跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 04:04 — 2026-11-22 04:04(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

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 21,490 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
新论文 · v1arXiv:2611.21852

The Hidden Cost of MoE Diffusion Decoding: Profiling and Fixing the Sampler

Harshit Samrat, Ramakrishna Paramahamsa Kompella

原文摘要

Masked diffusion language models (dLLMs) decode by iteratively denoising a full canvas of tokens, so every forward pass runs a per-token sampling and stopping pipeline over the entire canvas-by-vocabulary logits tensor. We profile single-user decoding of a 26B-parameter diffusion Mixture-of-Experts model on a bandwidth-bound edge accelerator (NVIDIA GB10) and report a result that is easy to miss: after weight quantisation, this logits pipeline, not the expert GEMMs, is the single largest consumer of decode time. Unlike autoregressive decoding, where sampling touches one position's logits per committed token, diffusion decoding processes S times as many logit entries per output token, where S is the number of denoising steps. We show this pipeline is largely redundant or fusable and remove it in two lossless tiers: a bit-exact tier whose output is byte-identical to the reference decoder, and an accuracy-parity tier using a fused single-pass entropy kernel and Gumbel-max sampling. Combined with a W4A16 expert kernel, the full stack reaches 2.4-2.7 times end-to-end speedup over bf16 at unchanged benchmark accuracy on GSM8K, HumanEval, and MATH, on a single 273 GB/s device. We confirm the finding on a second, independently built diffusion MoE (LLaDA2.0-mini: pipeline 28.8% of decode, fused W4A16 3.3 times at accuracy parity) and show it disappears on a dense diffusion model (3.6%). The cost is specific to MoE diffusion, where quantisation makes the backbone cheap. Code and quantised weights are released.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.21851

AR-WAM: efficient streaming world-action modeling for autonomous driving

Baiting Luo, Shatadal Mishra, Ahmadreza Moradipari, Nejib Ammar

原文摘要

Autonomous driving requires anticipating how traffic will evolve while responding quickly to new observations. Video foundation models offer the first ability, but repeated history encoding and iterative video generation make them costly to use for driving. We present AR-WAM, an efficient streaming world-action model that combines autoregressive temporal modeling with single-pass future conditioning. Because its video backbone is causal, AR-WAM updates its visual context incrementally, reusing past computation and conditioning future prediction on observed motion. We further hypothesize that future features computed from recent observations can improve generalization in dynamic traffic without iterative video generation. AR-WAM therefore obtains these features in one forward pass and uses them to condition trajectory generation, and reinforcement learning then improves the policy through direct optimization of driving rewards. With a single front camera, AR-WAM achieves 91.5 PDMS after supervised training and 94.0 after reinforcement learning on NAVSIM-v1, outperforming the compared strong end-to-end world-action models. In a dynamic setting of continuous driving, supervised AR-WAM keeps its visual history across decisions and outperforms strong world-action baselines.

cs.CV · cs.AI · cs.RO

版本更新 · v2arXiv:2605.22631

HolisticMotion: Holistic Modeling for Motion Reconstruction from Sparse Tracking

Runzhen Liu, Chuhua Xian, Hongmin Cai, Fa-Ting Hong

原文摘要

Reconstructing full-body motion from sparse tracking signals is crucial for immersive AR/VR applications. Existing methods predominantly adopt a sensor-centric observation perspective, learning full-body representations primarily under sparse conditioning, while additional joint observations available during training remain underutilized as inputs. We propose HolisticMotion, which shifts the modeling perspective toward holistic full-body modeling by treating every joint as a potential input source within a unified skeletal layout. Guided by this holistic perspective, we introduce three complementary designs. First, a curriculum masking strategy bridges full-body motion learning and sparse inference by gradually shifting training from a mixture of masked full-body and sparse inputs to exclusively sparse inputs. Second, body partitioning models region dynamics and helps preserve local motion cues. Third, Kinematic Attention coordinates body regions by combining dynamic spatial interactions with learnable structural priors inspired by the kinematic tree. Experiments on AMASS and HPS demonstrate competitive reconstruction performance across various tracking protocols, with the lowest positional errors among the compared methods. The unified representation also accommodates additional wearable sensors, yielding further improvements in reconstruction accuracy and motion smoothness.

cs.CV

版本更新 · v2arXiv:2608.26416

IoMT-SecAlarmBench: A Semi-Synthetic Counterfactual Benchmark for Integrity Attacks in IoMT

Emmanuel C. Ugwuabonyi, Dmitri Perkins

原文摘要

The Internet of Medical Things (IoMT) combines clinical physiological data with cyber-system information, creating challenges in determining whether an abnormal reading reflects a genuine physiological event, a device fault, or a cyber-attack within the expected physiological range. Answering this requires counterfactual ground truth, which no existing dataset provides. We present IoMT-SecAlarmBench, a semi-synthetic benchmark that injects controlled integrity attacks into genuine coupled ECG+PPG recordings using a structured experimental design combining four attack morphologies, four severity levels, two physiological plausibility conditions, and replay attacks. Each injected window retains its cause, attack subtype, and the clean signal that would have been observed without the attack. We evaluate six detectors from five method families using threshold-independent measures and a matched false-alarm budget. Results show no method consistently detects the most difficult cases: replay attacks and low-amplitude transient spikes remain close to chance-level performance across detectors. Results also reveal a trade-off between detecting attacks and distinguishing them from sensor faults: the best-performing detector on hard cases flags fault/artifact windows at 5.3 times its false-alarm rate on normal data. Three-way classification performs poorly for genuine physiological events, and a leakage audit of a dual-modality network dataset indicates previously reported IoMT intrusion-detection performance is partly driven by identifying information. Benchmark, generation code, preprocessing, evaluation tools, and datasheet are released.

cs.CR

新论文 · v1arXiv:2611.21847

Inventa: Decentralized Self-Improving Agents for Autonomous Scientific Discovery

Prithwish Jana, Nikos Kanakaris, Purak Jain, Anoop Deoras, Sahika Genc

原文摘要

Large language model (LLM) agents can generate research ideas and improve scientific discovery through iterative experimentation. However, increasing the number of agents or iterations does not automatically translate to producing more diverse or feasible ideas. Agents may converge on similar candidates, propagate unsupported claims through shared memory components and repeatedly apply search strategies that no longer yield any improvements. We introduce Inventa, a framework for automated scientific discovery that employs autonomous research units and verified shared knowledge. Each unit creates a lineage of candidate ideas using a mutator agent. A local orchestrator agent periodically adapts the mutator's harness. When progress stalls, the orchestrator agent replaces its model or restarts the idea evolution process. Verifiers evaluate each candidate idea and record verified improvements, useful components and constraint violations in a shared knowledge, the only channel between units. We evaluate Inventa on five benchmarks spanning the research cycle, covering retrieval (ScholarCatalyst), ideation (IdeaBench), proposal writing (IdeaScientist), and scientific law discovery (EurekaBench, SciLaws-Bench). It leads all five, achieving 73.6% on EurekaBench versus 56.2% for CORAL. On IdeaBench, it discovers 26.0 novel ideas per paper, compared with 18.6 for ResearchAgent, with 82% fewer model calls.

cs.LG · cs.AI

新论文 · v1arXiv:2611.21844

Bias-Reduced and Parallel Heavy-Tailed Stochastic Convex Optimization in $\ell_p$ Geometries

Zhengyun Nie, Anant Shyam, Brian Bullins

原文摘要

We consider the fundamental problem of parallel stochastic convex optimization (SCO), whose aim is to approximately minimize a convex objective when given the ability to query a moment-bounded stochastic gradient oracle multiple times in parallel per round. Whereas most previous results have focused on the variance-bounded Euclidean ($\ell_2$-norm) setting, meaning the objective is Lipschitz with respect to the $\ell_2$-norm over an $\ell_2$-bounded feasible set in $\mathbb{R}^d$, in this work we study parallel SCO in $\ell_p$ settings for $2 \le p < \infty$ under a heavy-tailed noise model. We begin by introducing a new class of $\ell_p$-optimal-distance-convergence (ODC$_p$) algorithms, drawing on prior stochastic bias-reduced techniques [ACJ+21], which combine with multilevel Monte Carlo methods to efficiently estimate the optimum of uniformly convex objectives. As a consequence of our ODC$_p$ algorithms, we first establish rates for projection-efficient $\ell_p$-Lipschitz optimization, composite convex minimization, and efficient $\ell_p$-proximal point estimation. Combining our ODC$_p$ algorithms with a new $\ell_p$-generalized Gaussian-based stochastic gradient estimator ($p$-GREG), we provide two efficient $\ell_p$ parallel algorithms, EpochDA and $\ell_p$-AC-SA, which achieve optimization error $ε> 0$ with at most $\tilde{O}(d^{\frac{p}{2p + 2}} ε^{-\frac{p}{p + 1}})$ query depth, improving upon the sequential heavy-tailed stochastic query depth of $O(ε^{-p})$ for $ε\leq \tilde{O}(d^{-1/(2p)})$. We also establish dimension-dependent lower bounds of $Ω\bigl(\min\{ε^{-p},d^{p/(3p-2)}\}\bigr)$ adaptive rounds for nonsmooth convex optimization over a subset of the unit $\ell_p$ ball. Our results improve upon the $Ω(\min\{ε^{-p},ε^{2/3}d^{1/3}\})$ bounds of [DG19], when adapted to the same feasible set.

math.OC · cs.LG · stat.ML

新论文 · v1arXiv:2611.23331

What Should an LLM Know? Knowledge-Guided Warm Starts for Software Optimization

Srinath Srinivasan, Tim Menzies

原文摘要

Large language models (LLMs) process gigabytes in minutes; human experts work far more slowly. Prior studies that explored combinations of human/AI optimizers ignore this gap. Those studies asked systems or humans to label too many examples (e.g., SynthCore needs over four dozen per trial). Here, we test human and AI knowledge under a budget where evaluation is practical (a few dozen labels or fewer). We compare five baselines (random search, RRP, EZR, few-shot prompting, and a budget-matched SynthCore variant) against three ways to give an LLM domain knowledge before it proposes its first configurations: (1) AMP lists the domain's rules, then checks each candidate against them; (2) HKMA adds scouted data or documentation to the prompt; and (3) H-DKP has human experts correct the LLM's rules. We find that domain knowledge improves the "start-up" phase of LLM optimization, but only when that knowledge is checked, by the LLM itself or by a human expert. Across 49 datasets, unchecked knowledge did no better than few-shot prompting or EZR. On the other hand, AMP's self-checking variant (AMP-4) reached the best statistical rank in 44 of 49 datasets (budget-matched SynthCore: 23 of 49), and H-DKP did so in 7 of 8 expert studies. These checks cost little: half a cent of LLM calls per trial, or 6 to 10 expert contacts. Hence we say LLMs may not need more data, but rather their knowledge needs checking (and checking is cheap).

cs.SE

版本更新 · v2arXiv:2610.02405

When Terminal-Agent Training Stalls: Demystifying Data Generation and Verification Challenge

Xi Qin, Isabel Kurth, Xin Cui, Elin Park, Alexander Schaefer, Yaad Oren

原文摘要

Automated terminal-agent training relies on generated environments and verifiers to turn open-ended interaction into reward. Yet a runnable Docker image and executable test suite do not guarantee that the resulting reward is faithful, informative, or even attributable to agent behavior. We present a pipeline that generates containerized terminal tasks and their executable verifiers, and use it to demystify failure modes in task generation and live-environment evaluation. Our analysis separates four requirements that are often conflated: structural validity, verifier faithfulness, policy solvability, and infrastructure reliability. In a GRPO training of Qwen3.5-9B, it overfits on a relatively easy dataset within 20 steps. Conversely, in a controlled Qwen3.5-9B comparison, adding hard tasks lowers mean rollout pass@2 from 81.3% to 20.6%, restoring informative failures without changing the training configuration. We further identify near-duplicate task generation, incomplete anti-shortcut safeguards, Dockerfile failures, asynchronous pass@k bias, and concurrency-induced environment errors as distinct threats to measurement. These findings should motivate the community for a terminal agent specific evaluation harness that pairs structural checks and rollout-derived solvability with extensive verifier audits.

cs.AI

新论文 · v1arXiv:2611.21839

VisHead-Spec: Head-Routed Visual Attention for Multimodal Speculative Decoding

Xin Guo, Arushi Rai, Xiang Zhou, Qiang Zhang, Siyu Lin, Xiangjun Fan, Lizhu Zhang

原文摘要

Speculative decoding accelerates vision-language models(VLMs) while preserving the target model's outputs, but its speedup diminishes under high concurrency serving as the system becomes more compute bounded as the batch size increases. This problem is pronounced for multimodal speculative decoding as the long range of the image tokens in the prompt can significantly increase the computational cost during draft token prediction. The block-diffusion drafters (e.g. DFlash, DSpark) can effectively speed up the draft model efficiency by predicting multiple draft tokens in one forward pass, but their speedup for VLMs under high concurrency is still modest (<9%). In order to understand this gap, we examine the information flow between different modalities from target model to draft model and identify the sparsity pattern of visual attention between the target and draft models: only small set of key-value heads in the draft model need direct visual feature attention in the context and only visual features from top level layers in the target model need to be attended in the context. We therefore propose VisHead-Spec, which selects a small, fixed set of key-value (KV) heads to attend to all image features from top level layers in the target model and restricts the remaining heads to text features. On Qwen3-VL-8B and MMSpec, VisHead-Spec-8 lets 8 of the drafter's 40 KV heads read the image while keeping accepted length within 0.3% of the block-diffusion draft model baseline (i.e. DSpark). At batch size 64, its throughput gain over autoregressive decoding increases to 16.0%, compared with 9.5% for DSpark; at batch size 1, its speedup remains comparable to DSpark.

cs.LG · cs.CV

版本更新 · v3arXiv:2610.05792

DASH: A da Vinci Adapter for Serial-link and Humanoid Robots as an Accessible Platform for Surgical Robotics Research

Sara Wickenhiser, Junrong Zhou, Zekai Liang, Lizzie Peiros, Liu Shanglei, Michael C. Yip

原文摘要

Robotic minimally invasive surgery offers well-documented clinical benefits, but the cost and infrastructure requirements of purpose-built platforms limit access in rural and lower-resourced facilities. Recent work has teleoperated general-purpose robots for laparoscopic tasks and in vivo procedures, but relied on handheld instruments coupled through passive linkages rather than native robotic actuation. Instead, we adapt da Vinci Classic and Xi instruments onto general-purpose robots that can integrate in clinical workflows. We present DASH, a da Vinci Adapter for Serial-link and Humanoid platforms, consisting of two types of adapters that require no modification to the instruments themselves. Each adapter is compatible with many robotic platform load capacities, engages the instrument's native latch, and wirelessly identifies inserted tools to load instrument-specific kinematics and coupling matrices. Teleoperated experiments demonstrate the efficacy of DASH and its benefits for enabling research access to surgical robotic platforms. DASH has been open sourced at https://github.com/sarawickenhiser/DASH_open_source.

cs.RO

版本更新 · v2arXiv:2611.08681

National and State-Level Approaches to Automated Vehicle Certification: A Comparative Framework for State Operational Governance

Sk Nahia Ahsan, Md Abdullah Al Hasan, Danjue Chen, George List

原文摘要

Automated vehicle (AV) deployment in the United States is expanding without a unified federal certification framework, leading to substantial variation in how states authorize and oversee AV testing and deployment. This paper examines how U.S. states regulate Society of Automotive Engineers (SAE) Level 4-5 automated driving systems (ADS), identifies common certification approaches, compares them with international practices, and evaluates the implications for North Carolina's future regulatory strategy. Publicly available state statutes, administrative regulations, agency guidance, and federal policy documents were reviewed. Ten states, selected to capture the range of regulatory approaches, were analyzed using a structured framework covering operational scope, governance and oversight, federal interaction, and implementation outcomes. Certification practices in the European Union, China, Japan, and Australia were reviewed for comparative context. Three state certification models were identified, reflecting increasing regulatory involvement: baseline legal compliance, administrative self-certification with ongoing oversight, and permit-based authorization requiring formal agency review before deployment. North Carolina currently aligns with the baseline compliance model. International frameworks are converging toward scenario-based testing, operational-design-domain-specific approval, safety-case documentation, cybersecurity assurance, and lifecycle oversight, although direct transferability to the U.S. is limited. The paper develops a three-model typology for comparing state AV certification approaches and integrates state practices with international frameworks, providing a consistent basis for evaluating differences in regulatory involvement, governance complexity, and institutional responsibilities across jurisdictions.

cs.RO · cs.SE

版本更新 · v2arXiv:2606.17541

Offline Preference-Based Trajectory Evaluation

Fernando Diaz

原文摘要

Offline evaluation of agentic systems often collapses trajectories into a binary terminal success value, discarding information about partial progress. This, in turn, results in widespread ties that create statistical inefficiency by reducing effective sample size and weakening the ability to distinguish systems. We propose preference-based trajectory evaluation, an evaluation measure that compares pairs of trajectories directly by using temporal preferences between time-to-return profiles. We find that, across diverse agentic and interactive benchmarks, success-based metrics result in tied comparisons on roughly 75% of instances, while trajectory-aware preferences reduce ties to roughly 35%, improving discriminative power, ranking stability, and data efficiency. Our results suggest that benchmark saturation, often portrayed as the result of poor data collection or problem difficulty, may also be explained by the design of the evaluation measure.

cs.LG · cs.AI

新论文 · v1arXiv:2611.21828

Coordination of Heterogeneous Teams with Uncertain Task Requirements

Jongann Lee, Melkior Ornik

原文摘要

Coordinating a team of heterogeneous agents to complete tasks with unknown requirements is a challenging multi-agent planning problem. Agents differ in their ability to discover task requirements and in their ability to engage tasks, so the planner must coordinate task discovery, execution, and staging. This paper introduces a hierarchical planner that uses a graph neural network policy to assign actions to agents, then finds a path to the action's location using a shortest-path algorithm. The central part of our approach is the CAAT graph, which is a graph representation of the planning context consisting of the agents, tasks, capabilities, and actions. We demonstrate that our learned planner can jointly coordinate a heterogeneous team to simultaneously discover task requirements and complete tasks in a shorter time compared to baselines that optimize task discovery and task engagement independently. Furthermore, we show that our policy can zero-shot plan on out-of-distribution settings by training only on an outdoor map then transferring without finetuning to an indoor map with more agents, tasks, and capabilities than seen during training.

cs.MA · cs.AI · cs.LG

版本更新 · v2arXiv:2607.22697

Test-Time Coverage: Test-Conditioned Data Curation for Deployment-Aware Learning

Nadine Chang, Maying Shen, Shizhe Diao, Jialiang Wang, Jingde Chen, Thomas Breuel, Pavlo Molchanov, Rafid Mahmood 等 9 位作者

原文摘要

Deployed AI systems are often trained from broad candidate data pools, necessitating data curation towards the deployment test distribution. However, standard data curation methods score training-side criteria rather than directly optimizing deployment match. We introduce TTCov (Test-Time Coverage), a data-level test-conditioned curation method that uses test-side information before training instead of updating model weights at inference. TTCov decomposes deployment-conditioned curation into coverage and distribution. To represent coverage, it builds a task Atlas, a collection of LLM-based atomic propositions (APs) describing deployment-relevant concepts, seeded from open task knowledge and expanded with unmatched APs extracted from unlabeled deployment samples. To represent distribution, it instantiates the matched deployment APs with their frequencies, yielding a Knowledge Atlas (K-Atlas) that operationalizes the deployment distribution as a curation target. TTCov then selects a budgeted training set whose deployment APs distribution approximates this target. We apply TTCov towards autonomous driving (AD), keeping adaptation off the inference path while selecting data with greater deployment-relevant coverage, closer K-Atlas matching, and stronger downstream end-to-end driving performance than data-curation baselines, including seamless adaptability to novel domains via city-to-city expansion. Code available at https://github.com/NVlabs/TTCov.

cs.AI · cs.CV · cs.LG

新论文 · v1arXiv:2611.21824

ASCEND: Automated Shockproof Cost-Efficient Network Design

Taha ValizadehAslani, Vaibhav Phatarpekar, Cameron Brackmann, Bala Ramachandran

原文摘要

Designing resilient and cost-effective IP network topologies over an existing physical infrastructure is a challenging combinatorial optimization problem, particularly at large scale and under extensive failure modeling assumptions. Traditional deterministic approaches struggle to jointly address resiliency against shock (large customer-impact outages) and implementation cost objectives when the number of candidate circuits grows quadratically with the number of sites to be interconnected. In this paper, we propose Automated Shockproof Cost-Efficient Network Design (ASCEND), a systematic design pipeline for IP core network optimization based on a two-level optimization framework. At the outer level, ASCEND uses Multi-Objective Particle Swarm Optimization (MOPSO) to select core sites and core circuits. Given a core design, the inner-level integral Multi-Commodity Flow (MCF) formulation selects edge circuits and maps both core and edge circuits onto optical (fiber/transport) paths while prioritizing resource disjointness and latency. Network designs are evaluated using two competing objectives: a performance cost capturing resiliency under probabilistic failure scenarios and an implementation cost. The performance cost incorporates an exponentially weighted vulnerability metric that explicitly penalizes infeasible configurations. Experimental results on multiple real-world networks demonstrate that ASCEND consistently identifies designs that outperform a manually engineered baseline in both resiliency and implementation cost.

cs.NI

新论文 · v1arXiv:2611.21823

TUSI: A Citation-Grounded Graph-Based Benchmark

Marzieh Karimi, Mehran Safayani, Alireza Basiri

原文摘要

Evaluating retrieval-augmented generation (RAG) systems in Persian law remains challenging because benchmarks lack realism, grounding, and coverage of legal reasoning. Existing resources are either synthetically generated from statutory texts, lacking natural information needs, or derived from informal legal question--answer sources without explicit linkage to authoritative legal documents, making them unsuitable for rigorous evaluation of grounded legal reasoning. To address this gap, we introduce TUSI-Bench, a structured Persian legal benchmark designed for the evaluation of RAG-based systems. TUSI-Bench is built upon a multi-layered legal knowledge framework containing 7,261 legal articles and integrating codified statutes, legal commentaries, doctrinal writings, and Supreme Court unification rulings. We also construct a legal knowledge graph linking articles and concepts for structure-aware retrieval. Based on this foundation, TUSI-Bench provides two complementary evaluation tasks: (i) TUSI-QA, an open-ended question answering benchmark containing 1,999 questions that requires grounded responses with explicit legal citations, and (ii) TUSI-Bar, a multiple-choice benchmark containing approximately 500 four-option questions derived from Iranian Bar examination questions. Furthermore, we propose a graph-based retrieval baseline that leverages relational structure within the legal knowledge graph. Experimental results demonstrate that incorporating graph-based relations improves retrieval recall by up to 8 percentage points compared to standard baselines, highlighting the importance of structured legal representations for RAG systems. The proposed benchmark provides a standardized resource for evaluating grounded legal reasoning in Persian and enables future research on structured legal intelligence.

cs.CL · cs.AI

新论文 · v1arXiv:2611.21822

Threat Landscape of Vibe Coding and the Road to Secure Autonomy

Devki Nandan Jha, Shubh Anand, Karthick Keeranagere Krishnaiah, Roman Ahearn, Suhas Nale

原文摘要

Vibe coding is reshaping software development, enabling faster implementation and allowing individuals with limited programming experience to describe requirements in natural language while AI agents write, test, and deploy the code. As these agents evolve into autonomous systems that execute commands, manage dependencies, access cloud resources, and interact with other agents, their security risks extend beyond incorrect code to actions with direct consequences for software systems. Although research on these risks is expanding, it remains fragmented across areas including prompt injection, insecure code generation, supply-chain attacks, and human factors, with limited consensus on terminology, threat assumptions, and evaluation. This paper consolidates emerging research through the lens of the vibe coding workflow. We establish a reference architecture, characterise six levels of agent autonomy, and develop a threat model centred on five trust boundaries spanning developers, AI models, tools, cloud infrastructure, and the wider software ecosystem. Building on this foundation, we propose a taxonomy of twenty-one threats across nine classes. For each threat, we review the available evidence, assess proposed defences, and identify limitations. Our analysis highlights that risks increase with agents' operational authority, while most defences rely on model judgement and address isolated threats. Finally, we identify eleven research challenges, including enforceable limits on agent authority and shared benchmarks and methodologies for assessing vibe coding security.

cs.CR · cs.ET

新论文 · v1arXiv:2611.21816

Rethinking Perceptual Similarity for Remote Sensing: Multi-Layer Attention Scoring and Human Preference Benchmarking

Eli Underwood, Marc Bosch, Neil Joshi, Jeffrey Wen, Myron Brown

原文摘要

Perceptual similarity metrics for natural images transfer poorly to remote sensing (RS), where severe geospatial and semantic failures can remain visually plausible while still being decisively wrong for downstream use. To address this, we develop a novel human-aligned perceptual quality metric for generated RS imagery and evaluate it across several generation tasks. We first conduct a controlled perturbation study where we progressively increase the severity of common synthetic perturbations. Using the layer-wise Aligned Attention Score (AAS) responses in RemoteCLIP, we find that different RS artifacts are best captured at different depths. Based on these findings, we introduce Remote Sensing Perceptual Distance (RSPD), a pairwise metric that averages seven independently calibrated layer distances without tuning on human-preference labels. To evaluate our metric on realistic RS generation tasks, we construct a blind, reference-conditioned two-alternative forced-choice (2AFC) benchmark with five 300-triplet subsets spanning synthetic artifacts, airborne and spaceborne super-resolution, SAR-to-optical translation, and timeseries controls. We also construct a 300-triplet ordered misregistration benchmark with deterministic labels. Using the same RemoteCLIP checkpoint, RSPD substantially outperforms simple cosine distance with the final global embedding and is competitive with the strongest generic baselines across the realistic RS generation tasks.

cs.CV

版本更新 · v2arXiv:2501.09646

NS-Gym: A Comprehensive and Open-Source Simulation Framework for Non-Stationary Markov Decision Processes

Nathaniel S. Keplinger, Baiting Luo, Yunuo Zhang, Kyle Hollins Wray, Aron Laszka, Abhishek Dubey, Ayan Mukhopadhyay

原文摘要

Many real-world applications require decision-making where the environmental dynamics evolve over time. These non-stationary environments pose significant challenges to traditional decision-making models, which typically assume stationary dynamics. Non-stationary Markov decision processes (NS-MDPs) offer a framework to model and solve decision problems under such changing conditions. However, there are no standardized simulation frameworks for NS-MDPs, as opposed to widely popular frameworks for stationary problems. We present NS-Gym, the first simulation toolkit designed explicitly for NS-MDPs, integrated within the popular Gymnasium framework. In NS-Gym, we segregate the evolution of the environmental parameters that characterize non-stationarity from the agent's decision-making module, allowing for modular and flexible adaptations to dynamic environments. We review prior work in this domain and present a toolkit encapsulating key problem characteristics and types in NS-MDPs. This toolkit is the first effort to develop a set of standardized interfaces and benchmark problems to enable consistent and reproducible evaluation of algorithms under non-stationary conditions. We also benchmark several algorithmic approaches from prior work on NS-MDPs using NS-Gym. We envision that NS-Gym will enable researchers to study decision-making under non-stationarity by providing standardized interfaces, simulation frameworks, and benchmark problems. Project documentation, webpage, and code can be found at https://nsgym.io and https://github.com/scope-lab-vu/ns_gym

cs.AI

新论文 · v1arXiv:2611.21814

Newton's Method for CP Decomposition

DuBose Tuller, Grey Ballard, Hussam Al Daas, Nicholas I. M. Gould

原文摘要

We present an algorithm for computing the CP tensor decomposition using Newton's method. The problem of fitting a CP model to a data tensor with least squares loss can be solved by various gradient-based optimization techniques, including Gauss-Newton methods that exploit the tensor structure of the problem and iteratively solve the linear system involving the approximate Hessian matrix to determine the step direction at each iteration. Gauss-Newton methods exhibit superlinear convergence when the residual is small but can otherwise struggle to converge when the approximation to the Hessian is not accurate. We show that the Gauss-Newton approach can be extended to Newton's method, using the true Hessian to obtain fast convergence even in the case of large residuals. In particular, we derive efficient means of applying the true Hessian to vectors for use within an iterative solver, we employ globalization and regularization techniques to make the Newton model robust to ill-conditioned and/or indefinite Hessians, and we propose hybrid use of Gauss-Newton and Newton steps to balance convergence behavior both far and near local minima. Our numerical experiments use synthetic examples to show in which scenarios Gauss-Newton and other methods struggle to converge, and we demonstrate the superiority of the hybrid approach on two application data sets.

cs.MS

版本更新 · v2arXiv:2605.09275

DiffATS: Diffusion in Aligned Tensor Space

Jinhua Lyu, Tianmin Yu, Brian Kim, Lizhuo Zhou, Chanwook Park, Naichen Shi

原文摘要

Direct diffusion modeling of high-resolution spatiotemporal fields is computationally challenging. Parameter-efficient primitives address this by representing high-dimensional data with a compact set of parameters. In this paper, we construct data-dependent tensor primitives without pretrained compression autoencoders. Our construction starts from Tucker decomposition, which captures low-rank multilinear structure through a core tensor and mode-wise factors. However, Tucker factors are non-unique: the same tensor can be represented by different rotated factors, which complicates generative modeling. We address this issue with orthogonal Procrustes (OP) alignment. Specifically, we select medoid anchor matrices from the data and align the factor matrices to resolve the gauge ambiguity. This yields matrix Grassmannian primitives and tensor Grassmannian primitives that are compact, data-adaptive, and directly decodable by explicit multilinear reconstruction. Theoretically, we prove that the proposed primitive maps are homeomorphisms between low-rank tensors and their corresponding primitive spaces, certifying that the representations are non-degenerate and topologically faithful. Building on these primitives, we propose *Diffusion in Aligned Tensor Space* (DiffATS), a generative framework that trains diffusion models directly on aligned tensor primitives. Across images, videos, and PDE solutions, DiffATS achieves strong unconditional and conditional generation performance while compressing original data by $3.9\times$ to $210\times$, without relying on any pretrained deep compression autoencoders.

cs.LG

新论文 · v1arXiv:2611.21812

Sketch, Don't Paint: Allocating Test-Time Compute in Generative Visual Reasoning

Sheng Lu, Guangpin Tao, Tong Lu, Ying Tai

原文摘要

Multimodal models increasingly reason by synthesizing pixels, sketching maze paths within interleaved chains of thought or rolling out video solutions frame by frame. Each visual thought runs the full diffusion schedule inherited from photorealistic synthesis, so iterative denoising dominates inference cost. We study how to allocate test-time compute along two axes: when to render visual thoughts rather than thinking in text or answering directly, and how many denoising steps each thought requires. Controlled interventions that vary only how the thought is rendered uncover three regimes. Causal thoughts carry the plan and become legible early: an 8-step sketch nearly matches a 50-step render in accuracy, commits to the same plan as often as two independent full renders agree, and in video models mostly fails by stalling short of the goal, so the rollout abstains. Decorative thoughts can be omitted without loss, whereas harmful thoughts lower accuracy. Because the regime depends on both model and task, always drawing is suboptimal. Across 14 model-benchmark pairs of three interleaved reasoners, answering directly, without any thinking, wins 9 pairs, and choosing among direct, text-only, and visual tiers from ten labeled examples per pair raises mean accuracy from 60.7% (always drawing) to 65.1%. Where drawing pays, we propose sketch-and-vote, which samples 8-step sketches (a step count chosen without labels) from independent noises until one answer reaches three votes. With this one setting, sketch-and-vote beats full rendering with fewer denoising steps on an image reasoner and two video reasoners, by 8.6 points on VSP spatial planning and by 9.6 and 22.1 points on mazes.

cs.CV

新论文 · v1arXiv:2611.21811

ARC-2: Continuous Compliance Through Delta Management

Tord Johan Eide, Einar Holt

原文摘要

ARC 1 introduced a three-layer governance architecture for autonomous systems comprising model safety validation, cognitive certification (CRAB), and operational authorization (LEA). However, it did not address how compliance should be maintained after deployment. This paper introduces Delta Management, a continuous governance framework that measures deviations between a system's current operational state and its certified baseline, defined as a region rather than a fixed point. Compliance is assessed through continuous monitoring instead of static certification. Four extensions are proposed. First, CRAB evaluation incorporates the worst verified behavioral deviations, with isolated outliers quarantined pending confirmation to prevent unjustified restrictions. Second, a layered trigger taxonomy distinguishes hard safety violations, critical single-dimension failures, correlated multi-system degradation, and risk-weighted composite indicators, each triggering proportionate responses. Third, a graduated safe transition protocol separates withdrawal of operational authorization from physical shutdown, consistent with established safety standards and EU AI Act requirements. Fourth, environmental delta is introduced as a distinct baseline validity condition: environmental drift beyond the certified Operational Design Domain (ODD) triggers recertification or ODD revision rather than automatic authority contraction. Together, these extensions transform ARC from a deployment-time certification architecture into a continuous framework for monitoring, evaluating, and enforcing compliance throughout the operational lifecycle of autonomous systems. The framework addresses the continuous compliance obligations established by EU AI Act Article 72(2).

cs.RO · cs.AI · cs.CY

新论文 · v1arXiv:2611.21808

SimAI: Mechanistic User Simulation through Psychological Network Models

Cheng Li, Adhyyan Narang, Jiayi Yuan, John F. Buss, Jina Suh, Devon Sandel-Fernandez, Yulia Tsvetkov, Adam M. Kuczynski 等 9 位作者

原文摘要

Realistic user simulation enables the study of human interactions when direct experimentation is costly or potentially harmful. However, existing simulators largely overlook the psychological mechanisms that drive user behavior. We introduce SimAI, a framework for mechanistic user simulation that models how psychological factors interact to shape user responses. To overcome the challenge of supervising open-ended behavior, we propose a graph reconstruction objective that provides graph-level rewards based on how well simulated conversations reflect the underlying psychological relationships. To support this approach, we construct PSYCHE, a dataset of 18,576 profile-network pairs derived from 516 psychotherapy cases. Automatic evaluations show that SimAI achieves greater simulation and behavioral diversity than existing patient simulators while maintaining strong profile alignment. In an interactive study with 30 mental-health professionals and trainees, SimAI receives the highest average ratings for conversational authenticity, realistic help-seeking behavior, and clinical training utility. Beyond simulation quality, SimAI enables realistic clinical training and uncovers safety failures in prolonged AI interactions with vulnerable users. Code is available at https://github.com/behavioral-data/ANGEL-UserSim.

cs.CL · cs.AI · cs.HC

新论文 · v1arXiv:2611.21806

A Probabilistic Lateral Motion Prediction Model with Improved Response Fidelity for Vehicle-in-the-Loop Simulation

Xiangyang Ye, Chaosheng Huang, Jinwen Yang, Zhengxian Chen, Jun Li

原文摘要

Vehicle-in-the-loop (VIL) simulation requires a lateral dynamics model that accurately reproduces vehicle responses and reliably generates horizontal lateral-position and heading commands through recursive integration. This paper presents a probabilistic lateral motion prediction model with improved response fidelity. A two-degree-of-freedom vehicle model provides the physical prior, while a recurrent neural network learns correlated residual corrections to lateral acceleration and yaw rate. To maintain prediction fidelity during recursive motion generation, multistep rollout training feeds corrected responses into subsequent states and histories and directly penalizes accumulated lateral-velocity error. A conditional Gaussian characterizes response uncertainty, which is propagated to lateral-response, position, and heading predictions through augmented-state linearization. Evaluation results demonstrate improved lateral-response and integrated-motion prediction. Compared with the Deep Dynamics lateral adaptation, the proposed model reduces mean lateral-position root-mean-square error (RMSE) from 0.596 m to 0.483 m, an improvement of 19.0%, while reducing mean lateral-velocity RMSE from 0.0469 m/s to 0.0441 m/s. These results demonstrate the effectiveness of combining physical priors, probabilistic residual learning, and multistep rollout training for response-faithful lateral motion prediction.

cs.RO

版本更新 · v3arXiv:2607.25987

IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in Large Language Models

Conor McCauley, Zeliang Kan, Jason Martin

原文摘要

When a language model receives conflicting instructions from different priority levels, which one does it actually follow? This question lies at the heart of reliable LLM deployment. Existing benchmarks answer this only partially, often focusing on a single hierarchy component or adapting public datasets with limited tool-use coverage. We present IH-Benchmark, a conflict-centered benchmark for instruction-hierarchy robustness across direct System $\succ$ User (S $\succ$ U) conflicts and tool-mediated User $\succ$ Tool (U $\succ$ T) conflicts. We organize tests into seven constraint categories according to the higher-priority requirements under evaluation. Each test is evaluated with a uniform binary pass/fail protocol combining a predicate domain-specific language (DSL) with rubric-based LLM judges. We report category-balanced compliance rates and evaluate non-conflict controls separately. Our evaluation of 32 model configurations over five runs each reveals substantial variation in overall compliance, with scores ranging from 32.9% to 97.8%. Models achieve higher compliance on S $\succ$ U than on U $\succ$ T on average, at 84.6% and 69.6%, respectively. Strong performance on the former track does not guarantee comparable robustness on the latter. Constraint hardening provides a prompt-based defense, but its benefits depend on the model and how conflicting instructions are delivered. Several models also resist unauthorized tool actions more reliably than injected instructions that alter response language or factual content. Together, these results show that high aggregate compliance can conceal weaknesses in specific conflict tracks and instruction requirements. We release IH-Benchmark, including the benchmark corpus, agent simulators, and evaluation harness, at LINK_RELEASE_AFTER_PEER_REVIEW.

cs.CR · cs.SE

新论文 · v1arXiv:2611.21804

Corrupting Ties: Investigating Robustness to Bias Injection Across Multi-Agent Network Topologies

Cléa Chataigner, Mina Arzaghi, Florian Carichon, Pablo Piantanida, Golnoosh Farnadi

原文摘要

AI systems are increasingly deployed in high-stakes decision-making contexts, where interactions among components can introduce fairness risks that remain undetected when auditing components or collective outcomes in isolation. As LLM-based multi-agent systems become more prevalent, understanding how biased information propagates through agent interactions is essential for assessing their fairness. We introduce a controlled bias injection framework that replaces selected agent responses with predefined biased ones, enabling an intervention-based analysis of how network topology and injection configurations shape system behavior. We propose decision divergence metrics that quantify the effects of these interventions at the agent, network, and system levels, and evaluate five topologies on three binary classification tasks using LLMs from the Qwen and Gemma families. Sequential networks show the greatest divergence, whereas fully connected and mesh networks show less. Injection position also matters: in star networks, injecting the central agent has larger effects than injecting peripheral agents. Models further differ in whether divergence follows the injected bias. These findings highlight the role of network structure in the propagation of biased information and motivate topology-aware auditing of fairness risks in multi-agent systems.

cs.CL · cs.MA

版本更新 · v4arXiv:2505.03563

Say It Another Way: Auditing LLMs with a User-Grounded Automated Paraphrasing Framework

Cléa Chataigner, Rebecca Ma, Prakhar Ganesh, Yuhao Chen, Afaf Taïk, Elliot Creager, Golnoosh Farnadi

原文摘要

Large language models (LLMs) are highly sensitive to subtle changes in prompt phrasing, posing challenges for reliable auditing. Prior methods often apply unconstrained prompt paraphrasing, which risk missing linguistic and demographic factors that shape authentic user interactions. We introduce AUGMENT (Automated User-Grounded Modeling and Evaluation of Natural Language Transformations), a framework for generating controlled paraphrases, grounded in user behaviors. AUGMENT leverages linguistically informed rules and enforces quality through checks on instruction adherence, semantic similarity, and realism, ensuring paraphrases are both reliable and meaningful for auditing. Through case studies on the BBQ and MMLU datasets, we show that controlled paraphrases uncover systematic weaknesses that remain obscured under unconstrained variation. These results highlight the value of the AUGMENT framework for reliable auditing.

cs.CL

新论文 · v1arXiv:2611.21803

Mechanism Design and Active Systems Theory: 60 Years of Parallel Development

Dmitry A. Novikov

原文摘要

The survey compares two research traditions within the mathematical theory of designing the rules of interaction (mechanisms) for purposeful participants: mechanism design, together with contract theory and implementation theory, and the theory of active systems created by V.N. Burkov and developed into the theory of control in organizations (TCO) by D.A. Novikov's school; the main results of Yu.B. Germeier's school and of the domestic schools adjacent to active systems theory (AST) are covered as well. The problem statements and principal results of 2006-2026 are presented: for mechanism design (MD) - robust and dynamic mechanism design, multidimensional screening, information design, simplicity of mechanisms and credibility of the designer, market design, algorithmic and learning-based design, mechanisms for AI agents, and robust, relational, dynamic and algorithmic contracts; for AST and TCO - a general typology of control, strategy-proof and incentive-compatible planning mechanisms, decomposition of the agents' game, systems with distributed control and coalitional interaction, reflexive games and informational control, control of staff and structure, dynamic active systems, and project management. A correspondence between the classical results is established (the fair play principle and the revelation principle, the serial resource allocation mechanism and the uniform rule, active expertise mechanisms and generalized median schemes, quasi-compensatory incentive schemes and contracts under observable actions), and priorities are delineated by uniform rules; the areas where the two traditions diverge are identified, as are the dimensions of the problem (staff, structure, institutions, awareness, agents' beliefs) covered only by TCO.

eess.SY · cs.GT

新论文 · v1arXiv:2611.21802

Data-Driven Variable-Length Compression of 3D Representations

Yvette Y. Lin, Sai Karthikey Pentapati, Sarvesh Sundaram, Guandao Yang, Sara Fridovich-Keil

原文摘要

Compressing 3D shapes is important for the efficiency of many applications, yet existing methods either cannot leverage dataset-level statistics or use a fixed compression ratio for all shapes. We propose a learned variable-length compression method that exploits structure across a training dataset while adapting compressed representation size to individual shape complexity using only fast feed-forward inference. Our method operates on general latent representations and improves rate-distortion for both meshes and signed distance fields. Code is available at https://github.com/voilalab/varlen-3D.

cs.CV · cs.LG