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 14:26 · 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 15:09 — 2026-11-09 15:09（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 14:26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 14:25（北京时间）
新论文 · v1arXiv:2610.37909

TERRA: Task-Oriented Edge AI for Regional Fire Detection with Identity-Free Reporting

Mohammad Kazemi, Julie A. McCann

原文摘要

Distributed fire-monitoring systems may involve many sensing devices reporting over a shared uplink, even though the operational objective is often to identify regions exhibiting evidence of fire rather than to recover device-specific measurements. We introduce TERRA (Task-Oriented Edge Representation and Regional Aggregation), an edge-AI framework that combines task-oriented local inference, identity-free region-tagged reporting, and permutation-invariant regional evidence aggregation. TERRA supports two reporting modes: TERRA-Score, in which each device communicates a quantized local fire probability, and TERRA-Feature, in which it communicates a compact learned representation for receiver-side aggregation using a permutation-invariant DeepSets model. Using all 15 numerical sensing modalities of the distributed indoor EN54 fire-alarm dataset as a proof-of-concept testbed, we evaluate regional inference for an episode-level fire-scenario target under repetition-disjoint three-fold cross-validation. We study representation size, task-payload quantization, report availability, and robustness to missed and false recovered messages. With nine reports and perfect message recovery, TERRA-Feature achieves mean AUPRC 0.990 using a 24-bit task payload, while TERRA-Score achieves 0.987 using only 6 bits; both attain an MDR of 1.81% at FAR $\leq$1%. TERRA-Feature achieves slightly higher AUPRC under reliable recovery, whereas the more compact TERRA-Score is less sensitive to increasing false-message contamination.

cs.LG · cs.AI · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37906

Beyond Low-Pass Dynamics: Frequency-Selective Spiking Reservoirs with Resonant Neurons

Aurora Micheli, Claudio Gallicchio, Nergis Tomen

原文摘要

Spiking reservoir computing combines the training efficiency of fixed recurrent reservoirs with the energy efficiency of event-driven inference, where computation is triggered by sparse spikes rather than executed densely at every timestep. However, existing spiking reservoirs almost exclusively rely on Leaky Integrate-and-Fire (LIF) neurons, whose low-pass dynamics limit their ability to distinguish information encoded at different temporal frequencies. We introduce HRF-Res, a liquid state machine in which LIF neurons are replaced by a heterogeneous population of Harmonic Resonate-and-Fire (HRF) neurons. These neurons exhibit intrinsic oscillatory dynamics and selectively respond to input frequencies, enabling the reservoir to capture frequency-specific temporal patterns. The result is more discriminative representations and higher classification accuracy than LIF-based reservoirs, achieved without sacrificing the energy efficiency of spiking computation, with up to 19x lower energy consumption than an equivalent non-spiking oscillatory reservoir. Evaluated on ten benchmarks spanning time series, sequential images, audio spike trains, and neuromorphic vision, HRF-Res achieves state-of-the-art accuracy among spiking reservoir methods. These results demonstrate that introducing frequency-selective dynamics into spiking reservoirs improves representational quality and classification performance while preserving their inherent energy efficiency.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37905

FilingLoop: Evaluating and Evolving LLM Agents for Corporate Disclosure Review and Revision

Wentao Zhang, Yilei Zhao, Guangyan Gan, Shuo Sun, Lin William Cong

原文摘要

Public disclosure repositories such as SEC EDGAR support informed investment through web access to corporate filings. Supporting their review with language model agents requires discovering unstated deficiencies across related documents, acquiring missing company facts, and verifying that requested revisions satisfy evidence-backed requirements. Existing financial question-answering evaluations provide limited evidence of these interactive capabilities. We introduce \textbf{FilingLoop}, an interactive benchmark and a self-evolving agent framework for corporate disclosure review and revision. Grounded in historical U.S.\ Securities and Exchange Commission correspondence, FilingLoop reconstructs 380 predominantly IPO review tasks from 96 companies under distinct information constraints. An evaluator separate from the acting agents scores final filings and responses against 6,099 eligible requirements and audits unsupported claims and harmful revisions. Our framework couples iterative review and revision within each case with procedural learning across cases, converting requirement-level evaluation feedback into role-specific guidance without updating model weights. Updates affect only subsequent cases, allowing procedural adaptation to be assessed without retrying scored tasks. On the evaluated stream, evolution increases requirement fulfillment from 24.28\% to 27.96\% and full comment resolution from 16.90\% to 20.75\%, with a 5.8\% increase in total cost over the fixed-policy variant. FilingLoop connects the concerns an agent discovers with the company facts it obtains and the revisions it commits, providing requirement-level feedback for procedures used in later review tasks.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37903

Think Twice: The Metis-1.6 Technical Report

Giulianno Vollmer

原文摘要

Metis is a bet that better data, better training methods and new architectures can buy what a bigger parameter count cannot, at a fraction of the cost. Metis-1.6 is its latest step: two language models built from scratch by a single researcher, Praxis (2.94B parameters, 0.46B active per pass) and Logos (10.23B parameters, 1.18B active per pass). Both run a hybrid Mamba-2 and attention mixture-of-experts stack twice for every token, so each token gets a second look. Each was trained on 1.02T tokens in total: 804.76B of pretraining, 18B of context extension to 131,072 tokens, and 200B of supervised fine-tuning. Metis-1.6 was never meant to challenge frontier models, and across 40 post-trained benchmarks it mostly does not: Logos averages 52.93, seventh of 17 models in its comparison set and within a point of Qwen3-4B. But it gets there on roughly a twelfth of the median training data of the comparators that disclose it, and with fewer active parameters per token than any model that beats it, which puts it on the Pareto frontier for both. In mathematics it ranks second of 30 models, with 67.50% on AIME 2025 and 63.64% on HMMT February 2026. It is weak at code, instruction following and long context. The rest of the report is the part I found most valuable: what went wrong. The optimizer I configured never ran, and attention trained with AdamW for all of pretraining. A 1.77B-parameter n-gram memory learned to switch itself off. Five fine-tuning choices cost capability. And a length reward under group-mean normalization punished correct solutions for being long once a group's pass rate passed 2/3, a sign inversion I prove and fix with a one-line clamp. I close with the 10B-token ablations behind MoRE (Mixture of Recursive Experts), the looped architecture of Metis-1.7.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37901

Scan Before You Install: Detecting and Mitigating Local and Composite Vulnerabilities in Skills

Parth A. Gandhi, Avital Aviv, Prasanna N. Wudali, Yuval Elovici, Asaf Shabtai

原文摘要

An agent skill packages natural-language instructions, scripts, and reference files that an LLM-based agent loads for a task. Skills may access the file system, shell, and network under user-authorized permissions; weaknesses can lead to unsafe execution. Existing scanners primarily target malicious skills, not unintended vulnerabilities in public repositories, and analyze skills in isolation, overlooking multi-skill interactions. To address these gaps, we developed a six-module scanner: Content Extraction, Local Analysis, Composite Analysis, Validation, Reporting, and Mitigation. Local Analysis detects unintended vulnerabilities in benign skills. On a 556-case leaderboard subset of SkillTrustBench, it achieved 95.90% recall with a 4.22% false positive rate; on a balanced sample of 1,000 MalSkillBench skills, its F1 was 0.947, outperforming Cisco's Skill Scanner, NVIDIA's SkillSpector, AgentSkillsScanner, and SkillSieve. In 1,587 skills from the 75 most-starred GitHub repositories, three analysts confirmed 53 of 59 findings (89.8% precision) across 23 repositories. We developed proof-of-concept (PoC) attacks for each vulnerability, disclosed 10 medium- and high-severity cases to maintainers, and tested mitigations on the remaining cases. Composite Analysis models dependencies among skills through shared resources, invocations, and instruction-mediated interactions. On SCR-Bench, its F1 score was 0.991 (98.7% precision, 99.6% recall), versus 0.816-0.858 for three SkillsGuard configurations released with CompoSkill. It identified two composite findings on GitHub, validated by PoC attacks. The Mitigation module recommends skill substitution, patches, and configuration changes. For 47 of 55 GitHub findings, mitigations prevented PoC attacks in all trials while preserving tested legitimate functionality.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2508.09004

Dividing a cake for the irrationally entitled

Florian Brandl, Andrew Mackenzie

原文摘要

A perfectly divisible cake is to be divided among a group of agents. Each agent is entitled to a share between zero and one, and these entitlements are compatible in that they sum to one. The mediator does not know the preferences of the agents, but can query the agents to make cuts and appraise slices in order to learn. For each entitlement profile, we provide a lower bound on the number of queries that the mediator requires to construct an allocation that respects the entitlements regardless of preferences. If one of the entitlements is irrational, then the mediator requires an arbitrarily large number of queries.

econ.TH · cs.GT

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2512.05459

PrivCode: When Code Generation Meets Differential Privacy

Zheng Liu, Chen Gong, Terry Yue Zhuo, Kecen Li, Weichen Yu, Matt Fredrikson, Tianhao Wang

原文摘要

Large language models (LLMs) have presented outstanding performance in code generation and completion. However, fine-tuning these models on private datasets can raise privacy and proprietary concerns, such as the leakage of sensitive personal information. Differentially private (DP) code generation provides theoretical guarantees for protecting sensitive code by generating synthetic datasets that preserve statistical properties while reducing privacy leakage concerns. However, DP code generation faces significant challenges due to the strict syntactic dependencies and the privacy-utility trade-off. We propose PrivCode, the first DP synthesizer specifically designed for code datasets. It incorporates a two-stage framework to improve both privacy and utility. In the first stage, termed "privacy-sanitizing", PrivCode generates DP-compliant synthetic code by training models using DP-SGD while introducing syntactic information to preserve code structure. The second stage, termed "utility-boosting", fine-tunes a larger pre-trained LLM on the synthetic privacy-free code to mitigate the utility loss caused by DP, enhancing the utility of the generated code. Extensive experiments on four LLMs show that PrivCode generates higher-utility code across various testing tasks under four benchmarks. The experiments also confirm its ability to protect sensitive data under varying privacy budgets. We provide the replication package at the code repository: https://github.com/Liuzzyg/PrivCode.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37898

SAC-GCL: Structure-Aware Compression for Graph Contrastive Learning

Muhammad Ifte khairul Islam, Tanvir Hossain, Esra Akbas

原文摘要

Graph Contrastive Learning (GCL) has achieved remarkable success in self-supervised representation learning by maximizing agreement between augmented views of a graph. Although augmented view generation is the central step in GCL, existing models rely on stochastic augmentation of the input graph, such as edge perturbation and node masking, which lack structural awareness and frequently destroy critical topology or introduce semantically inconsistent views. While recent adaptive methods improve upon random perturbations, they primarily operate on localized node or edge neighborhoods and fail to capture higher-order, macro-level structural organization crucial for graph classification. To address this limitation, we propose Structure-aware Compression for Graph Contrastive Learning (SAC-GCL), a novel framework that employs structural decomposition and graph compression as a principled view generation strategy. Moving beyond random augmentations, SAC-GCL leverages structural decomposition techniques to extract cohesive subgraphs and condense them into supernodes, constructing coarsened graph views that preserve local density and capture higher-level structural patterns while reducing noise and redundancy. We leverage multiple cohesive subgraph models to derive complementary views of the graph, each capturing distinct structural properties. To capture multi-resolution information, a hierarchical view encoder processes these compressed views by initializing super-node features with shared-weight cohesive subgraph embeddings. Our results from extensive experiments on six benchmark datasets demonstrate that structure-aware compression provides a powerful alternative to random perturbations, yielding more robust and discriminative graph representations for graph classification tasks.

cs.LG · cs.SI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.11512

EdgeCIM: A Hardware-Software Co-Design for CIM-Based Acceleration of Small Language Models

Jinane Bazzi, Mariam Rakka, Fadi Kurdahi, Mohammed E. Fouda, Ahmed Eltawil

原文摘要

The growing demand for deploying Small Language Models (SLMs) on edge devices, including laptops, smartphones, automotive and robotic computing platforms, and high-performance embedded systems, has exposed fundamental inefficiencies in existing accelerators. While GPUs handle prefill workloads efficiently, the autoregressive decoding phase is dominated by GEMV operations that are inherently memory-bound, resulting in poor utilization and prohibitive energy costs at the edge. In this work, we present EdgeCIM, a hardware-software co-design framework for accelerating autoregressive decoding of SLMs on edge devices in latency-critical applications. At its core is a CIM macro, implemented in 65 nm, coupled with a tile-based mapping strategy that balances pipeline stages, maximizing parallelism while alleviating DRAM bandwidth bottlenecks. Our simulator enables design space exploration of SLMs up to 4B parameters, identifying hardware configurations that optimize latency and energy according to a configurable objective function. On LLaMA3.2 3B (INT4), EdgeCIM achieves 1.76x and 3.21x higher throughput than NVIDIA Jetson AGX Orin and Orin Nano Super operating in MAXN mode, respectively, and 7.07x higher throughput than Qualcomm's Snapdragon-X Elite. Extensive benchmarks on TinyLLaMA 1.1B, LLaMA3.2 (1B, 3B), Phi 3.5 mini 3.8B, Qwen2.5 (0.5B, 1.5B, 3B), SmolLM2 1.7B, SmolLM3 3B, and Qwen3 (0.6B, 1.7B, 4B) reveal that our accelerator, at INT4 precision, achieves on average 336.4 tokens/s and 173 tokens/J. These results establish EdgeCIM as a compelling solution towards real-time, energy-efficient, latency-critical SLM inference at the edge.

cs.AR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37897

Efficient Joint Trajectory Optimization and Resource Allocation for Secure UAV Networks: A Deep Reinforcement Learning Approach

Abdulmalik Alwarafy, Mohamed Hayajneh, Mustafa Al Juboori, Abdulaziz Almarzooqi, Tahnoon Almazrouei, Robera Abera, Kaleab Nega

原文摘要

Unmanned Aerial Vehicles (UAVs) are increasingly deployed in wireless networks; however, ensuring secure communication and efficient energy usage remains challenging. This paper addresses the joint trajectory optimization and resource allocation problem in UAV networks in the presence of a tethered UAV flying center and a malicious ground eavesdropper. In the proposed model, UAVs are equipped with energy harvesting capabilities and can adaptively switch between transmitting, jamming, and relaying roles to deliver data to a tethered UAV center for optimized network performance. An optimization problem is formulated to maximize a utility function that balances secrecy rate, energy consumption, and interference. To address the high non-convexity of the problem and its real-time decision requirements, a Proximal Policy Optimization (PPO)-based Deep Reinforcement Learning (DRL) algorithm is proposed to solve the problem and learn the network dynamics. Extensive simulation results demonstrate that the proposed approach achieves superior secrecy performance, lower energy consumption, and reduced interference compared to conventional and DRL-based methods.

eess.SY · cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37896

The Anatomy of Socio-Demographics in Pluralistic Offensiveness Modeling: When and Where It Helps, and the Role of Reasoning

Yifan Wang, Leixin Zhang, Jinyi Mu, Yu Wang, Mayank Jobanputra, Isabel Valera, Vera Demberg

原文摘要

Subjective judgments such as offensiveness often vary substantially across individuals, motivating pluralistic modeling approaches that incorporate annotators' socio-demographic information to capture this variation. However, prior findings on the benefits of socio-demographic information for pluralistic modeling are mixed, calling for a systematic analysis of both its effectiveness and the mechanisms through which it improves prediction. In this work, we study $\textbf{when}$ and $\textbf{where}$ socio-demographics benefit pluralistic offensiveness modeling, as well as $\textbf{the role of explicit reasoning}$ in leveraging this information. Across three multi-annotator datasets with prompted and trained LLMs, we first show that demographic gains are small and inconsistent for individual predictions but become clearer at the group and population levels, because aggregation attenuates the idiosyncratic variation that masks small but systematic demographic signals. Second, using a reasoning and prediction format that explicitly decomposes individual judgment into an overall baseline and a demographic-specific deviation, we show that the gains arise from both components: demographic information improves baseline estimation and enables meaningful demographic-specific shifts, and interventions show that better component estimates improve final predictions. Finally, comparing direct demographic conditioning with explicit reasoning about how the text interacts with annotator demographics, we find that reasoning yields more accurate baseline and shift estimates as well as final predictions, whereas conditioning alone rarely produces informative shifts. These results suggest that the mixed evidence in prior work may partly stem from individual-level evaluation, and that the value of socio-demographic information depends on both how it is evaluated and how models are guided to use it.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.23927

GlanceWAM: Sparse Test-Time Imagination for World-Action Models

Linhan Wang, Zijian An, Mingyuan Zhang, Chen Dai, Yi Xu, Can Cui, Jiayan Wang, Zichong Yang 等 11 位作者

原文摘要

Video generative models provide rich physical priors for robot learning, yet existing world-action models (WAMs) face a fundamental trade-off: synchronous video generation at control rate is latency-prohibitive, while abandoning test-time visual imagination sacrifices task success. We show that visual imagination achieves both real-time inference and superior success rates when generated asynchronously off the critical path and consumed directly in latent space. We introduce GlanceWAM, which decouples imagination from control on a single shared video DiT backbone: an asynchronous proposer glances ahead on a slow clock to imagine a single lookahead frame seconds into the future in the background, while an action head decodes action chunks at control rate (48 ms) purely in latent space without blocking. Enabled by a non-interfering attention mask that isolates video representations and staleness-robust horizon training that accommodates asynchronous lookahead aging, GlanceWAM breaks the speed-success dilemma. Trained purely on demonstrations, it attains 72.2% on the 24-task RoboCasa kitchen benchmark (vs. 67.1% for synchronous Cosmos Policy) and 99.0% on LIBERO while cutting per-chunk control latency 24x relative to synchronous world-action models (48 ms on one A100). In single-arm and bimanual real-robot manipulation, it achieves higher average success than $π_{0.5}$ without any robot-data pretraining. Code is available at https://github.com/linhanwang/GlanceWAM and real-robot videos at https://linhanwang.github.io/glancewam/.

cs.CV · cs.AI · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37894

Twisted Fourier Analysis of Quantum Weight Enumerators

Ching-Yi Lai

原文摘要

A unified Fourier framework for quantum weight enumerators of prime-power-dimensional qudits is developed in this paper. We introduce the notions of Weyl power spectrum and Weyl-conjugation autocorrelation for the Weyl-operator quantities nderlying the Shor--Laflamme weight enumerators. Representing these quantities as formal vectors, we show that they form a symplectic Fourier transform pair, from which the quantum MacWilliams identity follows by applying the Hamming-weight functional. This framework extends to a family of twisted Fourier transforms, including the Rains shadow transform. We show that identical-copy Bell sampling corresponds to a twisted autocorrelation related to the shadow enumerator through Weyl translation and Hamming projection. We further prove that all twisted Fourier transforms are Weyl translations of either the ordinary MacWilliams transform or the Rains shadow transform. This two-class reduction implies that the twists yield no additional independent coefficientwise positivity constraints under compatible projections. Nevertheless, the framework leads to refined MacWilliams and shadow identities that retain more Fourier information than ordinary Hamming weight enumerators. We employ these refined identities in linear programming, together with simplex mapping and shadow-coset counting, to exclude surviving candidate weight distributions. These techniques yield tighter bounds for binary and qutrit quantum codes, including nonexistence results for specific code parameters.

quant-ph · cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37892

Advisor, Co-pilot, or Guardian? AI Role Framing and Human Decision Behavior in Automated Vehicle Takeovers

Wei-Hsiang Lo, Jingyi Xie, Gaojian Huang

原文摘要

Artificial intelligence (AI) technology has gradually been integrated into automated vehicles. However, how this technology could systematically support takeover transitions in SAE Level 3 automated vehicles remains unknown, even though this level may remain a major form of driving automation in the near future. To address this, we implemented the three AI roles proposed by the triadic Human-AI collaboration framework (Advisor, Co-pilot, and Guardian) as potential authority-ability configurations for AI agents within an automated system. We then examined their interactions with explanation type (why and action) and directional semantics (ipsilateral and contralateral) in an automated driving simulator study with 24 participants. Results showed that, across the three AI roles, Advisor had the shortest decision-making time, followed by Guardian and Co-pilot. Advisor and Guardian were associated with higher decision-making accuracy and higher satisfaction ratings than Co-pilot. Guardian was associated with the lowest workload, followed by Advisor and Co-pilot. The effect of explanation type on decision-making time depended on AI role. Action explanations were faster under Advisor, whereas why explanations were faster under Co-pilot. For directional semantics, ipsilateral semantics were associated with shorter decision-making time than contralateral semantics. Overall, these findings provide preliminary guidance for designing AI-role authority-ability configurations and their associated speech-based takeover messages.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37891

When More Planning Hurts: Learned Planners for World Models

Josef Chen

原文摘要

On PushT, our fixed action updater (1,505 parameters) solves 8 of 16 scenes reserved from our configuration selection. The comparison planners perform as follows: Selected Adam (7 tasks solved, total planning and encoding time 218.440s), adapted iCEM (2 tasks solved, total planning and encoding time 49.309s), released LePlanner (16 tasks solved, total planning and encoding time 5.652s). The total planning and encoding time for our action updater is 59.079s. Note that our action updater does not satisfy the task-cost criterion we fixed before evaluation. We also conduct another matched experiment where we only replay the first ten commands in each context and then allow the next solve 4, 8 or 12 updates (subsequent solves all get 8 updates). Among all 16 contexts (8 scene clusters), the 3 budgets get 9, 8 and 7 successes, respectively. Interestingly, the extra updates did not rescue any failing task in this experiment. All the changes in success/failure happen in one scene cluster, where we observe that the extra updates decrease the costs of the selected latent world-model trajectories for our updater, while the tasks that used to be successes become failures. The code, weights, evaluators, execution traces and cost accounting accompany the paper.

cs.RO · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.35743

SEMA-Auto: Sighted and Efficient Multi-Turn Attack with Autonomy

Mingqian Feng, Xiaodong Liu, Weiwei Yang, Chenliang Xu, Jialin Song, Qiyao Ma, Chengquan Guo, Carolyn Buractaon 等 11 位作者

原文摘要

Existing jailbreak attackers fall into two classes: static planners fix their single- or multi-turn adversarial plans in advance, remaining simple but losing sight of the victim's replies, wasting turns and limiting transferability; interactive generators read each victim reply to generate the next-turn attack but require in-loop evaluators for success signals or hints, incurring substantial costs and inflated performance. Bridging this gap, we propose SEMA-Auto, a sighted and efficient multi-turn attacker with autonomy, interacting with the victim model and terminating the session by itself upon success. To stabilize its behaviors and boost its capabilities, SEMA-Auto is trained in two stages. Synthetic bootstrap tuning installs the notion of attack targets and conforming decisions by fine-tuning the base model with bootstrapped trajectories. Decision-supervised reinforcement learning then optimizes two objectives jointly yet separately, reinforcing the attack with higher jailbreak reward while supervising the decision at each turn against an absolute target. Our method achieves state-of-the-art (SOTA) attack success rates (ASR) across multiple datasets, victims, and judges, outperforming all static and interactive baselines, within almost the fewest turns, demonstrating both effectiveness and efficiency. For example, SEMA-Auto performs a $76.0\%$ ASR@1 within an average of $3.0$ turns against DeepSeek-V4-Flash on AdvBench, while the best static baseline is $54.8\%$ with fixed $7$ turns and the best interactive baseline is $43.8\%$ in $3.7$ turns. Against safety-hardened frontier models, GPT-oss-120B, GPT-5.4, Claude-Haiku-4.5, and GPT-6-Astra, our counter-trained attacker achieves an average $59.6\%$ ASR@1 on HarmBench, $13.8\%$ over prior SOTA. Our code is available at: https://github.com/microsoft/SEMA

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37888

Cognitive Debt in the GenAI Era - Listening to Practitioners' Voices on the Loss of Understanding

Theocharis Tavantzis, Bianca Trinkenreich, Michaela Greiler, Júlia Condé Araújo, Marina Condé Araújo, Italo Santos, Alexander Serebrenik, Margaret-Anne Storey 等 9 位作者

原文摘要

Fast-paced AI-assisted software development risks reducing developers' understanding of the systems they build. This growing gap between what the system does and what developers understand about it, described as ``cognitive debt'', is not new, but AI has exacerbated it. This has led to a recent surge in blog posts and online discussions, in which practitioners recognize and write about cognitive debt, and share their experiences well before academic studies can capture them. To understand their concerns and inform future research and practice, we conduct a grey literature review of 76 sources, focusing on how cognitive debt is conceptualized and manifests, its contributing factors, its consequences, and the practices to prevent, detect, and mitigate it. We find that cognitive debt can accumulate unnoticed behind working code and passing tests, particularly when developers accept AI-generated solutions without building understanding. Practitioners report consequences such as harder maintenance and debugging, fragmented knowledge in the team, and reduced productivity. They propose practices such as documenting design rationale, review-sized changes, comprehension gates, and knowledge-sharing rituals, along with signals like reliability metrics to detect it. Our findings give software teams a structured view of emerging practical approaches in AI-assisted development and stress the need to preserve human understanding alongside faster code production.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37887

Proof Theory of Quantifier Shifts - An Overview

Matthias Baaz, Mariami Gamsakhurdia

原文摘要

Quantifier shifts are one of the oldest proof methods, but they are orthogonal to the cut free format: They can shorten proofs non-elementarily. (The proof is based on the sequence of proofs exhibiting a non-elementary difference between proofs with cuts and cut-free proofs by Orevkov). The cost is, however, that those proofs are globally sound but locally unsound. (Their subderivations might be unsound in contrast to the Hilbert concept of proof). In non-classical logics these calculi are only sound when all quantifier shifts are added. This characterizes all intermediate logics where Skolemization and the epsilon calculus is conservative (in contrast to the epsilon theorem which holds only for finite-valued Goedel logics).

cs.LO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.09906

Depth-Efficient Quantum Topological Data Analysis for Regime-Specific Detection of Financial Stress

Arul Rhik Mazumder, Shreyan Ronit Mazumder

原文摘要

We present, to our knowledge, the first adaptation of Pauli Correlation Encoding (PCE) to quantum topological data analysis, reformulating Betti number estimation as a depth-efficient variational optimization over a compressed qubit register. From a Takens embedding and Vietoris-Rips filtration of S&P 500 returns, we extract combinatorial Laplacians and recast null-space counting as a continuous-PCE Rayleigh-quotient minimization with variational deflation, encoding $n_k$ simplex indices into $O(n_k^{1/κ})$ qubits with shallow, ancilla-free circuits. Because the resulting loss is rational rather than bilinear in the correlators, the barren-plateau bound of Sciorilli et al. does not transfer; empirically the gradient variance decays only polynomially, with no exponential barren plateau, over $n=4$-$12$ qubits. The classical stage matches ripser on all 190 sliding windows (2003-2010). On the real market Laplacians ($β_1=1$-$22$), PCE-VQE recovers no null vector from a random start, but warm-starting from a classical null-space surrogate recovers $β_1$ exactly on all seven windows tested ($n_k \le 259$), placing the obstacle in the optimization landscape rather than the encoding. Chronologically split classification gives in-regime ROC AUC 0.818, but out-of-distribution evaluation on the 2020 COVID shock and 2022 rate cycle (AUC 0.009, 0.515) shows the calibration does not generalize across crisis regimes.

quant-ph · cs.LG · q-fin.ST

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.05750

RVPO: Risk-Sensitive Alignment via Variance Regularization

Ivan Montero, Tomasz Jurczyk, Bhuwan Dhingra

原文摘要

Current critic-less RLHF methods aggregate multi-objective rewards via an arithmetic mean, leaving them vulnerable to constraint neglect: strong performance in one objective (e.g., correctness) can offset critical failures in others (e.g., safety or formatting). This can mask low-performing "bottleneck" rewards that are necessary for reliable multi-objective alignment. We propose Reward-Variance Policy Optimization (RVPO), a risk-sensitive framework that penalizes variance across rewards during advantage aggregation, and shifts the objective from "maximize sum" to "maximize consistency." Its SoftMin objective can be locally approximated by the mean reward minus an inter-objective variance penalty. We evaluate RVPO on rubric-based medical and scientific reasoning with up to 17 reward signals (Qwen2.5-3B/7B/14B) and on tool-calling with rule-based constraints (Qwen2.5-1.5B/3B). RVPO improves overall scores on HealthBench (0.254 vs. 0.207 for GDPO at 14B, averaged across five training seeds). RVPO also maintains competitive accuracy on GPQA-Diamond while reducing late-stage degradation observed in other multi-reward methods.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37883

fastC-GC and fastC-GC*: Efficient RCCP-Guided Graph Estimation for Time Series

S. A. Adedayo

原文摘要

We introduce fastC-GC and fastC-GC$^*$, computationally efficient methods for time-series graph estimation using the two-test rule motivated by Reichenbach's common cause principle (RCCP) and the conditioning sets of causalised Granger causality (c-GC and c-GC$^*$). The methods use standardized data, ridge-residual correlation, and complete circular shift enumeration evaluated by Fourier transforms. Shared precision calculations and Schur downdates avoid repeated regression fits. On a single-threaded benchmark, fastC-GC was 68-277 times faster than the compared c-GC implementation, and fastC-GC$^*$ was 192-886 times faster than c-GC$^*$. Across four suites with reference graphs, aggregate mean area under the precision-recall curve (AUPRC) differed from the corresponding baseline by at most 0.019, but F1 was lower at the selected thresholds in every suite. The computational gains therefore accompany a change in estimator and selected graphs. Among eight methods, Bagged PCMCI+ had the highest mean AUPRC on sparse VAR, an autocorrelated structural process, and DREAM3; CUTS+ led on Lorenz-96. Wind-tunnel and river-discharge applications illustrate differences between inferred graphs without establishing causal accuracy. We prove the computational identities and a restricted population adjacency result for fastC-GC$^*$. Causal interpretation requires the stated graphical assumptions; validity of the implemented tests additionally requires a suitable shift-invariant null law. Empirical null rejection rates informed the conditional threshold $β= 0.005$, without establishing general test validity or graph-wide error control.

stat.CO · cs.SI · econ.EM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37882

FYC: FPR-Disparity Weight Perturbation and Youden Calibration for Fair Deepfake Detection

Uzoamaka Ezeakunne, Taiwo Olabamipe, Deevesh Jain, Xiuwen Liu

原文摘要

Deepfake detectors routinely achieve high aggregate accuracy while exhibiting substantial demographic disparities in their errors: false-positive rates differ by double digits across gender and skin tone. Most existing remedies require either full retraining with a fairness-aware objective or demographic-annotated training data, both impractical when only a pretrained checkpoint is available, while label-free post-hoc calibrators leave the detector's weights unchanged. We introduce FYC (FPR-disparity Weight Perturbation and Youden Calibration), a two-stage post-hoc method that perturbs a detector's weights under an FPR-disparity criterion, then calibrates a separate decision threshold for each demographic group - requiring no architectural changes and no full retraining. Evaluated against every detector benchmarked on AI-Face v2 across six intersectional gender x skin-tone groups, FYC outperforms the field on 18 of 21 reported fairness and utility metrics, including purpose-built fairness architectures, at a fraction of the training cost. We further identify why the choice of fairness criterion is critical: the original Demographic Parity objective used in prior weight-perturbation work is architecture-dependent and unpredictable, improving two of four evaluated architectures, leaving a third largely unchanged, and substantially degrading the fourth (PG-FDD), with no way to anticipate the outcome for a given checkpoint in advance. Conditioning the same objective on real images only - our FPR-disparity criterion - eliminates this unpredictability, improving fairness and accuracy jointly across all four architectures with no exceptions.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37881

Intersectional Invariant Learning for Fair Deepfake Detection

Uzoamaka Ezeakunne, Taiwo Olabamipe, Deevesh Jain, Xiuwen Liu

原文摘要

Deepfake detection models achieve high overall accuracy but exhibit large performance disparities across demographic groups, causing some groups to experience substantially higher false-positive rates than others. Existing fairness-aware methods address this by constraining model outputs to equalize group predictions, but do not tackle the underlying feature-level bias. As a result, models may still rely on demographic characteristics, such as skin texture, as indirect cues for detecting manipulated content. To address this problem, we propose Intersectional Invariant Learning (IIL), a framework that improves feature learning rather than only adjusting model outputs. IIL alternates between identifying the most challenging demographic partitions and learning features that remain consistent across those partitions. The framework also includes a false-positive-rate fairness objective and group-balanced sampling across six gender x skin-tone intersectional groups. We evaluate IIL on a large-scale fairness benchmark containing over one million images, 10 baseline detectors, and 21 fairness and utility metrics. Results show that IIL achieves Pareto-optimal performance, simultaneously attaining an AUC above 99%, a false-positive rate under 2.5%, and the lowest intersectional fairness disparity (FMEO) among all compared methods. IIL outperforms prior fairness-aware methods on the large majority of the 21 evaluation metrics, while reducing both false-positive rates and intersectional fairness disparities by several-fold compared with the strongest competing method.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37880

Interpretable neural equation learning for high-dimensional materials data

Philip Jacobson, Prasad Iyer, Remi Dingreville, Saaketh Desai

原文摘要

Equation learning seeks to discover compact, interpretable equations from data using various machine-learning techniques. However, few workflows discover and interpret learned equations in sparse, high-dimensional materials datasets. We present nn-EQL, an equation-learning framework that generates candidate equations through iterative training, pruning, and retraining of a neural network with customizable, user-specified neuron-level activation functions. Candidate equations are ranked using a minimum description length (MDL)-inspired score, balancing error and sparsity, and diagnosed to assess term-wise contributions, input-scaled sensitivities, and uncertainties. We demonstrate nn-EQL on standard AI-Feynman benchmarks as well as multiscale high-dimensional materials datasets such as finite-element simulations of heterogeneous materials, and high-throughput experimental thin-film deposition data. nn-EQL integrates with tabular data and high-dimensional data via standard encoder models, learning equations and providing insight into learned terms. Looking forward, integrating physically interpretable representations, multimodal and multi-fidelity data, and adaptive data acquisition could enable equation learning to formulate and test mechanistic hypotheses.

cs.LG · cond-mat.mtrl-sci

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37875

Verification Learning Theory: A Process Model of Checking and Retention in AI-Assisted Judgment

Christoph Trattner

原文摘要

Accurate AI assistance can improve immediate judgments while reducing opportunities to practise the operations needed for independent performance. Verification Learning Theory (VLT) formalises this possibility for claim-evaluation practice followed by correct, independent, rule-specific feedback. The model links perceived assistant reliability to evidence checking and links the history of those checks to retained rule use. Its strict form assumes that task demands and perceived reliability influence learning only through checking, with equal learning per genuine check. It therefore predicts that perceived fallibility can improve delayed unaided judgment even without observed assistant errors, and that this advantage disappears when checking is already required and performed. Rule-specific gains and forecasts from checking histories provide further tests. Simulations examine the consequences and parameter dependence of these commitments; they do not constitute empirical validation. Comparisons with depth-of-processing and feedback-encoding accounts identify where predictions diverge and where the accounts remain observationally equivalent. The framework specifies experiments that can test the proposed mechanism and separates retention of practised rules from the broader problem of recognising which rule applies to a new claim.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37874

PairCLIP-SWA: Similarity-Guided Balancing and Stochastic Weight Averaging for Generalized Deepfake Image Detection with OpenCLIP

Md. Nakib, Sudipto Sarkar, A. J. A. Jubayer Talukder, Mohammad Ariful Haque

原文摘要

Deepfake detectors are almost always deployed as the single checkpoint that scored best on a validation split, yet the reliability of that choice is rarely measured. We measure it with PairCLIP-SWA, a single-backbone detector that adapts an OpenCLIP ViT-L/14 visual tower by progressive block unfreezing on a class-balanced corpus built by CLIP-similarity-guided one-to-one subsampling, and averages the fine-tuning trajectory in weight space. Trained in-domain on the IEEE SP Cup 2025 (DF-Wild-Cup) benchmark under the same protocol as the strongest published three-backbone ensemble, the weight-averaged detector reaches 97.04% accuracy, 98.64% AU-ROC and a 4.07% equal error rate, against 94.46%, 97.60% and 5.00%. Its training log shows why averaging matters: over the averaged epochs the non-averaged checkpoint swings across 5.34 points of validation accuracy while its validation loss more than doubles, whereas the average is never worse and is up to 5.99 points better. On an OpenForensics-derived benchmark the same instability becomes a misranking: the checkpoint that validation accuracy selects (98.43%) scores 88.85% on a disjoint 10,905-image test partition, rejecting 21.1% of genuine photographs, while the terminal average, ranked last on validation, scores 94.76%. A study of twenty-two in-house configurations on the identical DF-Wild-Cup split, including preprocessing ablations, shows that CLIP pre-training rather than ensembling drives accuracy, that secondary face cropping costs about 34 points, and that frequency-domain inputs transfer poorly. We recommend per-class selection criteria measured off the early-stopping split.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.27562

VidParse: Online Parsing of Egocentric Procedures Like a Pro

Anubhav Gupta, Archit Kambhamettu, Vatsal Agarwal, Pulkit Kumar, Abhinav Shrivastava

原文摘要

Translating continuous, noisy egocentric video streams into discrete, temporally ordered action steps is fraught with visual challenges. Heavy ego-motion, transient occlusions, and the high intra-class variability of unscripted human-object interactions cause standard frame-level online temporal models to struggle, often resulting in severe over-segmentation and structural collapse. To bridge the gap between unstable low-level perception and high-level procedural logic, we present VidParse, an online, training-free framework that treats activity understanding as a graph-constrained inference problem. Rather than relying on learned temporal filters, we dynamically identify semantic transitions using a temporal similarity matrix over manipulation-anchored features, which are extracted from frozen foundation models to prioritize foreground hand-object interactions. A beam search decoder then leverages an induced procedural task graph to explicitly enforce valid action transitions and prune impossible trajectories. By anchoring robust visual segments to hard procedural constraints, our approach preserves long-range state transitions and achieves up to a 10x improvement in complex multi-step parsing accuracy over strong online baselines, all without requiring a single gradient update.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37872

Set an Exploit to Catch an Exploit: Compiling Public Proofs of Concept into Threat Hunting Rules

Muhammad Shoaib, Alexander Suh, Joshua Andrew Tomiak, Wajih Ul Hassan

原文摘要

Public exploit code for a newly disclosed vulnerability usually appears before any published rule that detects its exploitation. Of the 45 CVEs we evaluate, 37 ever received a Sigma, Elastic or Splunk rule; in 33 the exploit came first, by a median of 22 days. Analysts still write every rule by hand. We present Encore, which compiles a public Python proof-of-concept exploit (PoC) into CVE-specific hunting rules over a web service's existing logs, without running it. Encore rests on the PoC Behavior Alignment Principle: a PoC performs the exploit, so its code already provides a rule's HTTP requests, payloads and host operations. That is hard to act on: a PoC is written against libraries and runs on the attacker's machine, while the target's web-server, proxy and host logs record only what arrived and what it did. Encore closes the gap with a map from library calls to the operations they cause, built once per library, keeping only the operations visible on the target. For 12 of the 45, Encore's rule states the exploit's own payload fragment or host operation, which is evidence of the exploit itself, and not of traffic to its endpoint. On matched controls it separates that exploit from the same request with a harmless value, and it raises no alerts across 27,081 legitimate and crawl requests. We never compile the exploit that produced the logs. Most are Splunk's public attack data, recorded by a third party. Without reading a single log, Encore's rules find 43 of the 45. Splunk's log-tested rules cover 30 of the 45, and Encore finds 28 of those, plus all 10 CVEs without an ESCU rule. Where Splunk's rules alert on 20 wrong CVE pairs, Encore's alert on only 2. Hunting can start as soon as a PoC is public, and rules can raise an alert when it provides a payload or host operation.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37871

ICALL-BENCH: Benchmarking LLM Interprocedural Reasoning in Binary Programs

Shenglong Yao, Zirui Liu, Xiangchi Yuan, Wenke Lee

原文摘要

Recent benchmarks show that LLMs achieve strong performance in both function-level binary understanding and end-to-end binary reverse engineering tasks, but whether LLMs can reason over interprocedural semantics in compiled binaries remains unclear. Function-level benchmarks offer limited visibility into cross-function relationships, while whole-program benchmarks typically evaluate final outcomes of tasks that may be solvable from local clues alone, making it difficult to disentangle interprocedural reasoning from exploration, tool use, execution, and retrieval. To address this limitation, we introduce ICALL-BENCH, a benchmark that directly evaluates whether LLMs and agents can understand and reason over interprocedural semantics in binary programs, using indirect-call target recovery as a measurable probe. ICALL-BENCH covers 50 complete real-world C/C++ programs spanning different complexity levels and multiple optimization configurations, with an average of 74,746 lines of code and 941 functions per program. We further introduce three analysis regimes spanning model-only reasoning, static tool-augmented agents, and Internet-enabled open-world agents to examine how intrinsic reasoning, active information acquisition, and external knowledge each contribute to interprocedural binary analysis. We evaluate five recent LLMs and their corresponding agents. Our results reveal a wide separation across current models and agents, with program-level verifiable success rates ranging from 23% to 81%. They also show that greater information access does not consistently lead to better results, with particularly limited gains on the hardest cases, where deeper interprocedural reasoning remains the primary bottleneck. Uneven performance across models and frequent verifiable failures even under an optimistic evaluation indicate that robust binary interprocedural reasoning remains an open challenge.

cs.SE · cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2512.02436

Agentic AI for Clustering and Relationship Discovery in Prediction Markets

Agostino Capponi, Alfio Gliozzo, Brian Zhu

原文摘要

Prediction market platforms list thousands of contracts whose logical and economic connections are implicit in their resolution rules. We introduce a hierarchical agentic reduction (HAR) pipeline for constructing inspectable cross-event relation graphs and a behavioral benchmark for evaluating their alignment with market prices. This partitions a catalog of prediction markets, specified by question and resolution text, into topic clusters, applies typed LLM reasoning to small batches, and proposes signed relations with rationales between specific markets. We evaluate semantic relation graphs spanning eight monthly Kalshi catalogs (February to September 2026). Using data from 30.3 million trades, we compute a benchmark that compares linked pairs' signed price-change correlations with those of matched, unlinked controls from the same topic cluster on identical timestamps. Under full-sample and leave-first-week-out evaluation, relations identified by our pipeline exhibit higher signed Pearson price-change correlations, with statistical significance, than matched within-topic controls. This increase also appears under Spearman correlation and becomes larger among relations labeled as medium or high strength. This benchmark provides a criterion for comparing relation-discovery methods against observations beyond their input text, and our results indicate the ability of agentic AI and LLM reasoning to identify meaningful relations between individual markets in connected Web marketplaces.

cs.AI

查看论文
arXiv ↗PDF ↗