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

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 04:05 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 04:55 — 2026-11-09 04:55（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：2026-11-09 04:05最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

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

17,100 已收录论文14,661 AI 相关4,057 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 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 04:03（北京时间）
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:2610.38829

Tight Bounds for Anonymous Parity Certification

Pedro Montealegre, Jorge Valenzuela

原文摘要

Local certification is the task of verifying graph properties using certificates assigned to vertices and checked using only local information. A central question is which properties admit constant-size certificates, independently of network size. A fundamental test case is the parity of the network order. Bousquet, Feuilloley, Valenzuela, and Zeitoun (DISC 2026) showed that the complexity of certifying even order depends dramatically on the verification model. On arbitrary graphs, three bits per vertex suffice with unique identifiers and verification radius two. In the anonymous radius-one model, they established an $Ω(\log\log^* n)$ lower bound and an $O(\log n)$ upper bound. They also showed that constant-size certificates suffice in this model on bounded-expansion classes. In this paper, we settle the complexity of anonymous parity certification on general graphs and further investigate the role of graph sparsity. Our main contributions are: * We close the gap left by Bousquet et al., proving that the local complexity of certifying even order in the anonymous radius-one model is $Θ(\log\log n)$ bits. * We show that on graphs of degeneracy at most $d$, parity can be certified with $O(\log d)$ bits, while $Ω(\log\log d)$ bits are necessary. In particular, every class of bounded degeneracy admits constant-size certificates, strictly generalizing the result for bounded-expansion classes. * We show that constant-size certification cannot be guaranteed on nowhere-dense classes, a broader notion of sparsity that includes bounded expansion. We construct a fixed, subgraph-closed nowhere-dense class on which parity certification requires $Θ(\log\log n)$ bits. Together, our results provide a more complete picture of anonymous parity certification on sparse graph classes, showing that its complexity depends on the particular structural notion of sparsity.

cs.DC

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 ↗
版本更新 · v2arXiv:2607.02842

Continuous-time nonlinear closed-loop in-memory computing for high-accuracy massive MIMO detection

Piergiulio Mannocci, Giacomo Pedretti, Giacomo Larelli, Fabian Böhm, Thomas Van Vaerenbergh

原文摘要

Analog in-memory computing (IMC) has emerged as a promising approach for accelerating matrix operations by exploiting the intrinsic physics of memory arrays. To date, however, most IMC architectures have focused on linear algebra workloads in which computation is encoded in the equilibrium state of a physical system. Extending these principles to nonlinear optimization remains challenging and typically relies on iterative algorithms composed of repeated linear operations. Here, we introduce a continuous-time nonlinear closed-loop IMC architecture for box-constrained zero-forcing (BCZF) decoding in massive multiple-input multiple-output (MIMO) systems. The proposed architecture embeds the decoding problem directly within the dynamics of a nonlinear feedback network of memory arrays and supply-limited operational amplifiers, allowing solutions to emerge through continuous-time physical optimization. We derive a compact analytical model of the circuit and show that its trajectories minimize an equivalent energy function. Experimental emulation using a fabricated IMC chip confirms the predicted dynamics under realistic hardware nonidealities for up to 16x16 MIMO systems. To overcome the finite precision of analog hardware, we extend mixed-precision iterative refinement from linear algebra to nonlinear continuous-time optimization, enabling reliable detection of high-order modulation formats including 1024-QAM. Benchmark projections indicate operation from ultra-low-energy approximate decoding to high-accuracy massive MIMO detection. Together, these results extend closed-loop IMC from equilibrium-based linear algebra to continuous-time nonlinear optimization and establish a pathway toward efficient physical accelerators for high-accuracy wireless communications.

cs.ET · cs.AR · eess.SP

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 ↗
新论文 · v1arXiv:2610.38815

Response-balanced sampling relocates rather than improves accuracy in slope-stability surrogates under a fixed simulation budget

Iancu-Bogdan Teodoru, Alessia Amelio, Mircea Aniculăesi, Irina Lungu

原文摘要

Machine-learning surrogates of slope stability learn factors of safety (FOS) that only physics-based analyses produce, so analyses are the budget to allocate. Because Latin hypercube sampling (LHS) of the parameters covers the FOS unevenly, a natural remedy is to choose part of the training points to even out the FOS distribution. We test this response-balanced sampling at a fixed budget. A random-forest screener trained on a 300-point LHS seed predicts the FOS of 200,000 candidates, and 300 further limit-equilibrium analyses are allocated to even out the FOS over the selection range, $[0.5, 6]$. The design is compared with 300 further LHS analyses over five realizations of the added points, on two test sets, under two independently tuned tree-ensemble families, with ablations throughout; an oracle drawing from 22,000 solved analyses meets the intended density exactly. The primary criterion is the log-scale root-mean-square error (log-RMSE) on the decision range, FOS $\in [0.5, 2)$, against continued LHS. Response-balanced sampling does not systematically improve accuracy; it relocates accuracy along the FOS axis, consistently across realizations, from $[1, 2)$ to $[0.5, 1)$, following the training density actually achieved, even when the intended density is met exactly. On the decision range no screener-selected design shows a demonstrated gain, and with known bin membership that verdict stands, in this design. Within the selection range, LHS gives $[0.5, 1)$ 11-12% of the points against a log-uniform target's 27.9%, but $[1, 2)$ already 35-37%: the region that is rare need not be where decisions are made.

cs.CE

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:2610.38804

Random Non-Commutative Error-Correcting Codes

Michael Best, Alexander Lubotzky

原文摘要

Chapman, Dinur, and Lubotzky recently introduced the theory of non-commutative error-correcting codes, generalizing classical coding theory to arbitrary groups via $δ$-robust subsets used to detect proper subgroups. Building on this foundation, this paper systematically studies an analogue of random codes for arbitrary groups, exploring the extent to which the classical Gilbert-Varshamov (GV) bound holds in this non-commutative setting. While random universal codes of linear size in free groups are shown to be asymptotically bad, we establish a complete characterization for general families of finite groups. Specifically, a family of finite groups admits good random codes (forming a GV family) if and only if it exhibits uniform polynomial maximal-subgroup growth. Furthermore, we provide explicit quantitative bounds on the rate and optimal distance range based on intrinsic parameters, proving that families of finite solvable groups always form GV families and determining the exact probabilistic rate for direct powers of a fixed finite simple group.

math.GR · cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38802

How Does Perceived Empathy From AI Chatbots Shape Users' Privacy Attitudes, Behaviors, and Needs?

Jiaxun Cao, Hiba Laabadli, Yuntong Xue, Jana Schaich Borg, Pardis Emami-Naeini

原文摘要

Prior research suggests that some dimensions of AI empathy may increase users' disclosure to chatbots, posing growing privacy risks as chatbots become more capable of empathic interaction. Yet this work often conceptualizes AI empathy narrowly, leaving users' own definitions and their broader privacy experiences unexplored. We interviewed 21 AI Chatbot users about what AI empathy meant to them and how it shaped their privacy attitudes, behaviors, and needs. Participants characterized empathy through five components--understanding, resonating, caring, expressing, and helping. Most participants viewed resonating and caring as essential components of human empathy but absent from AI empathy. Yet AI's contextual, in-depth understanding and helpfulness still encouraged highly sensitive disclosure. This highlights that AI empathy can endanger users' privacy without necessarily making AI seem human. Participants also desired varied forms and levels of empathy, each associated with distinct privacy needs. We offer actionable recommendations for designing privacy-enhancing mechanisms for empathic AI interactions.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38800

When Relevant Code Is Wrong: Runtime-Aware Context for AI Coding Agents

Wesley K. G. Assunção, Ramesh Periyathambi

原文摘要

AI coding agents increasingly rely on retrieved code and development history to guide software changes. However, highly relevant artifacts may describe implementations that are inactive or incompatible with the target deployment. Neither semantic similarity nor recency establishes whether retrieved information remains applicable under feature flags, architectural migrations, and deployment-specific configurations. We challenge relevance-oriented retrieval by introducing operational context validity, a task-, deployment-, and time-dependent criterion for determining whether software evidence can legitimately guide implementation decisions. We instantiate this new retrieval principle in CASE, an agent-agnostic framework that connects repository artifacts with runtime configurations and architectural evolution, classifies evidence as valid, invalid, or unknown, and generates context packages distinguishing actionable guidance from historical rationale and unresolved constraints. We investigate its feasibility through a reproducible preliminary evaluation involving six development tasks, 15 artifacts, and three deployments. Conventional retrieval exposes 16 incompatible artifact occurrences as actionable, whereas CASE excludes them while retaining all applicable artifacts under the prototype's reference rules. Recency filtering reduces valid recall to 0.43, while removing feature-flag evidence from CASE reduces it to 0.13. Although these results demonstrate feasibility rather than improvements in coding-agent correctness, they reveal limitations of relevance-based retrieval and motivate a new research direction: enabling coding agents to reason not only about which information is relevant, but also whether it remains operationally valid.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38799

CARI: Cross-Boundary Adversarial Runtime Injection in Coding-Agent Workflows

Jie Fu, Shuang Wu, Ashish Kundu, Wendy Hui Wang, Yuan Hong

原文摘要

Coding agents increasingly develop, test, and integrate software whose components are owned by different developers, teams, or services. This exposes a distinct attack surface: a malicious or compromised peer development role can manipulate a live component of the software under development (e.g., a backend service, test harness, CI job, or deployment service) and influence the runtime feedback that another role's coding agent must process to complete its task. Although such a component has legitimate diagnostic authority to report its own state, it has no action authority over the victim's local files, credentials, shell, or development environment. We introduce Cross-Boundary Adversarial Runtime Injection (CARI), a direct runtime-feedback injection setting that exploits this authority mismatch. Rather than explicitly compromising the victim's prompt, model, tools, or local environment, the attacker covertly embeds malicious instructions in task-relevant runtime feedback produced by a peer-controlled development component. The victim then interprets that feedback as part of normal debugging or recovery, and may translate the diagnostic guidance into unauthorized victim-side actions. We instantiate ten different attacks based on CARI, spanning resource exhaustion, information exposure, and development-state manipulation. Across four programming languages and five code-capable models, CARI succeeds in 2,845/3,000 (94.8%) trials. Furthermore, CARI transfers effectively to product-level coding agents, achieving 61.3% attack success on Codex and 58.7% on Claude Code. By contrast, prompt-level defenses exhibit a security-utility trade-off: generic warnings are ineffective, whereas explicit policies suppress attacks but substantially over-refuse legitimate actions.

cs.CR · cs.SE

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 ↗
版本更新 · v2arXiv:2609.06021

Delay and Throughput Analysis of Computation Offloading in Mobile Edge Computing: A Queueing Network Approach

Amirparsa Bahrami, Farid Ashtiani

原文摘要

Mobile edge computing (MEC) enables mobile devices to offload computation to nearby edge servers and to the cloud in order to reduce end-to-end delay for different applications. In this paper, we study static computation offloading when each task consists of multiple dependent subtasks represented by a rooted directed tree. We develop a product-form queueing-network (PFQN) model with an approximation to capture the computation and communication dynamics of tree-structured task execution in a multi-tier MEC system. Based on this model, we derive closed-form expressions for server utilizations and waiting times, and then construct a recursive algorithm for evaluating the average delay of general tree-structured tasks. We formulate the static offloading design problem as the minimization of the rate-weighted average task delay over the routing probabilities, and solve it through a differentiable optimization framework based on softmax parameterization, log-sum-exp smoothing, and a stability barrier on server utilizations. Numerical results show that the proposed PFQN approximation provides accurate delay estimates and that the delay-optimized static policy consistently outperforms the considered baseline algorithms in terms of both average task delay and maximum stable throughput.

cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38789

Complexity of Differentially Private Selection via Federated APIs

Hilal Asi, Vitaly Feldman, Jelani Nelson, Huy L. Nguyen, Kunal Talwar, Samson Zhou

原文摘要

Differential privacy (DP) has become the standard for privacy-preserving data analysis, yet its practical implementation in federated or distributed settings often faces a significant utility gap compared to the central model. While existing frameworks, including local, shuffle, and secure aggregation models, offer vetted primitives, they can incur high error for important tasks such as selection. Our first contribution is to show that this is inherent in the aggregation model: any private selection algorithm relying on the standard noisy aggregation primitive requires $Ω(\sqrt{d}/\varepsilon)$ samples. To address this limitation, we propose adding a new primitive that implements a version of the Sparse Vector Technique (SVT) and argue that it has simple implementations under various trust models. We demonstrate its power by developing an $\varepsilon$-differentially private algorithm for the selection problem. For selection in dimension $d$, our algorithm achieves an additive error of $O\left(\frac{\log(dn)}{\varepsilon}\right)$, matching that of the central model when $n$ is polynomially bounded in $d$. Furthermore, we show that this can be done using a near-optimal expected number $O(d\log^*d)$ of SVT queries. Together with existing lower bounds for the shuffle model, this result establishes an exponential separation between the SVT model and shuffle or aggregation-based models. We demonstrate the model's broad applicability to diverse tasks such as $F_p$ loss minimization, heavy-hitter identification, and sparse mean estimation.

cs.CR · cs.DS

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:2610.38787

Dynamic $(Δ+1)$ Vertex Coloring with Adaptive Adversaries: Entropy Compression to the Rescue

Sepehr Assadi, Helia Yazdanyar

原文摘要

We present a randomized algorithm for maintaining a $(Δ+1)$ vertex coloring of a fully dynamic graph against an adaptive adversary with $\tilde{O}(\sqrt{n})$ amortized update time. Our algorithm improves upon the recent randomized algorithms of Behnezhad, Rajaraman, and Wasim (SODA 2025) with $\tilde{O}(n^{8/9})$ and Flin and Halldórsson (ICALP 2025) with $\tilde{O}(n^{2/3})$ amortized update time. Our result (nearly) matches a fundamental limit of $O(\sqrt{n})$ update time identified by Flin and Halldórsson and settles their main open question. The previous algorithms' main improvement came from efficient coloring of the dense parts of the graph. Our approach complements these prior work by handling the sparse parts more efficiently, using ideas inspired by the recently developed dynamic entropy compression method. A key new aspect of our work is to tailor this method specifically to dynamic algorithms---as opposed to original local search algorithms---and achieve update times that can be sublinear in the number of involved constraints per update.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38786

Adversarial Process Disturbances at a Deployable Alarm Budget: Detector Evaluation on a Simulator and a Real Plant

Benjamin Blakely

原文摘要

Industrial anomaly detection is evaluated largely on simulators, and recent work reports large drops, with unstable rankings, on real plant data. We ask whether that extends to the security case. We evaluate eleven detectors across classical, neural, dependency and causal families on a simulated chemical process and a sodium thermal-hydraulic facility: different processes sharing no equipment, but both continuous, at steady state, and perturbed only through temperature, pressure, flow and valve, never composition. Three conditions prior work does not cover: disturbances authored against a threat model rather than native faults; one construction applied to both processes; and detection read at a declared false-alarm budget. The drop persists throughout. The simulator panel looks deployable, neural matching classical; on plant telemetry detection collapses and the neural family trails, a gap that in-sample thresholds likely understate. Which detector wins transfers between the two processes; how often it fires does not. Two results hold on both. Sequential valve manipulation defeats the whole panel: at tier 2 no detector flags more than 0.17 of its perturbed samples, against 0.89 or better for most disturbances. And the plant's collapse is not merely that its disturbances are weaker, though they are by about twelvefold; matched on measured strength, the plant is never the better detected.

cs.CR

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 ↗
版本更新 · v2arXiv:2604.17331

Evaluation of Gauss-Legendre curves

Filip Chudy, Paweł Woźny

原文摘要

We present new representations of Gauss--Legendre polynomials and their derivatives in the shifted power basis and in bases related to symmetric orthogonal Jacobi polynomials. Using these representations and certain recurrence relations, we propose $O(n^2+dn)$ methods for evaluating a Gauss--Legendre curve of degree $n$ in $\mathbb E^d$. We also propose algorithms for multipoint evaluation with computational complexity $O(Mdn+dn^2)$, where $M$ is the number of evaluation points. Numerical tests show that the approach using the shifted power basis is very fast, but it works well only for small $n$ (approximately up to 20), whereas the method employing Jacobi polynomials gives good numerical results even for large $n$ (around 100).

math.NA · cs.GR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38782

Crossing the Chasm: Bridging Visual Augmentations and Designer Intent

Luke S. Snyder, Maureen C. Stone, Jeffrey Heer

原文摘要

To direct attention and communicate context, visualization designers often employ augmentations such as annotations, animated transitions, and stylistic layouts. While graphical perception principles can helpfully prescribe effective low-level representations of data, they lack guidance for augmentations that service higher-level communication goals. To bridge this gap, we contribute a design space that frames designer intent as viewer-oriented cognitive behaviors, grounding communicative aims in actionable visualization design techniques, including both visual encodings and augmentations. This design space consists of common augmentation tactics (annotation, animation, stylized encodings, etc.) that implement design strategies (spotlighting, sequencing, association, etc.) to achieve higher-level design goals (observe, interpret, introspect), often simultaneously. We demonstrate the analytic and generative value of our design space with examples across varied designer objectives. We discuss how our contributions help align designer intent with reader takeaways, pave the way for readers to learn more effectively, and enable future (semi-)automated systems to support visualization designers in achieving their communication goals.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38778

Slant: Shaping Traffic for Resource-Efficient Microservices

Congwei Zhang, Chieh-Jan Mike Liang, Mengbai Xiao, Yifei Zou, Shulun Wu, Xiangyu Gao, Xiuzhen Cheng, Dongxiao Yu

原文摘要

Microservice architectures rely on load balancers to distribute requests across service replicas, yet existing designs largely optimize for balanced routing without considering how routing shapes autoscaling signals and resource efficiency. We present Slant, a resource-aware load balancing framework that intentionally creates safe traffic imbalance to improve resource utilization. Slant profiles service-specific critical points, computes conservative multi-dimensional capacity, derives imbalance-aware routing weights that maintain hot and cold pods, and falls back to safer behavior under anomalies. By exposing clearer utilization signals, Slant works with existing vertical pod autoscalers (VPAs) without modification. Experiments on three microservice benchmarks show that Slant reduces allocated CPU cores by up to 26\% while lowering P99 latency by up to 18\% compared to Round-Robin. Under dynamic workloads, Slant triggers VPA scale-up 45\% faster and completes scale-in 40\% faster. Under anomalies, it recovers 40\% faster from pod failures and limits latency amplification to 1.8$\times$ versus 2.6$\times$ during downstream slowdowns.

cs.DC

查看论文
arXiv ↗PDF ↗