跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+229新增论文
+172其中 AI 相关
+31已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-13 10:11 · 全站最近入库：2026-11-13 10:10各信源进度 →

统计口径与数据新鲜度

统计 2026-11-12 10:14 — 2026-11-13 10:14（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：2026-11-13 10:11最近发现新增版本：2026-11-13 10:10库内论文最新更新时间：2026-11-11 13:12

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。

21,904 已收录论文18,495 AI 相关6,106 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 18,495 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-13 10:09（北京时间）
新论文 · v1arXiv:2610.38850

Autonomous Quantum Measurement with Agentic AI

Eunbi Rha, Abhijatmedhi Chotrattanapituk, Mouyang Cheng, Chung-tao Chou, Shenyong Ye, Ashley S. Dale, Long Ju, Luqiao Liu 等 9 位作者

原文摘要

Quantum materials exhibit diverse electronic and functional phenomena, but their characterization requires extensive experimental expertise, iterative decision-making and accumulated laboratory knowledge that is difficult to document and transfer. Here we introduce Quantum Agent (QUANTA), an agentic artificial intelligence (AI) framework for autonomous quantum-materials characterization. Using a widely adopted Physical Property Measurement System (PPMS) as an experimental platform, QUANTA combines retrieval augmentation using scientific literature, experimental protocols and prior measurements with specialized agents for experimental planning, troubleshooting, and data interpretation. A separate deterministic control layer validates instrument actions. Guided by incoming data, QUANTA evaluates measurement quality, revises experimental plans and selects subsequent measurements. We demonstrate these capabilities through transport measurements of the topological Weyl semimetal TaP, as well as investigations of nonlinear responses in magnetic material Co2MnGa. These results establish QUANTA as a generalizable framework for evidence-driven, safeguarded and closed-loop quantum-materials characterization.

cond-mat.mtrl-sci · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.12094

Differentiable Systematic Resampling for Variational Sequential Monte Carlo

Fredrik Cumlin, Saikat Chatterjee

原文摘要

Particle filters are a standard tool for nonlinear state estimation, but their resampling step is discrete, preventing gradient-based learning in variational sequential Monte Carlo. We introduce Differentiable Systematic Resampling (DSR), a temperature-controlled relaxation of systematic resampling, that preserves the CDF-ordered, banded structure of systematic resampling while enabling full gradient flow. DSR converges to exact systematic resampling as the temperature vanishes, and we prove a pointwise exponential convergence rate for the induced bias. Compared to optimal-transport-based differentiable resampling, DSR avoids iterative solvers and has substantially lower computational overhead. Experiments on stochastic dynamical systems and real-world handwriting data show that DSR achieves comparable or superior filtering and dynamics learning performance.

stat.ML · cs.LG · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38838

Discovery of Diverse and Realistic Financial Tail-Risk Using Generative Flow Networks

Adir Serruya, Gilad Katz

原文摘要

Accurate modeling of rare, high-impact financial events is essential for robust risk management. Sampling-based techniques such as Sequential Markov Chain Monte Carlo (SMCMC) generate diverse scenarios but inefficiently explore high-risk regions, while Deep Reinforcement Learning (DRL) converges on narrow sets of scenarios, limiting diversity. We present GRID, which uses Generative Flow Networks (GFlowNets) -- samplers that draw objects in proportion to a reward -- to systematically generate diverse and realistic financial tail-risk scenarios. Building on continuous GFlowNets, GRID introduces a flexible mixture-policy architecture with variable-specific distribution families for high-dimensional, sequential macro-financial data, together with plausibility constraints that keep generated trajectories realistic. A central practical advantage is robustness to reward-proxy imperfection: because GFlowNets sample proportionally rather than maximize, they remain broadly exploratory even when the oracle's out-of-sample accuracy is low -- an unavoidable reality in financial forecasting. On three real-world crises, GRID improves scenario diversity, realism, and tail-risk coverage over RL and MCMC baselines, and ablations over oracle architectures and distribution families yield practical insights into continuous GFlowNet behavior under noisy rewards.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38835

What to randomize matters: a controlled study of volume, axis and representation in low-data molecular generation

Neerav Kaushal, Alisa Teige, Ajay MNV Penmatsa

原文摘要

Chemical language models can struggle to generate new molecules when trained on small datasets, where a model may reproduce training examples rather than learn a useful generative distribution. Randomized SMILES augmentation varies atom traversal, whereas Sequential Attachment-based Fragment Embedding (SAFE) also allows the order of fragment blocks to vary. How these distinct sources of representational variation affect low-data molecular generation has not been clearly studied. Here, using 1,000 seed molecules to train an autoregressive sequence model, we compare canonical SAFE with randomized SAFE at increasing corpus sizes, isolate atom-order and fragment-order axes of SAFE randomization, and compare fully randomized SAFE with randomized SMILES at molecule-by-molecule matched training corpora. Three findings emerge. First, randomization of SAFE alone raises the genuine yield of novel molecules more than 450-fold, turning a model that merely reproduces its training set into a practical molecular generator. Second, the two axes of randomization act jointly rather than additively: atom order alone reaches a tenth, and fragment order alone a seventh, of the genuine yield obtained when both vary, which is four times their combined contribution. Third, at matched corpus size and compute, randomized SAFE delivers 2.8 times the genuine yield of randomized SMILES. Welch tests with Games-Howell post-hoc comparisons resolve every difference on the primary outcomes. In the low-data regime, thus, what one randomizes rather than only how much determines whether augmentation produces new molecules or merely new spellings of the training set.

cs.LG · cs.CE · cs.CL · q-bio.BM · q-bio.QM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38833

Discovering Jailbreaks via Curriculum of Models

Michał Burzyński, Noah T. Rossi, Shomit Basu, Andy Arditi

原文摘要

Automated jailbreak discovery aims to find prompts that elicit prohibited behaviors from safety-trained language models, helping developers identify vulnerabilities before deployment. One class of approaches uses reinforcement learning to train an investigator model to generate prompts that elicit a specified behavior from a target model. However, training directly against a safety-trained target is difficult because nearly all prompts are refused, leaving the investigator with a sparse reward signal. Prior work addresses this with the propensity bound (PRBO), a proxy reward estimated by sampling responses from a more compliant target, and then adjusting for how likely those responses would have been under the original target. We introduce Curriculum of Models (CoM), an alternative method that trains the investigator against a sequence of modified versions of the target, progressing gradually from a version that readily exhibits the specified behavior to the original target. For jailbreak discovery, training begins against a target version that rarely refuses harmful requests, and advances to the next, harder version once the investigator reliably elicits the behavior from the current one. We evaluate CoM on elicitation tasks involving CBRN materials, explosives, and illicit drugs, using two open-weight targets, gemma-4-31b-it and gpt-oss-120b. We compare against PRBO and direct training on the original target without a curriculum. When the investigator is trained to elicit a single behavior, CoM finds successful jailbreaks more reliably than either baseline. When trained on multiple behaviors simultaneously, the CoM-trained investigator can elicit held-out behaviors, though PRBO-trained investigators achieve higher success rates. Our results suggest that a simple curriculum over target models offers a promising approach for addressing sparse rewards in rare-behavior elicitation.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38830

Beyond Region Memory: Local Point Tracking for Vocal Cord Localization in Video Laryngoscopy

Huayu Wang, Gyungmin Ko, Jung Heon Kim, Jia-Xian Jian, Dae Kon Kim, Dong Keon Lee, Hsiang-Wei Huang, Pau-Choo Chung 等 12 位作者

原文摘要

Reliable vocal-cord localization in emergency video laryngoscopy remains visually challenging due to rapid tissue deformation, specular highlights, and instrument occlusions. We propose Local Point Tracking (LPT), a robust framework that combines a single-frame detector, local point propagation, and stateless mask refinement. LPT follows a localize first, snap second pipeline. First, a single-frame semantic detector generates sparse anchors, within which LPT initializes local query points (SAM-supported by default, with a regular grid as fallback). A point-propagation module tracks these points through detector-missed frames and recovers temporal bounding boxes from their geometry. Second, because point-derived boxes can be loose around the visible boundary, a box-snap step refines the selected box to the target boundary. This decomposition keeps temporal state in local point coordinates rather than a stateful mask or whole-region representation, while the spatial refinement module handles single-frame boundary precision without feeding mask errors back into temporal memory. Extensive evaluations on two distinct datasets demonstrate that our proposed LPT method achieves strong overall performance against existing baselines, with the best mAP_50, success AUC, and missing rate on both datasets. Furthermore, ablation studies confirm that point tracking primarily enhances temporal tracking robustness, while box-snap refinement effectively improves boundary tightness.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38825

Evaluating Visual Realism of AI-Generated Videos with Eye Tracking

Danqing Shi, Lan Jiang, Jake Lyons, Miri Zilka

原文摘要

Human evaluation of AI-generated videos has so far relied on explicit human feedback, such as judgments or ratings. While these signals capture the conclusions viewers reach, they fail to offer insights into the perception that leads to them. This paper investigates eye tracking as a complementary human evaluation signal for AI-generated videos. We conducted two Visual Turing Test (VTT) experiments with a total of 90 participants on videos generated by latest generative models, in which participants watched each video twice and then gave their feedback. Across the experiments, we collected 4,286 valid eye-tracking trials on 438 videos. Our analysis indicates that gaze patterns offer informative evaluation signals that align with explicit human feedback. Building on the findings, we propose the first computational method GazeEval to predict the perceived visual realism of AI-generated videos from eye-tracking data. It achieves 71.3% accuracy in prediction, providing evidence that eye tracking data carries informative signals about how people evaluate a video. We release the study data to support further research on eye tracking for evaluating AI-generated video.

cs.HC · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38822

CopyLoop: Fast Looped Transformer Decoding via Context Copying and Shallow Screening

Wenyu Du, Stephen Chung

原文摘要

Looped Transformers increase computational capacity through the repeated application of shared blocks, but their recurrent depth makes conventional full-depth decoding expensive. While existing speculative pipelines accelerate generation by processing consecutive token positions at varying depths, they are typically limited by sequential decoding overheads. We introduce CopyLoop, a training-free decoding algorithm that combines low-cost context-copy proposals with shallow screening and continuous recurrent scheduling. Rather than step-by-step generation, CopyLoop proposes multi-token suffixes from repeated context. It then evaluates them early at a shallow recurrent depth to efficiently filter out incorrect branches, processing newer blocks concurrently while earlier blocks are still progressing toward full-depth verification. We evaluate CopyLoop across six model checkpoints from the Ouro, Raven, and Huginn families, covering code generation and multi-step mathematical reasoning. CopyLoop achieves decoding speedups of 2.98x--10.70x over full-depth autoregressive decoding on Base models and 2.74x--3.52x on Thinking models, consistently outperforming or closely matching all competing baselines across evaluation tasks. Furthermore, ablation studies confirm a strong synergy between shallow screening and continuous scheduling, while our analyses show that CopyLoop requires only lightweight model calibration and yields greater speedups on longer generations with reusable contexts.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38816

UnEZ: A Fully Unsupervised Self-Templating Neural Network for Redshift and Line Strength Estimation

Asha Abd, Karl Glazebrook, Colin Jacobs

原文摘要

As spectroscopic surveys grow, estimating galaxy properties such as metallicity, star formation rate, and redshift becomes computationally cumbersome. Methods of estimating such properties rely on template spectra or curated redshift catalogs, which fail to represent the diversity of objects seen in large-scale surveys. We present UnEZ, a fully unsupervised, physics-informed machine learning model that can predict spectroscopic redshifts and line strengths with no prior redshift or line strength labels. An encoder predicts emission and absorption line amplitudes/widths, and a fixed deterministic decoder constructs a unique template, estimated redshift, redshift confidence curve, and spectral model. UnEZ was tested on the Sloan Digital Sky Survey (SDSS) Data Release 18 due to its large dataset and thoroughly vetted redshift catalog which serves as an independent benchmark. Despite the lack of templates, line strength labels, or redshift labels, UnEZ's performance competes with modern redshift estimation algorithms. At SNR > 10, UnEZ achieves an outlier fraction of 0.459% and a normalized median absolute deviation (NMAD) of $1.237 \times 10^{-4}$. At SNR > 3, UnEZ achieves an outlier fraction of 3.89% and an NMAD of $1.471 \times 10^{-4}$. Furthermore, we demonstrate how UnEZ's line strength and redshift predictions can be utilized for various purposes such as constructing template spectra required in traditional redshift estimation algorithms. UnEZ illustrates how a fully unsupervised neural network can allow redshift, among other galaxy properties, to emerge naturally from the spectra themselves, providing a template-free, label-free approach that scales to the demands of future surveys.

astro-ph.IM · astro-ph.GA · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.36195

Learning to Read Braille: Benchmarking and Improving Braille Recognition Capabilities of VLMs

Kartik Jangra, Atharva Gawane, Siddharth Pulipaka, Hemachandran Karah, Raj Dabre

原文摘要

Despite rapid progress in visual understanding and document transcription, modern vision-language models (VLMs) struggle with a fundamental accessibility task: reading Braille from images. We introduce BrailleBench, a manually curated benchmark of 259 real-world Grade-1 and Grade-2 Braille images. We evaluate proprietary, open-weight, OCR-specialized, and tool-assisted multimodal systems and find that standalone general-purpose models perform poorly at directly transcribing Braille images, whereas tool-assisted systems perform much better. We design a synthetic Braille generation pipeline with diverse layouts and image perturbations. A 2B VLM model trained on our synthetic data reaches 87% exact match on Grade-1 and 61% on Grade-2 BrailleBench, outperforming standalone VLMs and achieving the highest Grade-2 exact match score among the evaluated systems. We further show that high accuracy on synthetic validation data does not guarantee high accuracy on real photographs in our experiments: models trained on prior synthetic data reach up to 96% on their synthetic validation set but at most 3.26% on Grade-1 BrailleBench. Our results identify an accessibility-relevant capability gap in multimodal systems and show that targeted synthetic supervision can improve real-world Braille transcription.

cs.CV · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38809

Causal Attention on CPU: A Cache-Aware and Load-Balanced Scheduling Kernel for Prefill

Kwun Fung Lau, Frost Mitchell, Kanya Mo, Emani Ashok

原文摘要

Agentic AI drives significant productivity gains across diverse domains, but concurrent long-context prefills from multiple agents can saturate GPU compute resources. Although CPUs offer a viable alternative, existing CPU attention kernels fall short in adapting to multi-tier cache hierarchies and lack effective thread scheduling. To address this, we introduce CACPU, a high-performance attention kernel featuring tiered cache blocking and an in-kernel task dispatching mechanism designed for causal full-sequence prefilling. CACPU achieves up to a 2.01x speedup over PyTorch SDPA, FlexAttention, and SGLang attention kernels. Integrated into SGLang, it reduces Time to First Token (TTFT) of Llama-3.1-8B by up to 1.74x while preserving model accuracy.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.08441

DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards

Haoyu Hu, Xuandong Zhao, Xuhai "Orson'' Xu, Nori Jacoby

原文摘要

Reinforcement learning with verifiable rewards (RLVR) generates hundreds of thousands of tokens per training step, with rollout generation dominating the computational cost. The overall token budget can be controlled along two main dimensions: (i) deciding which prompts to allocate rollouts to, and (ii) deciding how long each rollout should be. Prior work has generally controlled only one of these dimensions at a time. We show that jointly tuning both decisions under a shared compute budget improves both reasoning quality and wall-clock training time. We instantiate this view as \textbf{DU}al-controlled tok\textbf{E}n alloca\textbf{T}ion (DUET), a computationally efficient layer over GRPO that uses a lightweight pre-rollout surrogate of prompt informativeness to set how many rollouts each prompt receives, and a marker-gated abort rule with importance reweighting to set when to stop them. On Qwen3-1.7B trained on MATH, DUET outperforms full-budget GRPO and the other three budget-aware baseline methods. DUET's advantage further generalizes to other benchmarks across math and coding, and is on par with the best baseline on the scientific Q\&A domain, while also achieving a $1.62\times$ wall-clock speedup. More notably, using only 50\% of the token budget, DUET still outperforms all baseline methods at their full budget, achieving an even higher $2.51\times$ speedup over full-budget GRPO. We verify the high performance of DUET on other backbone LLMs, including Qwen3-4B to 14B and Llama-3.2-3B-Instruct. Notably, the gap between DUET and the strongest baseline \emph{widens} as the budget tightens, contrary to the usual pattern in which efficient methods trade off quality as compute decreases. More broadly, these results suggest that DUET budget-aware control strategies are valuable not only for accelerating training, but also for improving the quality of the learning signal.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38797

Pinpointing Pivot Points: The DECIDE Framework for Data Analysis Decision Importances

Zachary T. Rewolinski, Jan Simson, Frauke Kreuter, Christoph Kern, Bin Yu

原文摘要

Human judgment calls made throughout the data science life cycle can change the conclusions drawn from data. Independent analysts often make different choices when given the same data, leading to often unacceptable variations in results and contributing to the ongoing reproducibility crisis across scientific disciplines. The rapid adoption of agentic tools threatens to amplify this crisis. Several approaches have been developed to address this variation by following the same strategy: repeating an analysis under different combinations of analytical decisions and inspecting the distribution of outcomes. Examples include multiverse analysis, specification curve analysis, and vibration of effects. More broadly, the Predictability-Computability-Stability (PCS) framework assesses how documented judgment calls across the data science life cycle affect conclusions, with predictability serving as a reality-check that a model captures signal. Each of these approaches results in a "multiverse" object. While the distribution of outcomes reflects the overall variability of conclusions, estimating the influence of each individual decision requires additional tools. A common heuristic is to train a model to predict the outcome from these decisions and treat its coefficients or feature importances as proxies for each decision's influence. Although this strategy may work in certain cases, it assumes the model is correctly specified and accurately predicts the outcome, which we show is not always the case. In this work, we introduce DECIDE, a model-free framework that quantifies each decision's importance from the actual outcomes across the plausible decision space, avoiding issues of predictability by design. We demonstrate the effectiveness of DECIDE by applying it to real-world multiverse analyses. We further provide what is, to our knowledge, the first formal definition of the multiverse.

stat.ML · cs.LG · stat.ME

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38796

Routed Continual Learning

Michael Philip, Mahesh Balakrishnan, David Geraghty, David Mao, Vidhya Venkat, Ilya Mironov

原文摘要

Agents deployed at scale repeatedly encounter related problems, and it is natural to let them learn from each other's experience rather than starting over each time. Unfortunately, there is no single way to retain that experience that works well across settings, and no way to know in advance which future problems a given experience will help with. A global history preserves every detail but becomes expensive and mixes together experience that may not belong together; compressing that history into one fixed representation limits the cost but can throw away valuable details. We introduce Routed Continual Learning (Routed CL), an architecture that decides how to partition and retain experience. Past trajectories are grouped into clusters, each of which maintains state using one memory system from a fixed library. Before each run, an LLM-based router either reuses an existing cluster or creates a new one, basing its decision on the problem statement, memory system descriptions, and cluster summaries. We also introduce Context Memory Adapter, which mediates between the memory system and the agentic loop. We evaluate the architecture on a heterogeneous stream that interleaves 301 instances from the six CL-Bench tasks with 97 banking instances from $τ^3$-Bench. Across four language models and five matched rollouts, Routed Continual Learning raises normalized reward over a single global in-context learning (ICL) history by 15-30% of the maximum attainable normalized reward, achieves higher mean normalized reward than ICL-only clustering, and reduces estimated API cost by 65-72% relative to Global ICL. These results support approaching continual learning as a routing problem that chooses both a learning mechanism and a state cluster rather than committing to one representation globally.

cs.LG · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.18002

Asynchronous Heavy-Tailed Optimization

Junfei Sun, Dixi Yao, Xuchen Gong, Tahseen Rabbani, Manzil Zaheer, Tian Li

原文摘要

Heavy-tailed stochastic gradient noise, commonly observed in transformer models, can destabilize the optimization process. Recent works mainly focus on developing and understanding approaches to address heavy-tailed noise in the centralized or distributed, synchronous setting, while asynchronous optimization under such noise remains underexplored, especially in the practical settings with local updates. In this work, we first investigate two asynchronous communication schemes (server- and client-centric) that handle stragglers under heavy-tailed gradient noise. We further propose and theoretically analyze algorithmic modifications based on delay-aware learning rate scheduling and delay compensation to enhance the performance of asynchronous algorithms. Our convergence guarantees achieve the optimal rate under heavy-tailed noise and improve delay tolerance compared with existing asynchronous approaches. Empirically, our approaches outperform prior synchronous and asynchronous methods in terms of accuracy/runtime trade-offs and are more robust to hyperparameters in both image and language tasks.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38793

Trustworthy Distributed Machine Learning in Cloud-Edge-IoT Systems: A Heterogeneity-Aware Survey of Security, Privacy, and Robustness

Long Dang, Ali Alfatemi, Kaiqi Xiong, Mohammed Aledhari, Abdellah Chehri, Shawqi Al-Maliki, Mohamed Rahouti

原文摘要

Distributed machine learning (DML), including conventional distributed training and federated learning (FL), enables collaborative model development across cloud-edge-IoT systems without fully centralizing raw data. However, distributing data, computation, updates, and orchestration increases the attack surface and introduces coupled challenges across privacy, robustness, reliability, fairness, and governance. This survey presents a security-centered, heterogeneity-aware roadmap for trustworthy DML, with FL treated as a prominent high-risk case. We first characterize the assets, adversaries, trust assumptions, and coordination patterns that define DML/FL security boundaries. We then analyze how statistical, system, and trust heterogeneity, including non-IID data, resource asymmetry, intermittent participation, and cross-silo/cross-device trust differences, affect convergence, fairness, attack detectability, and defense reliability. Next, we synthesize attack-defense interactions across poisoning, backdoors, Byzantine manipulation, privacy leakage, model extraction, network/orchestration attacks, Sybil behavior, and strategic participation. We further compare layered defenses, including robust aggregation, drift-aware optimization, differential privacy, secure aggregation, homomorphic encryption, secure multiparty computation, trusted execution environments, watermarking, provenance, authenticated communication, and monitoring. Finally, we discuss deployment, evaluation, governance, and open research guidelines, emphasizing reproducible, non-independent and identically distributed (non-IID) partitions, attack-aware benchmarks, privacy budgets, attack success rate, client-level disparity, latency, communication, memory, energy/carbon overhead, and auditable lifecycle artifacts.

cs.CR · cs.DC · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38788

Gold vs.~Translation: Are We Measuring Language, Knowledge, or Locality in Translated Benchmarks?

Klaudia-Doris Thellmann, Bernhard Stadler, Dan Saattrup Nielsen, Michael Färber, Jens Lehmann

原文摘要

Translated versions of English-origin benchmarks such as MMLU are widely used to evaluate large language models in non-English languages, yet it remains unclear whether they measure the same constructs as natively created benchmarks. We frame this as a proxy validity question and compare DeepL-translated MMLU proxies against six native benchmarks in seven pairings across five Nordic and Baltic languages, evaluating 29 models on each pairing. Beyond ranking agreement, we test incremental proxy validity: does the translated score add predictive value for native performance after controlling for model size and language proficiency? Proxy validity varies substantially across benchmark pairings. Applying the same robustness criteria to all seven pairings, we find four robust effects, two marginal effects, and one null result. The strongest evidence occurs for curriculum-overlap benchmarks such as Skolprov ($ΔR^2$=.128, 95% CI [.038,.253]), whereas translated MMLU provides no significant incremental value for Sweden-specific factual knowledge in SwedishFacts (p=.242). Because SwedishFacts is also the only open-ended benchmark, we cannot fully separate the effects of local content and response format. Overall, the results indicate a clear pattern: translated benchmarks provide a better proxy when their source content overlaps with the native evaluation target, while locally anchored knowledge is less reliably captured.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38784

Loss is Not Behavior: A Unified Output-Space Analysis of Gradient-Based Machine Unlearning

Xingjian Zhao, Mohammad Mohammadi Amiri, Malik Magdon-Ismail

原文摘要

Gradient-based machine unlearning methods typically ``unlearn'' by optimizing forget and retain losses, but similar losses do not necessarily imply similar output-space behavior. Prior work has shown that high forget loss alone does not certify that unlearning has produced retraining-like output behavior. We therefore ask: when a gradient-based unlearner differs from the model that would have been learned on only the retain data, what structure does the resulting output-space gap have? We derive closed-form expressions for this gap in linear regression, with an extension to nonlinear models via a generalized Gauss-Newton and local linearity approximations. Our analysis puts various gradient-based methods under a unified framework parametrized by geometry, reweighting, and projection. Two leverage matrices emerge that capture the forget-retain entanglement under the retrained model geometry: forget self-leverage and retain cross-leverage. We show both theoretically and empirically that these two leverage matrices drive the impact of the forget residual on the forget and retain outputs, and existing methods account for this geometry only partially. Our framework yields precomputable leverage diagnostics for auditing forget sets to identify what type of gradient-based unlearning is likely to be successful.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38776

A 211K Parameter Foundation Model: Genetic Prompting in Neural Cellular Automata

John Kalkhof, Niklas Ihm, Daniel Kirste, Anirban Mukhopadhyay

原文摘要

The scale of modern foundation models enables broad task generalization. In medical imaging, where segmentation demands vary widely across clinical contexts, such flexibility is invaluable. But current models, such as SAM trade adaptability for scale, locking their utility behind high-end infrastructure and leaving behind the low-resource environments most in need of diagnostic support. To bridge this gap, we introduce Foundational-NCA, a lightweight foundation model capable of adapting to a wide range of medical segmentation tasks without retraining. Built on Neural Cellular Automata (NCA), Foundational-NCA incorporates gradient-based learning with genetic optimization over a latent task space, using a compact task vector to guide predictions. This enables dynamic adaptation via a genetic prompt mechanism, allowing the model to generalize across tasks while keeping the parameter count magnitudes lower at just 211 thousand, compared to SAM-based models with 38.9 to 636 million parameters. We evaluate Foundational-NCA on 15 trained and 6 entirely unseen segmentation tasks from the TotalSegmentator dataset, achieving an average Dice score of 84.5% on known tasks and 60.4% on unseen ones. These results demonstrate that task generalization is possible in ultra-compact models, laying the groundwork for resource-efficient, deployable foundation models in clinical environments where infrastructure is limited. By reducing model size by over 180 times, Foundational-NCA takes a step toward a more equitable future for medical AI, one where powerful tools are within reach of every healthcare setting.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38775

Skillful and realistic precipitation forecasting with reinforced diffusion

Ozan Sener, Anand Avati, David Hafner, Jierui Lin, Laura Manduchi, Xiaoying Pang, Langwen Huang, Torsten Hoefler 等 10 位作者

原文摘要

Accurate precipitation forecasting remains elusive as physics-based models struggle to resolve mesoscale convection and machine learning often yields physically inconsistent, blurred results that consistently underestimate extreme events. We present FitzRoy, the first system that simultaneously achieves state-of-the-art predictive skill and physical realism over the continental United States. Through a reinforced diffusion framework, where a conditional discrete diffusion model is refined via reinforcement learning, FitzRoy effectively resolves the long-standing trade-off between pointwise accuracy and structural fidelity. Across lead times up to 24 hours, FitzRoy consistently matches or exceeds state-of-the-art models while preserving structural realism and capturing extreme events. Its low-latency inference further enables deployment in real-time operational settings. In case studies such as the 2025 Texas Hill Country floods and the 2026 Missouri floods, FitzRoy signals record-breaking accumulations that existing models largely missed. By bridging the gap between realism and skill, FitzRoy establishes a new frontier for high-fidelity precipitation forecasting.

cs.LG · physics.ao-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38774

Auditable Hierarchical Inference with Multimodal Evidence and Bayesian Active Inquiry

Yucheng Liu, Everett X. Wang

原文摘要

Most multimodal classifiers assume that all useful evidence is available upfront, whereas clinical inquiry is sequential. We present a synthetic evaluation framework separating objective multimodal inference from active inquiry. An objective model maps synthetic tongue, bilateral multipressure pulse, and acoustic observations to eight syndrome families. A provenance-bearing Knowledge Core and training-only answer model support Bayesian narrowing over 33 fine terms using 25 typed questions, while seven safety questions remain outside the diagnostic posterior. Weak shared symptom factors limit fine-term influence on objective phenotypes, and an objective-only probe tests leakage. In a preregistered 600-case synthetic evaluation, objective family accuracy was 87.0%. Cost-sensitive expected information gain (cost-EIG) raised family accuracy to 95.5% and exact fine-term accuracy to 42.5%, versus 92.7% and 33.0% for an unoptimized fixed-order baseline. Selective family accuracy reached 96.9% at 95.3% coverage. However, cost-EIG asked more questions on average than fixed order (9.795 versus 9.352). Missing-audio routing retained 94.0% family accuracy, and a workflow invariant enforced abstention when all objective modalities were absent. Permuting fine-term answer likelihoods reduced family accuracy to 78.7%. Five of six frozen checks passed, but the question-efficiency hypothesis failed. Comparisons are descriptive because only aggregate, not paired case-level, outputs were retained. These results establish a reproducible synthetic workflow, not clinical diagnostic or treatment validity.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.07114

Where to Spend Rollouts: Hit-Utility Optimal Rollout Allocation for Group-Based RLVR

Tao Wang, Shuo Li, Yan Sun, Dongsheng Ding, Edgar Dobriban

原文摘要

Reinforcement learning with verifiable rewards (RLVR) has emerged as a central paradigm for improving the reasoning capabilities of large language models. Group-based policy optimization methods, such as GRPO, typically allocate a fixed number of rollouts to every prompt. This uniform allocation can be inefficient: it over-allocates compute to prompts whose sampled groups are already saturated while under-exploring prompts for which additional samples may reveal useful correct trajectories. To address this limitation, we introduce hit utility, the posterior probability that at least one rollout in a proposed additional allocation for a prompt will be correct. Building on this notion, we propose Hit-Utility Optimal Rollout Allocation (HORA), a learning-free rollout allocation policy that maximizes total posterior hit utility within each allocation batch. HORA adaptively reallocates rollout budgets while leaving the downstream reward evaluation and group-based advantage estimator unchanged. Across two training sets, four mathematical reasoning benchmarks, and three model families at multiple scales, HORA preserves comparable Pass@1 and improves Pass@K over compute-matched GRPO, and it outperforms related allocation baselines at large K. It is also drop-in compatible with other group-based estimators such as RLOO. Ablation studies indicate that the uniform prior used by HORA is competitive with five prompt-conditioned learned-prior alternatives.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.30177

Search-Aware Reinforcement Learning for Multi-Component Query Understanding in Roblox Game Search

Nayoung Choi, Shengjian Chen, Xiaokai Wei, Wenzheng Zhang, Daiyao Yi, Rachit Pareek, Vincent Su, Michelle Gong 等 9 位作者

原文摘要

Query understanding (QU) in production search systems has typically relied on separate models for each subtask, such as search intent classification, attribute extraction, and query rewriting. Large language models (LLMs) now make it possible to consolidate these subtasks into a single model that emits a unified QU output. This consolidation, however, introduces a new optimization challenge. A single model serves multiple components, each with a distinct downstream role within the search pipeline, and the utility of each depends on how the underlying search engine acts on it rather than on agreement with static labels. We present a search-aware reinforcement learning (RL) framework for multi-component QU based on a distill-then-RL paradigm. Teacher-student supervised fine-tuning (SFT) first yields a schema-compliant small policy. The RL stage then starts from this policy, executes each QU plan on the live production search engine, and optimizes every component with a reward tailored to its operational role, rather than relying on a single reward tied to the final search outcome. On a large-scale user-generated game platform, this component-specific optimization raises NDCG@20 by 8.9 points over the SFT policy and by 3.5 points over a single end-to-end reward. The resulting small, low-latency student models also surpass their much larger teacher, and our final model is being incrementally deployed in production.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38773

Rennala NSGD: Asynchronous Stochastic Optimization Beyond Euclidean Geometry

Igor Sokolov, Alexander Tyurin, Peter Richtárik

原文摘要

The empirical success of matrix-aware optimizers, such as Muon (Jordan et al., 2024) and Shampoo (arXiv:1802.09568), highlights the potential of non-Euclidean geometry for deep learning, including large language model (LLM) training. Despite this progress, the theoretical understanding of stochastic optimization in general normed spaces remains limited, particularly in distributed settings. We analyze minibatch stochastic gradient descent (SGD) for smooth nonconvex optimization with respect to an arbitrary norm on a finite-dimensional space. Using the framework of $κ$-regular normed spaces (arXiv:0809.0813), we derive high-probability oracle complexity bounds under a light-tail condition stated directly in the dual norm induced by the update norm. The bounds make the dependence on geometry explicit through the regularity constant $κ$ of the dual space. In the Euclidean case, our bound recovers the standard minibatch SGD rate up to logarithmic factors. For some non-Euclidean geometries and noise models, it is sharper than bounds obtained by converting a Euclidean noise assumption, reducing a linear dimension dependence to a logarithmic one. Building on this framework, we introduce Rennala NSGD, a semi-asynchronous distributed algorithm, and establish wall-clock time complexity guarantees under fixed, heterogeneous worker computation times. In the Euclidean case ($κ=1$), our bound matches the parameter dependence of classical Rennala SGD up to logarithmic factors.

cs.LG · cs.DC · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.01202

Towards AI-Assisted Clinical Trial Matching: Practical Considerations, Multicenter Evaluation, and Real-World Deployment

Yin Fang, Qiao Jin, Shubo Tian, Lauren He, Maya Geer, Noor Naffakh, Ryan Huu-Tuan Nguyen, Zifeng Wang 等 27 位作者

原文摘要

Clinical trials are essential for evidence-based medicine and drug development, but many fail because of insufficient patient enrollment. Although there is growing interest in using AI to support patient recruitment, existing systems largely perform eligibility assessment alone and have rarely been evaluated in real-world workflows. Here we present TrialGPT 2.0, an AI-assisted clinical trial recommendation system improved for responsible real-world deployment. Rather than asking only whether a patient may qualify, the system assesses which trials warrant further consideration given the patient's current clinical needs and local workflow priorities, and provides structured, inspectable explanations for expert review. Importantly, we evaluated TrialGPT 2.0 retrospectively and prospectively across government research, patient-advocacy, academic medical center, and community-based radiation-oncology settings. In retrospective multicenter cohorts comprising 288 cases, TrialGPT 2.0 retrieved at least one clinician-recommended trial in its top 10 recommendations for approximately 91% of cases while reducing clinician screening time by 55.0%. In a six-month prospective evaluation embedded in an active precision oncology tumor board, TrialGPT 2.0 contributed additional trial opportunities missed by the routine workflow, increasing the number of patient cases with at least one final trial recommendation by 90.9%. To support scientific reproducibility, we also developed NIH-TrialBench, a clinician-authored benchmark comprising 126 diverse synthetic patient vignettes and matching scenarios from 11 NIH Institutes and Centers. Together, these findings support the value of AI to assist clinical trial matching by improving clinician efficiency and identifying frequently overlooked trial opportunities, ultimately helping to expand and accelerate accrual to cancer trials.

cs.CL · cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38755

Leaving, Staying, or Living There? Duration Commonsense Reasoning with Human-LLM Co-annotations

Chenyang Yu, Zhaomin Xiao, Yan Huang, Eduardo Blanco

原文摘要

Gardening in the backyard implies living there, while checking into an Airbnb more likely means staying for a few days. Such duration judgments are important for understanding human mobility, travel behavior, and social context. However, duration is rarely stated explicitly in social media posts and must instead be inferred from noisy textual, visual, and contextual cues. In this paper, we investigate whether vision-language models possess such duration commonsense. We create a new corpus of geotagged tweets co-annotated by humans and LLMs to serve as a testbed for this task. We find that state-of-the-art models struggle with duration inference, even when guided by multi-turn Chain-of-Thought prompting. Error analyses further reveal that models often fail to integrate critical contextual information, or they overly rely on prominent visual details while overlooking subtle hashtags and semantic nuances. These findings underscore the significant challenges remaining in context-aware multimodal understanding.

cs.AI · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38754

Alpha-TCM: A Nine-Layer Framework for TCM-Guided Multimodal Inference and Structured-Prior Auditing

Yucheng Liu, Everett X. Wang

原文摘要

Alpha-TCM makes two contributions under a central thesis: auditable systems should separate domain knowledge, case evidence, probabilistic inference, and downstream authority. First, it proposes a nine-layer TCM-oriented architecture covering semantic definitions, multimodal acquisition, quality control, provenance-bearing knowledge, probabilistic inference, longitudinal updating, constrained decisions, language interaction, and human governance. Each layer specifies its information contract, failure boundary, dependencies, and validation status. This is a system-design proposal, not a claim of complete clinical implementation. Second, a controlled synthetic prototype instantiates Layers 1-5 to audit the knowledge-evidence interface. Four conditional-Gaussian encoders process synthetic tongue images, pulse waveforms, inquiry fields, and text, while a frozen bridge predicts a five-dimensional synthetic outcome. A versioned contextual prior is compiled independently of the renderer. Fusion removes duplicated reference-prior information before adding context. Equal-information controls, prior regularization, graded contamination, and structural corruption test contextual benefits, Bayesian specificity, and conflict detection. Across ten paired seeds and four training sizes, contextual knowledge improved mean absolute error over marginal committee fusion at 600 and 1,200 cases, but not over equal-information neural controls. Fully incorrect context harmed performance at every size, while prior effects were inconsistent and conflict scores did not track case-level damage. The results support contextual structure in low-data synthetic settings, not a specifically Bayesian advantage. The prototype establishes no claims about TCM theory or clinical, diagnostic, therapeutic, causal, longitudinal, or transfer validity.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38753

Metropolized backward sampling for conditional sequential Monte Carlo

Adrien Corenflos

原文摘要

Particle Gibbs samplers with backward sampling are widely used for sampling the smoothing distribution of state-space models, but, with few particles, the new trajectory often coincides with the current one at many time steps. A known but rarely used remedy replaces the random selection of the final particle by a Metropolis--Hastings move which avoids the current particle. We show that, with backward sampling, this remedy only helps at the last time steps, because its effect on the update rates decays geometrically with the distance to the final time. We propose instead Metropolized backward sampling, which makes such a move at every step of the backward pass, forcibly switching trajectories whenever possible. Additionally, we introduce a coupled version which prevents proposing the current trajectory, maximizing the chances of an actual switch versus the current trajectory and performing perfect sampling when the state-space model has no observations, a feature not shared by backward sampling. We prove that, at every time step, both methods dominate backward sampling as they update the state more often and have smaller lag-one autocorrelations than it does. Our methods are drop-in replacements for backward sampling, and can be used to improve any particle Gibbs sampler.

stat.CO · eess.SP · math.PR · stat.ME · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.15493

LEADER: Lightweight End-to-End Attention-Gated Dual Encoder-Decoder Network for Robust Minutiae Extraction

Raffaele Cappelli, Matteo Ferrara

原文摘要

This paper introduces LEADER (Lightweight End-to-end Attention-gated Dual Encoder-decodeR), a neural network that maps raw fingerprint images to minutiae descriptors, including location, direction, and type. The proposed architecture integrates non-maximum suppression and angular decoding to enable end-to-end inference using only 0.9M parameters. It employs a novel ``Castle-Moat-Rampart'' ground-truth encoding and a dual encoder-decoder architecture, interconnected through an attention-gating mechanism. Experimental evaluations demonstrate state-of-the-art accuracy on plain fingerprints and robust cross-domain generalization to latent impressions across two benchmark datasets. Specifically, LEADER outperforms top-tier commercial systems, achieving F1-score gains of up to 34% and 39% over the closest competitor on NIST SD27 and SD302, respectively. Qualitative visual analysis suggests that the internal representations learned by the model align with established fingerprint domain concepts, such as segmentation masks, orientation fields, frequency maps, and skeletons. Inference requires only 15ms on GPU (average latency per image at batch size 32) and 322ms on CPU, outperforming leading commercial software in computational efficiency. The source code and pre-trained weights are publicly released to facilitate reproducibility.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.26065

FlowS: One-Step Motion Prediction via Local Transport Conditioning

Leandro Di Bella, Adrian Munteanu, Bruno Cornelis

原文摘要

Generative motion prediction must satisfy three simultaneous requirements for real-world autonomy: high accuracy, diverse multimodal futures, and strictly bounded latency. Diffusion models meet the first two but violate the third, requiring tens to hundreds of denoising steps. We identify a conditioning strategy that resolves this tension: \textit{single-step integration is accurate when the underlying transport problem is local}. A model that must both discover the correct behavioral mode and traverse a long displacement in one step accumulates large discretization errors; conditioning the base distribution to lie near plausible futures reduces the problem to short-range refinement, the regime where a single Euler step suffices. We instantiate this \emph{local transport conditioning} in FlowS, a conditional flow matching framework with two mechanisms. First, an online, scene-conditioned learned prior emits $K$ calibrated anchor trajectories per agent, each already near a plausible future, converting mode discovery into local correction. Second, a step-consistent displacement field enforces semigroup self-consistency, guaranteeing that a single step inherits multi-step accuracy. Crucially, anchoring this field at learned priors along straight-line paths yields a {stable, low-variance} training target, unlike prior self-consistency methods that suffer from {high-variance bootstrap} signals on curved diffusion paths. On the Waymo Open Motion Dataset, FlowS achieves state-of-the-art Soft mAP {(0.4804) and mAP (0.4703) with ensemble at 75\,FPS} with single-step inference, demonstrating that local transport conditioning makes one-step generative motion prediction practical for safety-critical autonomy. Code and pretrained models will be released upon acceptance.

cs.RO

查看论文
arXiv ↗PDF ↗