiable topology optimization

Pramod Thombre, Rahul Kumar Padhy, Roshan M. D'Souza, Krishnan Suresh

原文摘要

Computed Tomography Angiography (CTA) is widely used to reconstruct vascular geometry from projection measurements, with conventional approaches such as Filtered Back-Projection (FBP) and Iterative Reconstruction (IR) forming the clinical standard. Despite recent advances, these methods remain susceptible to sparse and noisy measurement, making accurate recovery of critical anatomical features challenging. This consequently leads to poor estimation of blood flow. In this work, we present a fluid-physics-constrained reconstruction framework that leverages topology optimization (TO) to jointly recover vascular geometry and blood flow directly from time-resolved CTA sinograms. The formulation couples a steady incompressible flow model with a transient advection-diffusion contrast transport model, mapped to sinogram space through a differentiable projection operator. The velocity field is recovered as part of the reconstruction, and thus hemodynamic information can be obtained without requiring a separate computational fluid dynamics pipeline. The proposed method is demonstrated on synthetic phantoms under varying sparsity and noise levels, and on representative projection data.

cs.CE

版本更新 · v4arXiv:2408.05086

A systematic framework for generating novel experimental hypotheses from language models

Kanishka Misra, Najoung Kim

原文摘要

Neural language models (LMs) have been shown to capture complex linguistic patterns, yet their utility in understanding human language and more broadly, human cognition, remains debated. While existing work in this area often evaluates human-machine alignment, few studies attempt to translate findings from this enterprise into novel insights about humans. To this end, we propose a systematic framework for hypothesis generation that uses LMs to simulate outcomes of experiments that do not yet exist in the literature. We instantiate this framework in the context of a specific research question in child language development: dative verb acquisition and cross-structural generalization. Through this instantiation, we derive two novel, untested hypotheses: (1) the alignment between argument ordering and discourse prominence features of exposure contexts modulates how children generalize new verbs to unobserved structures; and (2) that this alignment in the first postverbal argument of the exposure context has a more noteworthy effect. Additionally, we also design a set of experiments that can test these hypotheses in the lab with children. This work contributes both a domain-general framework for systematic hypothesis generation via simulated learners and domain-specific, lab-testable hypotheses for child language acquisition research.

cs.CL · cs.AI

版本更新 · v5arXiv:2605.25240

JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment

Russell Yang, Ruishi Chen, Pierce Kelaita, Riya Ranjan, Sibo Ma, Charles Dickens, Matthew Guillod, Megan Ma 等 9 位作者

原文摘要

Two methodologies dominate current practices of benchmarking: rubric-based scoring evaluates items against predefined criteria, whereas comparative judgment elicits pairwise preferences between outputs. Although both methodologies are widely used, the choice between them is rarely justified. We release JudgmentBench, a benchmark of 30 real-world legal tasks, paired with 1,539 rubric scores and 1,530 pairwise preference judgments collected from practicing attorneys--including at major U.S. law firms--with substantial experience. The annotations constitute the first publicly available dataset in a high-expertise domain in which both supervision signals are elicited from the same pool of experts on the same tasks. Using LLM-generated outputs at three constructed quality levels, we provide an initial empirical comparison: comparative judgments recover the intended quality ordering substantially better than rubrics under both a per-task rank-correlation metric (mean Spearman's rank correlation of 0.908 vs. 0.150, estimated difference = 0.758 [0.494, 1.021]) and a per-judgment pairwise win-rate metric (0.669 vs. 0.542, estimated difference = 0.127 [0.067, 0.186]), while requiring less than half the annotation time. The patterns hold for human annotators and LLM autograders. Beyond this initial comparison, the paired structure of the dataset supports a broader research agenda on how expert judgment should be elicited, aggregated, and used as supervision in domains without verifiable ground truth.

cs.CL · cs.AI · cs.CY

版本更新 · v2arXiv:2605.30519

OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation

Lin Zhao, Yushu Wu, Yifan Gong, Yanzhi Wang, Pu Zhao

原文摘要

Autoregressive (AR) video generation extends videos by producing latent chunks sequentially, but scaling to long videos requires repeated access to a growing historical KV cache. Existing methods reduce this cost by truncating the KV cache or compressing it into implicit memory, but both lose explicit access to query-relevant historical details. We propose OmniMem, an explicit full-range memory retrieval framework that performs sparse KV retrieval over the historical cache. To make this practical for chunk-based AR video generation, OmniMem addresses two issues: (i) local bias in sparse KV selection and (ii) Union Explosion in memory access. Adaptive Window Exclusion removes local-window blocks from the selection candidates when sufficient long-range history is available, preserving the sparse budget for informative long-range retrieval. Query-Shared KV Selection reduces cross-query diversity, while Per-Head Scattered KV Access avoids expanding head-specific selections into a large selected KV buffer. This allows each attention head to retrieve non-contiguous KV blocks according to its own selection pattern. Experiments on long-video generation show that OmniMem improves Dynamic Degree by 52.3% and preserves strong consistency over strong baselines, while maintaining comparable memory usage.

cs.CV

版本更新 · v2arXiv:2512.20237

Knowing What is Missing: Efficient Conversational Memory via Explicit Evidence-Gap Tracking

Xingbo Du, Loka Li, Duzhen Zhang, Leonard Song, Le Song

原文摘要

Long-term conversational memory poses a fundamental system challenge for LLM agents: reasoning over all past interactions improves coverage but incurs prohibitive token costs and noise, while retrieval-based methods are efficient yet often fail on multi-hop and temporal questions. Existing multi-step retrievers partially address this gap, but typically operate over an ever-growing textual history, causing context expansion and noise accumulation across iterations. We propose MemR$^3$, a backend-agnostic closed-loop controller that reformulates conversational memory retrieval as explicit stateful decision-making. At each iteration, MemR$^3$ maintains an evidence-gap state consisting of grounded information (evidence) and unresolved information requirements (gaps), and uses this state to route among three actions: retrieve, reflect, and answer. Newly retrieved snippets are incorporated into the state and then masked from subsequent prompts, so the model conditions on a compact summary of progress rather than the full retrieval history. This design turns multi-step memory retrieval into a bounded, inspectable control process whose query-time context scales with the state instead of raw accumulated text. Experiments on LongMemEval$_s$ show that MemR$^3$ surpasses implicit multi-step retrieval baselines and often approaches or exceeds full-context prompting while retrieving only 1%-5% of the full conversation tokens on long conversations. On LoCoMo, MemR$^3$ consistently improves over its underlying RAG- and Zep-based memory backbones. These results suggest that explicit evidence-gap tracking is an effective abstraction for token-efficient conversational memory.

cs.AI

版本更新 · v2arXiv:2607.25310

Human-in-the-Loop Signature Bootstrapping for UAV Hyperspectral PFM-1 Mine Detection

Sagar Lekhak, Prasanna Reddy Pulakurthi, Emmett J. Ientilucci

原文摘要

Hyperspectral imaging (HSI) is useful for material discrimination, but operational mine screening also depends on how many false alarms must be inspected before targets are found. This paper studies PFM-1 landmine detection in unmanned aerial vehicle (UAV) visible and near-infrared (VNIR) HSI using spectral angle mapper (SAM), matched filter (MF), adaptive coherence estimator (ACE), and constrained energy minimization (CEM). We compare a ground-measured SVC signature, a fully informed in-scene core-pixel signature, and a simulated human-in-the-loop signature bootstrap. Besides receiver operating characteristic area under the curve and average precision, we report target-discovery curves and spatial candidate-review counts. Full-review bootstrapping reaches the fully informed in-scene signature case after all seven target regions are verified, but the required inspection effort varies strongly: ACE confirms all regions in two rounds and nine candidate inspections, whereas the SAM variants need thousands of candidate reviews for their final target locations. Code is available at https://github.com/SagarLekhak/IEEE_WHISPERS_2026_UAV_HSI_PFM1.

cs.CV · eess.IV

版本更新 · v2arXiv:2607.18164

A Continual Validation, Updating, and Decision-Making Framework for Self-Adaptive Digital Twins: A Case Study in Additive Manufacturing

Yi-Ping Chen, Ying-Kuan Tsai, Vispi Karkaria, Seul Lee, Daniel Apley, Wei Chen

原文摘要

Digital Twins support real-time decision-making through predictive models of physical systems, yet their reliability can deteriorate as operating conditions evolve. Maintaining predictive fidelity under such changes is challenging, particularly when model adaptation relies on limited streaming data, and updated models must be evaluated before deployment. Here, we present an online adaptation framework that integrates gradient-based drift detection, parameter-efficient fine-tuning, and statistical model validation within model predictive control. Changes in prediction-loss gradients trigger batch-wise model updates using Low-Rank Adaptation, while a paired moving-block bootstrap test evaluates predictive improvement before deploying the updated model. The framework is evaluated using a stochastic dynamical system with abrupt changes and a simulated directed energy deposition process with gradual changes in material properties. Results show improvements in predictive accuracy and uncertainty estimation during the evaluated post-adaptation intervals, alongside improved reference tracking and reduced constraint violations in the manufacturing case study compared with the investigated baselines. These findings demonstrate the potential of integrating continual validation with model adaptation while acknowledging the trade-off between responsiveness and predictive reliability in evolving Digital Twins.

cs.LG · cs.AI · math.ST

版本更新 · v3arXiv:2603.00326

Vectorized Dynamic Histograms for Sparse Oblique Forests

Ariel Lubonja, Jungsang Yoon, Haoyin Xu, Yue Wan, Yilin Xu, Richard Stotz, Mathieu Guillame-Bert, Joshua T. Vogelstein 等 9 位作者

原文摘要

Sparse oblique (SPO), part of the top-ranked configuration of Google's Yggdrasil Decision Forests (YDF), improve the accuracy while maintaining interpretability of Random Forests (RF) and Gradient Boosted Trees (GBT) by scanning a sparse linear combination of features instead of a single feature. Because projections are sampled at runtime, training is significantly slower, as pre-run optimizations such as presorting cannot be used. We overhaul SPO training in YDF, first by fixing inefficiencies in the released version, achieving 2-5x speedup, then by devising two novel methods, one aimed at GBTs and the other at RFs: (1) Hierarchical AVX2 and AVX-512-vectorized histogram filling speeds up typical GBT-depth trees by up to 1.6x in SPO-GBT and 2x for SPO-RF, and (2) runtime-dynamic histograms between vectorized histograms and exact splits, speeds up deeper, RF depth-typical trees (depths 16 to purity) by up to 1.6x with no detectable effect on accuracy. Our optimizations bring SPO-RF training time on par with YDF's axis-aligned RF. We extensively evaluate on 8 natural and 11 synthetic datasets of up to 10.5 million rows and 1.6 million features, from depth 6 to purity, and open-source the implementation.

cs.LG · cs.DC · cs.PF

版本更新 · v2arXiv:2605.08007

Interpreting Reinforcement Learning Agents with Susceptibilities

Chris Elliott, Einar Urdshals, David Quarel, Daniel Murfet

原文摘要

Susceptibilities are a technique for neural network interpretability that studies the response of posterior expectation values of observables to perturbations of the loss. We generalize this construction to the setting of the regret in deep reinforcement learning and investigate the utility of susceptibilities in a simple gridworld model that nevertheless exhibits non-trivial stagewise development. We argue that susceptibilities reveal internal features of the development of the model in parameter space that one cannot detect purely by studying the development of the learned policy. We validate these results with activation-steering, and discuss the framework's extension to RLHF post-training.

cs.LG

版本更新 · v3arXiv:2509.26158

Towards Continual Expansion of Data Coverage: Automatic Text-guided Edge-case Synthesis

Kyeongryeol Go

原文摘要

The performance of deep neural networks is strongly influenced by the quality of their training data. However, mitigating dataset bias by manually curating challenging edge cases remains a major bottleneck. To address this, we propose an automated pipeline for text-guided edge-case synthesis. Our approach employs a Large Language Model, fine-tuned via preference learning, to rephrase image captions into diverse textual prompts that steer a Text-to-Image model toward generating difficult visual scenarios. Evaluated on the FishEye8K object detection benchmark, our method achieves superior robustness, surpassing both naive augmentation and manually engineered prompts. This work establishes a scalable framework that shifts data curation from manual effort to automated, targeted synthesis, offering a promising direction for developing more reliable and continuously improving AI systems. Code is available at https://github.com/gokyeongryeol/ATES.

cs.CV · cs.AI

版本更新 · v2arXiv:2605.30214

GRUFF: LLM Pronoun Fidelity, Reasoning, and Biases in German

Fabian Mewes, Anne Lauscher, Vagrant Gautam

原文摘要

Third-person singular pronouns have long been used to study stereotypical biases in language models and to test their abilities to reason about reference. More recently, the interplay between reasoning and bias has been investigated with the task of pronoun fidelity, which assesses models' abilities to correctly reuse a previously-specified pronoun for a discourse entity, independent of other potentially distracting discourse entities mentioned in between. However, such research focuses on English, a language with limited grammatical gender and almost no gender agreement. In this paper we contribute a novel, large-scale dataset, GRUFF, to measure pronoun fidelity in German, covering four different gender agreement systems in nouns, and four sets of pronouns. With this dataset, we show that LLMs display strong grammatical agreement for masculine and feminine entities in the absence of explicit context, but not for neopronouns xier and en. In the presence of distractors, however, models degrade on all pronoun sets. Finally, we show that occupational stereotypes in this context are poorly correlated across grammatical cases and most models, except ones with closely related architectures.

cs.CL

版本更新 · v3arXiv:2511.13904

Edge Assisted Multi-Camera Vehicle Tracking Framework for Real-Time and Scalable Deployment

Yuqiang Lin, Sam Lockyer, Shucheng Zhang, Florian Stanek, Markus Zarbock, Adrian Evans, Wenbin Li, Yinhai Wang 等 9 位作者

原文摘要

Cameras are a core sensing modality in modern intelligent transportation systems (ITS), providing rich visual information on road-user activities. Multi-Camera Vehicle Tracking (MCVT) uses this data to reconstruct vehicle trajectories across camera networks, supporting applications such as traffic flow prediction and optimisation. However, most existing MCVT studies emphasise tracking accuracy while paying limited attention to real-time performance and scalability, both essential for real-world and city-scale deployment. To address this gap, we propose Edge-Assisted, Scalable and Efficient MCVT (EASE-MCVT), a distributed edge--server framework designed for real-time throughput and scalable operation. On the edge side, each camera stream is processed through object detection, single-camera tracking, geo-mapping and feature extraction, while only lightweight metadata, including vehicle locations and appearance features, is sent to the central server for cross-camera association. To improve both tracking accuracy and system efficiency, EASE-MCVT is optimised from algorithmic and system perspectives. Algorithmically, it introduces a dynamic workload scheme for tracklet-level feature extraction, a server-side re-match module to reconnect fragmented tracklets, and a self-supervised camera link model that learns spatio-temporal constraints to accelerate and stabilise cross-camera association. Systemically, it integrates production-oriented data engineering components to standardise deployment and data exchange for large-scale operation. To the best of our knowledge, EASE-MCVT is the first MCVT framework explicitly designed to address both real-time performance and scalability in a distributed edge--server setting. Experiments on the RoundaboutHD and CityFlow datasets demonstrate real-time throughput with competitive tracking accuracy, paving the way for city-wide real-time traffic management.

cs.CV

版本更新 · v3arXiv:2601.07524

Stagewise Reinforcement Learning and the Geometry of the Regret Landscape

Chris Elliott, Einar Urdshals, David Quarel, Matthew Farrugia-Roberts, Daniel Murfet

原文摘要

Singular learning theory characterizes Bayesian learning as an evolving tradeoff between accuracy and complexity, with transitions between qualitatively different solutions as sample size increases. We extend this theory to reinforcement learning, proving that the concentration of a generalized posterior over policies is governed by the local learning coefficient (LLC), an invariant of the geometry of the regret function. This theory predicts that deep reinforcement learning with SGD should proceed from simple policies with high regret to complex policies with low regret. We verify this prediction empirically in a gridworld environment exhibiting stagewise policy development: phase transitions over training manifest as "opposing staircases" where regret decreases sharply while the LLC increases.

cs.LG

版本更新 · v2arXiv:2509.00305

Language-Aware Information Maximization for Transductive Few-Shot CLIP

Ghassen Baklouti, Maxime Zanella, Ismail Ben Ayed

原文摘要

Transductive few-shot learning has triggered an abundant literature focusing on vision-only models, but is still at a nascent stage within the recent context of foundational vision-language models (VLMs). Only a few recent methods addressed the problem, pointing to the potential of tranduction in VLMs and to the need for VLM-tailored methods. Building on this momentum, we leverage information-theoretic concepts and recent progress in parameter-efficient fine-tuning (PEFT), developing a highly competitive transductive few-shot CLIP method. Specifically, we introduce a novel Language-aware Information MaximizatiOn (LIMO) loss integrating three complementary terms: (i) the mutual information between the vision inputs and the textual class descriptions; (ii) a Kullback-Leibler (KL) divergence penalizing deviation of the network's probabilistic outputs from the text-driven zero-shot predictions; and (iii) a standard cross-entropy loss based on the labeled shots. Furthermore, we challenge the commonly followed fine-tuning practices in the context of transductive few-shot learning, and explore PEFT strategies, completely overlooked in this context. Surprisingly, we observe substantial boosts in performances, which points to the potential of adapting a subset of the model's parameters in the transductive few-shot setting. We report comprehensive evaluations, which show that LIMO outperforms the very recent transductive few-shot CLIP methods by a large margin and yields significant gains over the best-performing inductive methods. Our code is publicly available at:https://github.com/ghassenbaklouti/LIMO

cs.CV

版本更新 · v2arXiv:2611.07502

Coverage Hides Churn: Auditing and Preserving Conformal Decisions as VLM Label Registries Grow

Jai Kumar Sharma, Peeyush Tapadiya

原文摘要

Vision-language classifiers can learn new labels from text alone, so the label lists they serve keep growing. We show that this growth silently changes conformal decisions about old labels. Common softmax-based conformal scores compare each label with an average over all labels; adding labels changes that average, and with it the score of every old label, even when the model, the image, and the old calibration data stay the same. Recalibrating after the update keeps the coverage guarantee, yet across eleven settings it changes at least one old decision on 53-90% of new images. Coverage cannot reveal this, because it checks only the true label: in five controlled settings that keep the old calibration, so that only the normalizer changes, old-class coverage moves by at most 0.01 while 60-67% of images change. We propose a lifecycle audit that measures these changes alongside coverage and set size, and a simple fix, PrefixCP: each class keeps the label registry that existed when it was added. Its old decisions then never change, each class keeps exact class-conditional coverage under exchangeability, and one prefix scan computes all historical normalizers at once. PrefixCP recovers 40.9-58.5% of the set-size gap between never updating the reference and recalibrating, which gives smaller sets but changes old decisions.

cs.CV · cs.LG

版本更新 · v2arXiv:2605.01919

Refining and Repairing Signed Distance Data With Global Consistency

Letao Chen, Sanju Mupparaju, Christopher Batty, Silvia Sellán, Oded Stein

原文摘要

We propose a method to interpolate exact Signed Distance Function (SDF) data from a discrete set of samples. Unlike prior work, our approach ensures that the new SDF data values are fully consistent with the input and each other, such that the augmented data still corresponds to a geometrically realizable surface. We express the theoretical properties of exact SDFs as hard geometric constraints, and construct an efficient greedy algorithm for consistent SDF interpolation that is made even faster with powerful parallelized GPU preprocessing. We exemplify the usefulness of our method by evaluating it on three practical applications: global SDF refinement, in which the SDF data is upsampled without knowledge of the ground truth; mesh reconstruction, where our method can reconstruct highly detailed surfaces using global information from coarse input SDFs; and repair of pseudo-SDFs, which result from many pipelines such as CSG Boolean operations and must be turned into valid SDFs for downstream processing tasks. Our refined SDFs are guaranteed to be consistent with the input, where previous methods have no such guarantee.

cs.GR

版本更新 · v4arXiv:2510.01632

BioBlobs: Unsupervised Discovery of Functional Substructures

Xin Wang, Kaiwen Shi, Carlos Oliver

原文摘要

Protein function is often localized to cohesive substructures, such as catalytic triads, binding pockets, and structural motifs, that occupy only a small fraction of a protein's residues. Yet existing predictive pipelines typically aggregate residue-level embeddings and do not explicitly model or infer these functional substructures, leaving the central biological question unanswered: which substructure of a protein is responsible for its function? We introduce BioBlobs, an encoder-agnostic, end-to-end differentiable framework that compresses a protein into a small set of cohesive substructures (blobs) and predicts function from these blobs alone, so that each blob corresponds to a candidate functional region. Across diverse protein function prediction tasks and both sequence-only and structure-aware protein language models, BioBlobs is competitive with strong baselines while operating on only a small fraction of residues. Trained only on protein function labels, BioBlobs recovers expert-curated functional sites in InterPro and experimentally annotated catalytic sites in the Mechanism and Catalytic Site Atlas, demonstrating unsupervised functional substructure discovery and opening a path to large-scale functional site discovery in unannotated proteins. The discovered blobs adapt their spatial scale to the task, ranging from local catalytic sites to entire structural domains. Code is available at https://github.com/OliverLaboratory/BioBlobs.

q-bio.BM · cs.AI

版本更新 · v2arXiv:2607.05184

Rethinking On-Policy Self-Distillation for Thinking Models

Simran Kaur, Narutatsu Ri, Yinghui He, Liam Fowl, Sanjeev Arora

原文摘要

On-policy self-distillation (OPSD) is a promising approach to recursive self-improvement. In this setting, a model acts as its own teacher when augmented with privileged information, such as a solution to a math problem. Thinking models seem especially well positioned to teach themselves this way, since they can deliberate, verify, and self-correct. Surprisingly, we show that OPSD degrades thinking models on long reasoning traces: across five Qwen3 and OLMo thinking models evaluated on AIME24, AIME25, and HMMT25, privileged-context distillation causes a relative drop of up to 17\% in avg@16 accuracy. The degradation scales with the amount of privileged context withheld from the student and is most pronounced at long rollout budgets, where thinking models otherwise obtain their largest gains. This failure mode extends to distillation from a larger, privileged teacher: on-policy distillation (OPD) improves thinking models, but privileged OPD reverses these gains. Our diagnostics suggest that privileged teacher context reshapes learning at high-entropy forking positions, i.e., rollout positions where multiple continuations remain plausible and may lead to different reasoning paths. Privileged context lowers fork rates in thinking-model rollouts but not in instruction-tuned model rollouts, which may explain the observation that OPSD training helps instruct models more reliably than thinking models.At self-correction branches, privileged OPD penalizes sampled reconsideration tokens that vanilla OPD supports. Consistent with this, thinking models trained with a privileged teacher produce fewer verification, backtracking, and hedging markers, even after length normalization. These findings indicate that applying self-distillation methods to strong thinking models requires further consideration of token-level signal---especially around tokens related to correction and crucial reasoning steps.

cs.AI · cs.LG

版本更新 · v4arXiv:2601.21636

Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation

Jan Schuchardt, Nikita Kalinin

原文摘要

We study privacy amplification for differentially private model training with matrix factorization under random allocation (also known as the balls-in-bins model). Recent work by Choquette-Choo et al. (2025) proposes a sampling-based Monte Carlo approach to compute amplification parameters in this setting. However, their guarantees either only hold with some high probability or require random abstention by the mechanism. Furthermore, the required number of samples for ensuring $(ε,δ)$-DP is inversely proportional to $δ$. In contrast, we develop sampling-free bounds based on Rényi divergence and conditional composition. The former is facilitated by a dynamic programming formulation to efficiently compute the bounds. The latter complements it by offering stronger privacy guarantees for small $ε$, where Rényi divergence bounds inherently lead to an over-approximation. Our framework applies to arbitrary banded and non-banded matrices. Through numerical comparisons, we demonstrate the efficacy of our approach across a broad range of matrix mechanisms used in research and practice.

cs.LG · cs.CR · stat.ML

版本更新 · v2arXiv:2609.30667

StarWM: Self-Supervised Trained Attention Routing for Robust World Models

Zeqiang Zhang, Fabian Wurzberger, Maximilian Otte, Daniel Schmid, Sebastian Gottwald, Arne Peter Raulf, Daniel Alexander Braun

原文摘要

A robust world model must strike the balance between faithfully capturing environmental dynamics and abstracting away from irrelevant content. While reconstruction-based world models ensure faithful supervision, they misallocate representational capacity by pixel area rather than dynamics relevance for visual tasks, which can cause task-irrelevant content to dominate the learned representation. Alternatively, reconstruction-free methods avoid this bias but risk discarding possibly relevant information. We propose StarWM, which uses a cross-attention module trained on self-supervised dynamics to decide where reconstruction applies. A dual-stream decoder then restricts reconstruction to the attended regions, with stop-gradient barriers preventing interference between the two objectives. These components allows reconstruction to supervise the visual content of attended regions without contaminating the latent with non-predictive information. On DeepMind Control with dynamic video backgrounds, default (reward-free) StarWM achieves the strongest performance under random-frame distractors and substantially outperforms reconstruction-based baselines under sequential video. In addition, its reward-augmented variant matches or exceeds reconstruction-free methods on sequential video, achieving the highest overall return across all distractor regimes. Mechanistic probing confirms \starwm{} preserves state attributes with near-perfect fidelity through long-horizon imagination while systematically discarding distractors. Code is available on GitHub.

cs.CV · cs.LG

版本更新 · v3arXiv:2610.36116

Why and How to Do Science When AI Is Better at It: A Framework Grounded in Human Understanding and Direction

Hoda Heidari, Aydin Mohseni

原文摘要

As AI begins to match or exceed human researchers at core scientific tasks, two questions become pressing: \emph{why} should humans keep doing science, and \emph{how} should they use AI when they do? This paper argues that the second can be answered only by answering the first. It holds that one indispensable aim of science is \emph{durable, collective human understanding of the world, pursued in service of human ends and values}. From this principle it derives a two-part test for when a research task can be delegated to AI. The first part, \emph{human understanding}, requires that the scientific community remain able to explain, defend and contest the resulting claims, and retain the skills to do so. The second, \emph{human direction}, requires that judgments about which questions matter and what findings mean stay with accountable humans. Applying the test to each phase of research in the Contributor Roles Taxonomy (CRediT) yields recommendations that fields can tailor to their questions and methods. The framework differs from existing guidance in three ways. It rests on an account of what science is for rather than on integrity norms. It holds even if AI outperforms human researchers, rather than depending on AI's current limitations. And it judges each use of AI by its effects on human understanding and direction rather than by the type of tool, across every phase of research, including peer review and the training of new researchers. It closes with the reforms needed to keep science aimed at human understanding and direction.

cs.AI · cs.CY

版本更新 · v2arXiv:2603.25687

On Neural Scaling Laws for Weather Emulation through Continual Training

Shashank Subramanian, Alexander Kiefer, Arnur Nigmetov, Amir Gholami, Dmitriy Morozov, Michael W. Mahoney

原文摘要

Neural scaling laws, which in some domains can predict the performance of large neural networks as a function of model, data, and compute scale, are the cornerstone of building foundation models in Natural Language Processing and Computer Vision. We study neural scaling in Scientific Machine Learning, focusing on models for weather forecasting. To analyze scaling behavior in as simple a setting as possible, we adopt a minimal, scalable, general-purpose Swin Transformer architecture, and we use continual training with constant learning rates and periodic cooldowns as an efficient training strategy. We show that models trained in this minimalist way follow predictable scaling trends and can outperform standard cosine learning rate schedules. Cooldown phases can be repurposed to improve downstream performance, e.g., enabling accurate multi-step rollouts over longer forecast horizons or sharper predictions through spectral loss adjustments. We also systematically explore a wide range of model and dataset sizes under various compute budgets to construct IsoFLOP curves, and we identify compute-optimal training regimes. Extrapolating these trends to larger scales highlights potential performance limits, demonstrating that neural scaling can serve as an important diagnostic for efficient resource allocation. We open-source our code for reproducibility

cs.LG

版本更新 · v2arXiv:2606.17310

SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues

Suttisak Wizadwongsa, Hyelin Nam, Supasorn Suwajanakorn, Jeong Joon Park

原文摘要

Generating novel renderings of a scene along user-defined camera trajectories from a single monocular video, dubbed video retaking, is a compelling but difficult problem in content creation and visual effects. Existing geometry-guided approaches reconstruct a 4D representation from the source video and render it along the target trajectory to condition video diffusion models. However, this guidance degrades as the target camera departs from the source trajectory, leaving newly revealed regions sparse or entirely missing. We propose SierpinskiCam, which addresses this limitation by augmenting geometry-based guidance with Sierpinski dome texture cues that contains rich trackable features even under large viewpoint changes. We further introduce a reference video conditioning mechanism that appends source-video tokens to the target-token sequence and separates the two streams with negative RoPE indices, enabling appearance grounding without architectural modification or per-video adaptation. Extensive experiments show that SierpinskiCam achieves significant gains in camera controllability, geometric consistency, and video quality across diverse and challenging retaking scenarios. Project page: https://hyelinnam.github.io/SierpinskiCam/.

cs.CV