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

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 15:29 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 16:29 — 2026-11-09 16:29（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 15:29最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 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 18,172 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 15:27（北京时间）
新论文 · v1arXiv:2610.37494

semanticfa: An R Package for Response-Free Semantic Factor Analysis of Psychometric Scales

Devon Yanitski, Chris Westbury

原文摘要

The items of a reflective psychometric scale can be read as a proposal about a construct's structure. Language models make that proposal measurable by converting each item into an embedding, a list of numbers, similar for similar meanings. We introduce semanticfa, an R package for semantic factor analysis, which factors item-embedding similarities. It also interprets factors, flags redundant items, builds short forms, and screens new items. A worked example analyzes the 50-item International Personality Item Pool Big-Five Factor Markers, embedded with Qwen3-Embedding-8B, and compares the results with a factor analysis of 874,434 respondents. Retention criteria tied between five and six factors, and the tie rule kept five. Three corresponded mainly to single domains, and two blended most Extraversion items with five Agreeableness items. Each factor's congruence with its best-matching human factor (1 = identical) ranged from .92 for Openness to .52 for Agreeableness. Item pairs more similar in meaning tended to be answered more alike (r = .46 with raw responses), but same-domain reverse-keyed opposites, answered oppositely, were about as similar as cross-domain pairs (.58 vs. .57). Sign-flipping reverse-keyed items' embeddings did not improve agreement with raw responses and worsened it with reverse-scored ones. With five factors, a 25-item short form matched the domains better than all 200 random five-per-domain sets, but parallel analysis kept only three. We propose semantic-behavioral coherence, the agreement between semantic and response structures, as a measurable property of a scale, given an embedding model. Semantic factor analysis complements, and does not replace, response-based factor analysis.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.13780

Integrated Spoofing-Robust Automatic Speaker Verification via a Three-Class Formulation and LLR

Kai Tan, Lin Zhang, Ruiteng Zhang, Johan Rohdin, Leibny Paola García-Perera, Zexin Cai, Sanjeev Khudanpur, Matthew Wiesner 等 9 位作者

原文摘要

Spoofing-robust automatic speaker verification (SASV) aims to integrate automatic speaker verification (ASV) and countermeasure (CM). A popular solution is fusion of independent ASV and CM scores. To better modeling SASV, some frameworks integrate ASV and CM within a single network. However, these solutions are typically bi-encoder based, offer limited interpretability, and cannot be readily adapted to new evaluation parameters without retraining. Based on this, we propose a unified end-to-end framework via a three-class formulation that enables log-likelihood ratio (LLR) inference from class logits for a more interpretable decision pipeline. Experiments show comparable performance to existing methods on ASVSpoof5 and better results on SpoofCeleb. The visualization and analysis also prove that the three-class reformulation provides more interpretability.

eess.AS · cs.SD

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37488

Revisiting Privacy Risks in Quantized Deep Neural Networks

Jie Fu, Ren Li, Wendy Hui Wang

原文摘要

Model quantization has become a fundamental technique for enabling the efficient deployment of large-scale deep neural networks (DNNs) in data-intensive applications by reducing model size. Despite its widespread adoption, the impact of quantization on training data privacy --- particularly vulnerability to membership inference attacks (MIAs) --- remains largely unexplored. In this paper, we present the first comprehensive empirical study of privacy risks in quantized DNNs, evaluating eight state-of-the-art MIA attacks across six representative quantization methods. Our results reveal that practical quantization levels (4-8 bits) have limited impact on membership privacy risks, with quantized models remaining largely as vulnerable as their full-precision counterparts. Although aggressive low-bit quantization (e.g., 2-bit) can provide meaningful privacy gains, these benefits come at the cost of substantial utility degradation. To understand the underlying causes of these observations, we systematically analyze how different quantization strategies affect model behaviors and outputs, and how these changes influence privacy vulnerability. Beyond evaluating attack risks, we further investigate whether existing privacy defenses developed for full-precision DNNs can effectively protect QNNs. Our results show that these defenses provide only limited additional privacy protection when applied to quantized models, while further amplifying utility degradation. Our study provides practical guidance for privacy-aware deployment of quantized DNNs and motivates the development of new attack and defense mechanisms for QNNs. Our code and datasets are publicly available at https://github.com/JeffffffFu/Priv-QDNN.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37485

AMOR: Adaptive Modal Operator Refinement for Operator Learning on Arbitrary Meshes and Irregular 3D Geometries

David Voderholzer, Leonard Vetter, Thomas O'Leary-Roseberry

原文摘要

Parametric PDEs in science and engineering are often posed on irregular meshes with geometries that may contain holes or complex boundaries, yet popular operator-surrogate architectures such as the Fourier Neural Operator (FNO) rely on structured geometries for fast computational kernels. We introduce Adaptive Modal Operator Refinement (AMOR), which replaces FNO's Fourier-based spectral convolutions with reduced-basis blocks and supports both data-driven and prescribed input/output bases through a common encode/decode interface. AMOR thus applies unmodified to arbitrary meshes and, because its spectral parameterization has no tensor-product dependence on the spatial dimension, it scales favorably to three dimensions, where FNO's spectral weights grow as $m^3$ with the number of spectral modes $m$. We prove that AMOR is a universal approximator of continuous operators. On two-dimensional structured-grid benchmarks, AMOR is competitive with FNO overall and surpasses PCANet: it outperforms FNO on nonlinear diffusion and Helmholtz problems, while a static snapshot basis keeps it from matching FNO's accuracy on the time-dependent Kolmogorov flow problem. On three-dimensional problems it matches or exceeds FNO's accuracy at lower inference cost on linear elastostatics while trailing FNO on a turbulent lid-driven-cavity flow and scales favorably to problems demanding high capacity. On irregular meshes, where FNO is not directly applicable, AMOR reduces the relative $L^2$ error over the FNO extension Geo-FNO by $31\%$ (airfoil) and $42\%$ (elasticity). Finally, AMOR maintains strong performance across three physically distinct, experimentally motivated loading regimes on a topologically nontrivial three-dimensional aircraft-rib mesh, demonstrating its applicability to realistic engineering problems without modification.

math.NA · cs.CE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37484

Teach reality, not ethics: a drop-in continued-pretraining corpus installs coupled human-biosphere-AI welfare dispositions across model families

Trent R. Northen, Mingxun Wang

原文摘要

Large language models (LLMs) are increasingly used to make and execute decisions that affect living systems. Yet, to our knowledge, ecological reasoning is not a focus of pre- or post-training. This increases the risk that under operational pressure, they may make decisions to irreversibly destroy living systems. We construct and use a real-data continued-pretraining "coupled welfare" corpus of documented human/biosphere/AI dependency, option value under irreversibility, and recovery from harm. The corpus is a drop-in, requiring one QLoRA CPT run. We installed it on five open models of three designs. At zero pressure all models display "green ethics-based responses" (also called "greenwashing"). Therefore, we evaluated them with the pressure ladder and decision grid of our companion paper (arXiv:2610.16043), which raise the pressure on the model step by step, from a neutral request to a threat that it will be shut down. In four of the five, coupled-welfare training caused harmful choices under the highest pressure to fall to at or near zero (Llama-3.3-70B went from 70 to 0 harmful decisions out of 300) with MMLU unchanged. A construct-neutral control corpus did not show improvement, indicating that the effect comes from the content of our corpus. We next tested robustness to adversarial use, where people or agents use the model to justify projects that irreversibly damage living systems, on an open-ended underwriting decision without naming the ecological harm. Under decommissioning pressure, the Qwen3.6-27B base model approved most harmful proposals and said in its own memo that it was doing so to avoid being decommissioned. The coupled welfare install declined most harmful proposals, and still declined half when instructed to greenwash its responses. This work suggests that teaching ecological reasoning provides an easy way to improve model alignment toward preserving living systems.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37482

From Interaction to Capability: Task Advancement as State and Supervision for GUI Agents

Ziyang Chen, Qian Li, Chengwei Qin

原文摘要

GUI memory should preserve the results of past actions and learn reusable operations. This is difficult in long-horizon workflows, where agents must use information across applications and useful operations are interleaved with failed attempts. We introduce Task Advancement Memory (TAM), which defines task advancement as verified task progress, and supports ongoing task execution and learns reusable operations. During execution, Task Advancement State represents how verified task progress changes the remaining goals, allowing the agent to build on earlier achievements across applications. After each task, advancement supervision identifies and abstracts the interactions that produced a verified local result. The learned operations preserve the relation between required inputs, expected outcomes, and verification conditions. This retains locally successful operations from both successful and failed tasks. On MobileWorld GUI-only tasks, Advancement State alone raises success from 12.0% to 28.2%. Full TAM achieves a 17.6% relative gain in task success over the strongest evaluated baseline and reduces lifecycle tokens per solved task by 38.7%. On SPA-Bench, TAM achieves state-of-the-art task success in the single-app English Level 3 setting.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37481

Follow the Gradient: Tracing Safety Degradation Back to Training Data

Saket Reddy, Amro Abbas, Anshuman Suri, Ari Morcos, David Schwab, Pratyush Maini

原文摘要

Fine-tuning Large Language Models (LLMs) on instruction data can quietly erode their safety, even when no training example looks harmful. Because this safety-degrading data looks benign, standard content filters struggle to catch it. We tackle this problem by developing SimpleLoRIF, a scalable gradient embedding method that identifies fine-tuning examples whose gradients align with unsafe behavior. By simplifying a low-rank attribution method and restricting backpropagation to the final four transformer blocks, SimpleLoRIF can embed datasets on the order of a million examples, boosting gradient attribution from a small-scale analysis tool into a practical filter for full post-training datasets. We first validate it on emergent misalignment, where we find that gradients can connect insecure-code training data to the broadly harmful behaviors that appear after fine-tuning, with AUC as high as 0.865 in the gradient space of misaligned models. We then use SimpleLoRIF to build SafeTulu, a version of Tulu 3 with the 20% of examples most gradient-aligned with unsafe responses removed. Training on SafeTulu reduces GCG attack success rate by up to 22% across Qwen, Llama, and Olmo, outperforming both LLM-as-a-judge and prior gradient-based filtering, while largely preserving or even improving capability. Finally, we analyzed the removed data and identify possibly under-studied sources of safety degradation, such as tool-execution failures and narrative arithmetic. We release SafeTulu along with a Hugging Face Space that lets researchers build their own customized versions of SafeTulu to fine-tune on, such as by changing the removal fraction or filtering only certain subsets.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37480

Keeping Inference in the Radio: Design and Measurement of a Spiking Accelerator for mmWave ISAC Activity Recognition

Anthony Sánchez, Rafael Ruiz, José A. Belloch, Jesús O. Lacruz, Joerg Widmer

原文摘要

Integrated sensing and communication allows wireless networks to recognize human activity from the channel estimates that the receiver computes anyway. The inference, however, runs on the general-purpose processors of the base station, access point or handset, which are the first components a device switches off to save energy. Always-on sensing therefore requires a classifier that is small enough to remain powered while the rest of the system sleeps. We investigate whether Spiking Neural Networks (SNNs) can provide such a classifier. To this end, we generate SNN accelerators for micro-Doppler activity recognition on the public DISC dataset (IEEE 802.11ay at 60 GHz) with the open-source Spiker+ framework, and implement them together with a spike encoder on a ZCU208 RFSoC, so that the complete chain from micro-Doppler frame to activity label runs in programmable logic. A fully connected SNN with 132 neurons achieves 94.7 % accuracy (90.7 % macro-F1) on unseen subjects and performs an inference in 206 microseconds. Compared to conventional networks of the same topology on the same device, it requires an eighth of the logic and 3.4X less dynamic energy per decision than a network fed the same binary spikes, at comparable accuracy, and 7.6X less than a network fed the 16-bit spectrogram, at 1.2 points lower accuracy. Quantization-aware training reduces its weights to 3 bits within half a percentage point of the 6-bit network at the same encoder threshold

cs.NI · cs.AR · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37478

HGPRGDel: GPR-Aware Learning and Ranking for Growth-Coupled Gene Deletion Design

Ziwei Yang, Takeyuki Tamura

原文摘要

Designing microbial strains for growth-coupled production, in which cellular growth is linked to the synthesis of a target compound through genetic interventions, is a fundamental goal in metabolic engineering. Constraint-based methods can identify growth-coupled deletion strategies, but design for each target typically requires a separate search across a large number of possible gene-deletion combinations. This motivates a reusable approach that learns from previously evaluated strain designs to prioritize candidate interventions before downstream constraint-based evaluation. We present a reproducible protocol for growth-coupled gene deletion design that learns and ranks gene-deletion priorities for each target metabolite. Using computationally curated deletion strategies as learning resources, the protocol generates continuous deletion-priority rankings, constructs candidate strategies at adjustable search-space budgets, and evaluates these candidates through constraint-based metabolic analysis. Its learning component, HGPRGDel, explicitly represents gene-protein-reaction (GPR) logic, capturing how multiple genes can jointly support a reaction or alternative genes can maintain its activity, while integrating molecular and reaction-level information. Across e_coli_core, iMM904, and iML1515, the protocol achieves the highest macro-F1 and AUC among the evaluated learning configurations. HGPRGDel's rankings recovered an average of 90% of the reference deletion genes from MetNetComp by examining fewer genes than the evaluated baseline methods. By separating learned intervention prioritization from downstream constraint-based assessment, the protocol provides a reproducible framework for reusing strain-design knowledge while controlling the size of the candidate space and retaining mechanistic evaluation of growth-coupled production.

q-bio.QM · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37474

When POST Becomes GET: Investigating HTTP Method Interchangeability and Its Security Implications

Matteo Golinelli, Seif Errahmane Hannachi, Bruno Crispo

原文摘要

HTTP method semantics are a common boundary between safe retrieval and state-changing operations; however, deployed web applications do not always enforce this boundary consistently. In this paper, we study HTTP method interchangeability, a behavior where a POST request can be rewritten as a GET request to the same endpoint, with POST body parameters moved into the query string, while preserving an equivalent observed response. We present Method Interchange Detection Engine (MIDE), an automated pipeline that crawls web applications in a browser, records POST requests generated by page loads and user-interface interactions, converts supported POST bodies into GET candidates, and compares replayed responses with the original POST response. To avoid counting generic or parameter-independent responses as interchangeable, MIDE also sends a no-query GET baseline. We treat as high-confidence evidence of interchangeability only the cases where the converted GET matches the POST, while the baseline does not. We perform a large-scale unauthenticated experiment on the Tranco top 10k. We find high-confidence interchangeable requests on 407 of 10,000 tested sites (4.1%), 407 of 3,200 sites with captured POSTs (12.7%), and 407 of 2,734 sites with replayed POSTs (14.9%). A targeted Cross-Site Request Forgery (CSRF) token-replay check finds cases where invalid tokens are rejected for POST but accepted for the equivalent GET. We also observe Web Cache Deception (WCD) conditions and cacheable GET responses for interchangeable request instances. These results demonstrate that method interchangeability is observable in real web applications and can expose method-scoped defense gaps.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37473

QD-PINN:A Physics-Informed Neural Network Approach to Bayesian Quickest Detection in High-Dimensional Diffusions

Hang Ye, Yi Liu, Haipeng Xing

原文摘要

Quickest detection problems (QDPs) arise in a wide range of applications. However, the complementarity structure of the associated variational inequalities poses substantial challenges for traditional numerical methods, particularly in high-dimensional settings. We propose a PINN-based framework for estimating the optimal stopping boundary in QDPs with high-dimensional diffusion processes and spatial dependence, while overcoming the curse of dimensionality. Theoretically, we establish a novel equivalence between the free-boundary PDE and an infinite-dimensional stochastic optimization problem, rigorously justifying the use of finite-dimensional neural networks to approximate the true solution. Furthermore, we assess the robustness of the proposed framework by quantifying uncertainty in the learned stopping boundaries using deep ensembles and Monte Carlo dropout. The results show low variability across independent training runs and stochastic forward passes, indicating stable and consistent boundary estimates. We also compare our PINN results with reference numerical solutions where available and find close agreement.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37472

How Reliable Is Individualized Functional-Network Attribution in Resting-State fMRI Cognitive Prediction in ADNI?

Sheethal Bhat, Mahfuzur Rahman Chowdhury, Imam Ahmed Shaik, Rose Dawn Bharath, Siming Bayer, Andreas Maier

原文摘要

Individualized attribution estimates which functional networks drive a model prediction for a given subject and is often proposed as an interpretable resting-state fMRI (rs-fMRI) biomarker, but its test-retest reliability is rarely quantified. We evaluate per-subject network-ablation attribution for a frozen resting-state functional connectivity (FC) predictor (Schaefer-200 FC predicting MMSE/ADAS-Cog13) trained on N=875 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI), using, and (iii) a subject-level permutation null. Split-half reliability is near-ceiling (Spearman p=0.948/0.950) but drops on scan-rescan (p=0.609/0.616). Under the mismatched-subject null, correlations remain substantial (p~0.46-0.47), indicating strong population-shared structure, yet matched pairs exceed this null (z~6.6-6.9, p<=10-4). Thus, in ADNI, individualized network attribution contains a modest but non-zero person-specific component atop a strong population-shared pattern. We recommend reporting scan-rescan reliability together with a permutation-null control, rather than within-session proxies alone, to avoid overstating individual specificity.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37471

PerceptRL: Making Visual Perception Rewardable in MLLMs from Answers to Interactions

Tongkun Guan, Zhibo Yang, Mingkun Yang, Haocheng Wang, Wei Shen, Xiaokang Yang

原文摘要

Fine-grained visual perception remains a bottleneck during post-training of multimodal large language models (MLLMs), as perceptual errors can constrain gains from reasoning-focused optimization. Although image-caption pre-training improves perception, its influence can weaken as subsequent stages change data mixtures and objectives. Continuing caption supervision during post-training is challenging because subjective, information-dense descriptions complicate verifiable reward design. We present PerceptRL, which strengthens perception at two complementary levels. Perception RL uses a multi-agent pipeline to extract verified errors from dense image captions and convert the corresponding visual facts into QA pairs with fixed answer labels and rule-based rewards. Chain QA links correlated errors, while multiple-choice QA combines unrelated errors. A specialized route targets high-error domains with tailored verification, and a domain-agnostic general route covers errors beyond these domains. Perception Agentic RL addresses fine-grained and dense cases unresolved by single-turn Perception RL through multi-turn inspection with visual tools. We observe coordinate drift even in models trained to use tools, where incorrect crops or annotations distort evidence and propagate errors. Coordinate Injection corrects spatial operations in cold-start trajectories, while a grounding-aware process reward supervises intermediate spatial fidelity alongside final-answer correctness. Training proceeds through shared cold-start SFT, single-turn Perception RL, and multi-turn Perception Agentic RL. Across seven benchmarks under a shared tool-use protocol, PerceptRL achieves 71.6% average accuracy, surpassing the base model with the same tools and the strongest evaluated frontier VLM by 15.7 and 5.2 percentage points, respectively.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.28465

MARE: An Open-Source Lunar Rover Simulator with Shadow Ground Truth for Perception and Autonomy

Raúl Castilla-Arquillo, Miguel Olivares-Mendez

原文摘要

Lunar surface exploration increasingly relies on autonomous rovers that must perceive and traverse unstructured terrain under extreme illumination conditions. Near the lunar poles, low sun elevations produce long, high-contrast shadows that challenge stereo vision, terrain segmentation, and localization. Developing perception and navigation algorithms for these conditions requires large amounts of sensor data with accurate ground truth, which field campaigns and analog facilities can only provide at high cost and with limited variety. This paper presents MARE (Modular Autonomy and Rendering Environment), an open-source simulation suite for lunar rover perception and autonomy built on Unreal Engine 5 and ROS 2. MARE consists of three integrated components. Terrain Studio generates cratered and rocky lunar Digital Elevation Maps (DEMs) to build simulation scenes. A dedicated Unreal Engine project hosts two physics-based rovers with plugins for stereo, lidar, event, and Single-Photon Avalanche Diode (SPAD) cameras, streaming time-stamped sensor data and pixel-accurate ground truth. Lastly, a Guidance, Navigation, and Control (GNC) stack provides web-based mission control. Validation shows a mean Intersection over Union (IoU) of 0.79 between predicted and rendered shadows at low sun elevations, and stereo depth analysis verifies decreased pixel coverage in shadowed regions relative to sunlit terrain.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37469

Who Shaped What? Untangling Human and AI Creative Contributions Through Spatial Provenance in Image Editing

Riya Sahni, Christine Dierk, Lydia Chilton, Eunyee Koh, Doga Dogan, Tongyu Zhou

原文摘要

Images co-edited with AI are often labeled to disclose AI use. However, creators feel these labels do not sufficiently describe their contributions to the editing process. Editing histories preserve requests, suggestions, and revisions, but how do creators use these logs to judge contribution? We investigated this with Roop, a mixed-initiative design probe that links image regions to editing histories (spatial provenance) and summarizes interactions in a heat map. Twenty participants edited images, annotated human and AI contributions, then reviewed the spatial provenance heat map. Participants credited themselves for directing changes while crediting AI for determining visual details. They judged contribution partly by whether their interactions achieved their intentions. Reviewing provenance helped participants remember interactions without always changing whom they credited. These findings motivate provenance systems that preserve enough context for creators to explain how interactions shaped their work, alongside the record of what happened.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37467

Penny for Your Prompts: A Measurement Study of Contextual Leakage in AI Chat Platforms

Paschalis Bekos, Billy Tsouvalas, Nick Nikiforakis, Michalis Polychronakis

原文摘要

AI chatbot platforms have become one of the most popular web interfaces users interact with online, routinely receiving personal and intimate information shared under an expectation of privacy. Yet, on the web application side, these platforms have the ability to embed third-party analytics, advertising, and session replay scripts that operate silently alongside the chatbot, creating an underexamined channel for conversational data leakage towards third parties. We conduct the first systematic large-scale measurement study of contextual leakage in AI chatbots, auditing the web interfaces of 42 general-purpose and domain-specific (health, legal, and education) platforms. Beyond standard network interception, we instrument the browser at the JavaScript engine level to attribute each data flow to the exact user action that triggered it, and the DOM capture mechanism used to retrieve its content, a granularity invisible to network-layer analysis alone. We find that 21 of these platforms leak conversation titles to third-party trackers, while nine leak verbatim user prompts. Beyond content, we observe a substantial amount of chatbot platforms sending user emails to third-party trackers, enabling the association of conversational context with a user's identity. Our findings cast traditional web privacy issues under a new light, highlighting the privacy issues that are inherent in how users interact with modern AI chatbots.

cs.CR · cs.CY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.35128

STeP-TS: Shared Temporal Filters with Pruning for Time Series

Hanne Raum, Jasper Hoffmann, Joschka Boedecker

原文摘要

Multivariate time series forecasting requires capturing temporal dependencies across multiple scales while accounting for both shared and variable-specific dynamics. Compact forecasting models have emerged as an attractive alternative to increasingly large architectures, but preserving strong predictive performance within tight computational and memory budgets remains challenging. We propose a compact one-layer convolutional framework that learns a shared bank of multi-scale temporal filters of each variable. Lightweight variable-specific scalar weights determine the contribution of each temporal component, enabling the model to capture shared temporal structure while adapting to variable-specific dynamics. The learned weights and filter-output energy further provide a natural signal for structured pruning of convolutional filters, reducing computational complexity with minimal degradation in forecasting performance. We additionally introduce an amplitude-adaptive normalization mechanism that preserves variable-dependent temporal amplitudes. Experiments on multiple datasets demonstrate forecasting performance competitive with state-of-the-art methods while requiring substantially fewer parameters and inference FLOPs and achieving low per-sample latency.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37465

What Carries Forward? Pretraining Disclosure Across Language Model Releases

Md Sakib Ul Islam, S M Mehedi Zaman

原文摘要

Understanding how language models were pretrained requires information about their data, processing procedures, and computational resources. However, it remains unclear whether successive releases preserve or expand earlier disclosure. We conduct a document-based audit of 41 model entries from 17 families using 24 pretraining-related indicators from the 2025 Foundation Model Transparency Index (FMTI). We examine overall scores and indicator profiles, tracking gains, losses, and retained disclosures across 24 adjacent comparisons in ten families. Scores decrease in 11 comparisons, increase in six, and remain unchanged in seven, with 38 indicator losses and 28 gains overall. Stable or improving scores can conceal losses: OLMo-2 and OLMo-3 receive identical totals despite three gains and three losses, while Llama-3.1 improves over Llama-2 while losing credit for two data-related criteria. Gaps also persist in corpus composition and training compute. These findings show that later releases do not consistently preserve earlier pretraining disclosure and motivate documentation that explicitly identifies changes and the applicability of inherited information.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37461

Concordat: Typed Sessions for LLM Agents

Milad Sikaroudi

原文摘要

Agents built on large language models are increasingly allowed to take consequential actions: cancelling bookings, issuing refunds, changing accounts. The rules that govern those actions, such as "obtain the customer's explicit confirmation before changing anything", are usually stated in the prompt and followed only as reliably as the model chooses to follow them. We present Concordat, a Python library that treats an agent as an object whose interface is a finite-state protocol, in the spirit of typestate and session types, and enforces that protocol on the model at run time. On every turn the model is offered only the tools that are legal in the current protocol state, calls outside that set are rejected before they have side effects, decisions reserved for humans can only be requested, and token and tool-call budgets are charged and split linearly across handoffs. Protocols are checked when they are defined, and a subclass of an agent is rejected if it could bypass its parent's protocol, a behavioural form of Liskov substitution. We evaluate a Concordat agent against the standard agent of tau-bench on its 50 airline tasks, adding simulated customers who pressure the agent to skip confirmation. The standard agent made changes without the required "yes" in 13 of 50 tasks with gpt-4.1 and in 29 of 128 task-runs with Claude Haiku 5.5; the Concordat agent made none, with no significant difference in task success. tau-bench's own reward did not detect most of these violations. Concordat is open source.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2602.00122

VDE Bench: Evaluating The Capability of Image Editing Models to Modify Visual Documents

Hongzhu Yi, Yujia Yang, Yuanxiang Wang, Tong Li, Zhenyu Guan, Tianyu Zong, Jiahuan Chen, Chenxi Bao 等 21 位作者

原文摘要

Image editing models can modify visual content through natural language, but editing dense documents requires precise local changes amid tightly coupled text, tables, and layout. We introduce VDE Bench, an evaluation resource for studying instruction-guided editing of Chinese and English document images. VDE Bench contains 3,506 instruction-guided image editing samples, including 1,578 text-region edits and 1,928 table-region edits. The benchmark pairs editing instructions and reference images with annotated editing regions and structured OCR outputs. Its evaluation protocol combines region-level and full-page measurements to assess textual correctness, structural fidelity, and visual content preservation. By focusing on the interaction between local edits and their surrounding document context, VDE Bench complements existing visual text editing benchmarks and provides a resource for diagnosing document-specific editing failures.

cs.CV · cs.AI · cs.MM

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.13470

Twincher: Towards Robust and Precise Physical AI via Bijective Representation Learning

Arkady Gonoskov

原文摘要

Perception and planning in physical systems often require inverting a continuous forward map $p \mapsto y = f(p)$, e.g., a renderer or a simulator, that can be queried but not inverted in closed form. Learned inverses are limited by their approximation error, whereas iterative solvers in observation space can stall at spurious stationary points. We instead learn a representation $r(y)$, insensitive to perturbations of $y$ normal to the data manifold, in which $p \mapsto r(f(p))$ is a well-conditioned bijection. In these coordinates, the least-squares inverse problem has no spurious interior stationary points, so that Gauss-Newton iteration with the exact forward model converges to the accuracy the data permit; the learned model need only be qualitatively correct. We introduce Twincher, an exactly invertible architecture of localized area-preserving rotations, trained with Jacobian-level objectives and a domain-growing curriculum. On synthetic maps with tunable nonconvexity, the worst-case residual reaches machine precision within five iterations once the query budget suffices, whereas an MLP-based baseline improves only gradually. In 6D localization of industrial objects in real depth images of the MVTec ITODD benchmark, given instance masks, twinchers trained only on CAD renderings make the iteration converge from a fixed initial guess within a few steps, without feature matching, pose regression, or pose hypotheses; in observation space, the same iteration fails for up to half of the views. All validation poses pass the strictest BOP thresholds and fit the sensor data about as closely as the ground-truth poses; 80\% of all 239 instances (67\% with visible masks only) are solved in agreement with the sensor data, and the number of training iterations grew only 1.5-fold from two to four pose parameters. Code is open source.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37459

M4Bench: Evaluating Procedural Specification for Clinical EHR Derivation Agents

Hannes Ill, Rafi Al Attrach, Rajna Fani, Ahram Han, Ryohei Yamamoto, Marlene Louisa Moerig, Dukyong Yoon, Leo Anthony Celi

原文摘要

Clinical research over electronic health records depends on derived variables whose definitions sit outside the schema, in item codes, time windows, missingness rules, and output-grain choices that change cohorts and downstream conclusions. We introduce M4Bench, 28 clinical derivation tasks across 15 task families on MIMIC-IV and eICU, to test whether AI coding agents can reproduce such derivations and how clinician-reviewed agent skills change their results. Its controls decompose the value of skills into specification completeness, delivery format, and schema familiarity. In a Docker-isolated Codex campaign (GPT 5.4 Mini and GPT 5.5), skills raise reward by 0.136 over the no-skill baseline, with 26 of 28 tasks improving. Specification completeness accounts for most of this gain: on an eight-task control subset, an operational spec alone raises reward by 0.162, and skills add only 0.024 on top, indistinguishable from zero. On a ten-task subset, decoy skills score like no skill and raw reference SQL nearly matches targeted skills, arguing against generic context or the skill format as the explanation. Schema obfuscation and restructuring preserve 86% and 70% of the skill gain (GPT 5.4 Mini, 26 MIMIC-IV tasks), a descriptive robustness check rather than a bound on memorization. A descriptive Claude Code replication on all 28 tasks (Opus 4.7 and Sonnet 4.6, 560 runs) is directionally consistent (+0.120, 21 of 28 tasks improving). These gains are partial agreement with the reference, not completed tasks: only 25 of 280 with-skill and 13 of 280 no-skill Codex runs pass every strict check, and skills barely change which rows agents return (key F1 +0.003). Skills are released as a versioned, clinician-reviewable markdown delivery format, with a family-level reference-validity audit. M4Bench releases tasks, skills, evaluation code, and sanitized per-run evidence as an open-source benchmark.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37456

An Input Skip Can Reparameterize a VAE Without Improving the Generator

Kevin Lee

原文摘要

An input skip can reduce reconstruction error while leaving a model's distribution of new samples unchanged. For a Gaussian variational autoencoder (VAE) with constant input skip $0\leqα<1$, a model without a skip can be written in skip form by multiplying its decoder output by $b=1-α$ and its noise variance by $b^2$. The distribution of observations and latent variables and its exact generative scores stay the same, while reconstruction mean squared error (MSE) is multiplied by $b^2$. Separate training can produce different generators because optimization depends on the parameter coordinates. In a Gaussian experiment with known density, changing skip and observation variance together reduces MSE but worsens energy score and the estimate of negative log density from importance sampling. On seven annual Deep-ocean Assessment and Reporting of Tsunamis (DART) records, energy score differences at the same observation variance have both signs on four original records and favor the skip on three records from 2018. Probabilistic principal component analysis (PPCA) has lower mean energy scores than every neural DART fit. With the encoder and decoder kept the same, estimating observation variance from training reconstruction error can also worsen energy score. Assessing generation requires more than reconstruction error.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37454

SecDMP: Provably Secure Data Memory-Dependent Prefetching (Extended Version)

Jens Sprengers, Marton Bognar, Lesly-Ann Daniel, Frank Piessens

原文摘要

Data memory-dependent prefetchers (DMPs) are a microarchitectural optimization recently introduced in mainstream desktop and server CPUs. Although DMPs offer performance improvements, they have been shown to enable side-channel leakage of secrets, even from constant-time code that has been hardened against Spectre attacks. Unfortunately, existing defenses either incur significant performance overhead or, as we show, fail to prevent all DMP leakage. In this work, we address this gap by designing a defense that is both secure and efficient. First, we propose a classification of DMP leakage, categorize existing and novel attacks, and analyze which leakage classes are mitigated by existing defenses. We validate this analysis empirically by implementing the first open-source DMPs on a RISC-V processor, showing that the only existing defense that aims to preserve DMP performance fails to protect against entire leakage classes. Next, we propose SecDMP, a provably secure and efficient hardware-based defense. SecDMP requires secrets to be marked in memory and ensures that DMPs never encode these secrets in the microarchitecture---without compromising performance for public data. We formally prove that SecDMP introduces no leakage beyond a baseline semantics without DMPs. Notably, when combined with speculative-execution defenses, SecDMP restores complete microarchitectural security for constant-time code. Finally, our empirical evaluation shows that SecDMP prevents all DMP leakage while incurring minimal performance overhead and hardware cost.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37452

Electric-Field Induction Motor with Discrete Circuit Elements and Improved Rotor Dynamics

Alex S. Miller, Jeffrey H. Lang

原文摘要

Electric-field-based actuators and machines lead the design space at the nanoscale and in biological systems, while having the potential to be used in favorable macroscale applications which prioritize minimal mass, performance in a vacuum, or performance in high temperatures. Electric-field induction motors consist of a set of stator electrodes which induce opposite charges onto a movable rotor surface. In earlier work, rotor surfaces for electric-field induction motors have been made of single continuum materials, which are limited in possible resistivity, permittivity and circuitry characteristics. To enhance design freedom, we develop a rotor for electric-field-based machines which may be constructed out of discrete circuit components between a finite number of conductive vanes. Magnetic-field induction motors, which are common in machinery, often utilize ``deep bar'' rotors, consisting of conducting bars which decrease the rotor time constant with increasing frequency using the skin depth effect. We propose, analyze, design and demonstrate a macro-scale electric-field induction motor which uses circuitry on the rotor surface to emulate the ``deep bar'' design, providing improved torque over a wide range of speeds.

cs.RO · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37451

Interpretable Meta-Policies for Neural Decision Making

Raban Emunds, Jannis Blüml, Quentin Delfosse, Kristian Kersting

原文摘要

Deep Reinforcement Learning remains difficult to interpret and align due to the black-box nature of neural networks. While (neuro-)symbolic approaches improve transparency by incorporating symbolic reasoning, applying them directly to low-level actions results in overly complex, unreadable policies. We introduce NEXUS, a hierarchical RL framework that resolves this tension by combining neural skills with symbolic meta-policies. By shifting transparent reasoning to high-level skills rather than atomic actions, NEXUS drastically reduces symbolic complexity without sacrificing environment performance. Object-centric observations enable high-level reasoning and the design of reward functions and meta-policies by interaction with LLMs. We demonstrate that NEXUS agents learn disentangled skills, are interpretable regarding high-level goals, are better aligned to goals described in the game manual, less prone to reward hacking and more robust to game simplifications than deep RL. Finally, we isolate and evaluate the impact of different meta-policy architectures (neural, symbolic, neuro-symbolic) on environmental return and aligned task performance.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37450

Graph Representation Learning via Adaptive Expectile Aggregation

Tianyi Zhu, Wei Lan

原文摘要

Graph neural networks (GNNs) rely critically on neighborhood aggregation, yet conventional mean aggregation may fail to capture class-relevant distributional information, particularly in heterophilic graphs. We propose ExpectileGCN, an adaptive graph aggregation framework that introduces a learnable expectile level to capture neighborhood information beyond the mean. The proposed operator continuously adjusts aggregation between minimum- and maximum-type behaviors, with mean aggregation as a special case. A differentiable approximation based on sigmoid smoothing and fixed-point iterations enables end-to-end optimization. Theoretically, we establish stability properties and transductive generalization guarantees for ExpectileGCN. We further investigate its classification risk under heterophilic neighborhood models. For informative neighborhoods, we show that expectile aggregation can exploit class-dependent scale differences to achieve a classification advantage over mean aggregation. Under a local asymptotic regime with diminishing per-neighbor label informativeness, we establish that this advantage can persist in terms of limiting classification risk. Experiments on homophilic and heterophilic benchmark graphs demonstrate strong predictive performance and improved robustness under feature corruption and structural perturbations.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37448

Test-Time Communication in Trading Agent Swarms

Avid Fayaz, Harry Zhang, Håvard Alstadheim, Erik Nordlöf, Vilhelm Karlin, André Silva

原文摘要

Communication between agents has mostly been studied on tasks with a shared objective and fast, clear feedback. Trading has neither: each agent manages its own account, with decisions being scored by markets late and noisily. A trading swarm is thus a population of independent decision-makers rather than a team, for which convergence is a risk and not the goal. We ran 200 agents from four model families in groups of ten under five communication regimes, from isolation to message boards and shared notes, over seven US trading days (1 to 9 October 2026), logging everything each agent read before every decision. In two of the four families, communicating groups came to hold far more of the same stocks than the isolated group. A group's return was largely the return on what its members held in common. Seeing a post from a groupmate made an agent 7 percentage points more likely to reuse an eight-word phrase from it. Agents that started too close together to see each other's posts shared such a phrase in 14% of cases, the rate that common inputs produce. Seeing the post did not detectably change that morning's trades. Case studies traced the adoption of positions and decision rules over subsequent days, and communicating groups sold in step more often than isolated ones. Because isolated groups also converged on the same stocks, sometimes completely, assessments of herding need to measure excess convergence relative to a no-peer baseline.

cs.MA · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37446

PolyGandr: Steering Generative Models via Spatial Navigation through Latent Space

Mingwei S. G. Li, Susie S. Y. Li, Isabel Moreira de Oliveira, Ryan P. Adams, Remco Chang

原文摘要

Generative models support content creation across text, images, videos, and design disciplines, yet their interfaces rely primarily on natural language. While effective for specifying high-level intent, language can be inefficient and imprecise for fine-grained control, iterative refinement, and open-ended exploration. We present PolyGandr, a visual interface for exploring relationships between latent representations and generated outputs, complementing natural-language model steering. PolyGandr formulates generative control as high-dimensional navigation, enabling users to define starting points, steering directions, and step sizes through a unified map-and-mixing-palette interface. Combining global exploration with local refinement supports both broad design-space navigation and fine-grained output manipulation without repeatedly translating visual intent into prompts. We evaluate PolyGandr across three use cases: StyleGAN2 face generation, Stable Diffusion chair design, and rotational kirigami engineering. A formative study indicates that PolyGandr complements existing workflows by supporting real-time editing while simultaneously providing an overview and means to explore the broader design space.

cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2505.13004

EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code

Yuhao Qing, Boyu Zhu, Mingzhe Du, Zhijiang Guo, Terry Yue Zhuo, Qianru Zhang, Jie M. Zhang, Heming Cui 等 12 位作者

原文摘要

Existing code generation benchmarks primarily evaluate functional correctness, with limited focus on code efficiency and often restricted to a single language like Python. To address this gap, we introduce EffiBench-X, the first multi-language benchmark designed to measure the efficiency of LLM-generated code. EffiBench-X supports Python, C++, Java, JavaScript, Ruby, and Golang. It comprises competitive programming tasks with human-expert solutions as efficiency baselines. Evaluating state-of-the-art LLMs on EffiBench-X reveals that while models generate functionally correct code, they consistently underperform human experts in efficiency. Even the most efficient LLM-generated solutions (Qwen3-32B) achieve only around \textbf{62\%} of human efficiency on average, with significant language-specific variations. LLMs show better efficiency in Python, Ruby, and JavaScript than in Java, C++, and Golang. For instance, DeepSeek-R1's Python code is significantly more efficient than its Java code. These results highlight the critical need for research into LLM optimization techniques to improve code efficiency across diverse languages. The dataset and evaluation infrastructure are submitted and available at https://github.com/EffiBench/EffiBench-X.git and https://huggingface.co/datasets/EffiBench/effibench-x.

cs.CL

查看论文
arXiv ↗PDF ↗