跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订，在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描：2026-11-16 01:34 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 04:01 — 2026-11-16 04:01（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：2026-11-16 01:34最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

论文修订列表

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 6,729 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33（北京时间）
版本更新 · v2arXiv:2604.04528

Receding-Horizon Control via Drifting Models

Daniele Foffano, Alessio Russo, Alexandre Proutiere

原文摘要

We study the problem of trajectory optimization in settings where the system dynamics are unknown and the controller cannot simulate candidate trajectories through a model at test time. When an offline dataset of trajectories is available, an agent could directly learn a trajectory generator by distribution matching. However, this approach only recovers the behavior distribution in the dataset, and does not in general produce a model that minimizes a desired cost criterion. In this work, we propose Drifting Receding Horizon Control (RHC), an offline trajectory optimization framework that combines drifting generative models with receding-horizon planning under unknown dynamics. The goal of Drifting RHC is to learn, from an offline dataset of trajectories, a conditional distribution over trajectories that is both supported by the data and biased toward optimal plans. We show that the target distribution of Drifting RHC is the unique solution of an objective that trades off optimality with closeness to the offline prior. We further bound the gap between the predicted and the executed cost of a generated plan by its consistency with the dynamics, and introduce a rollout-consistency loss that distills a learned model into the generator at training time only. On a mass-spring-damper, a cart-pole and a planar quadrotor, Drifting RHC attains the lowest regret among generative and model-based planners, outperforms DeePC on the nonlinear systems, and plans $9$ to $83$ times faster than iLQR, model-based and diffusion-based planners.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.07962

We Should Distinguish Unlearning From Untraining

Eleni Triantafillou, Ahmed Imtiaz Humayun, Monica Ribero, Alexander Matt Turner, Michael C. Mozer, Georgios Kaissis

原文摘要

There has been a recent surge in interest about the question of how we can ``delete'' specific data points or behaviours from a trained model, a goal referred to as ``machine unlearning''. We argue that the umbrella term ``unlearning'' actually spans two distinct problem formulations, but the distinction between them has not yet been observed in literature. This causes ambiguity around when an unlearning algorithm is expected to work, leads to the use of inappropriate metrics and baselines when comparing algorithms to one another, difficulty in interpreting results, and missed opportunities for pursuing critical research directions. In this paper, we argue for the position that a fundamental distinction must be made between two notions that we refer to as unlearning and untraining. On one hand, untraining aims to reverse the effect of having trained on a given ``forget set'', i.e. to remove the influence that that specific set of examples had on the model during training. On the other hand, unlearning aims not just to remove the influence of those given examples, but also of the entire underlying subdistribution from which they were sampled (and thus e.g. the concept or model behaviour that those examples represent). We discuss technical definitions of these problems and map problem settings studied in the literature to each notion. By disambiguating technical definitions, our work aims to accelerate progress in this important field.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.29963

Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots

Mark Vero, Fabian Kaczmarczyck, Ivan Petrov, Ilia Shumailov, Jamie Hayes, Niels Heinen, Tianqi Fan, Luca Invernizzi 等 9 位作者

原文摘要

Honeypots are decoy systems mimicking real system components designed to defend against cyber attacks. Recently, LLMs increasingly serve as simulation backbones for honeypots. They enable defenders to construct high-interaction honeypots with low system security risks. However, LLM-powered honeypot development lacks a unified evaluation framework. Most evaluations consist of measuring response similarity on fixed commands, manual testing, or real-world deployment. These methods are often not scalable for development, reproducible across evaluations, representative of practical attacks, or adaptable to various attacker and honeypot configurations. In this work, we bridge this gap and propose Honeyval, a comprehensive evaluation framework for LLM-powered HTTP honeypots. We address the limitations of prior evaluations by grounding the honeypots in 16 backend applications, using AI hacking agents as attackers, employing two control tasks to monitor agent and honeypot capabilities across customizations, and defining clear and verifiable exploit goals for the attacker. Using Honeyval, we conduct an extensive evaluation of recent cost-efficient LLMs as HTTP honeypots. Our experiments highlight the promise of LLM-powered honeypots; they lead to substantially longer interactions with the attacker than rule-based baseline honeypots and are far less frequently detected even by frontier models, all while, on average, preserving a running cost advantage against agentic attackers. Further, we experiment with various honeypot extensions and counter-offensive configurations, observing unique trade-offs, e.g., lower latency at the price of increased detection.

cs.CR · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.12923

Annealing in variational inference mitigates mode collapse: A theoretical study on Gaussian mixtures

Luigi Fogliani, Bruno Loureiro, Marylou Gabrié

原文摘要

Mode collapse, the failure to capture one or more modes when targeting a multimodal distribution, is a central challenge in modern variational inference. In this work, we provide a mathematical analysis of annealing based strategies for mitigating mode collapse in a tractable setting: learning a Gaussian mixture, where mode collapse is known to arise. Leveraging a low dimensional summary statistics description, we precisely characterize the interplay between the initial temperature and the annealing rate, and derive a sharp formula for the probability of mode collapse. Our analysis shows that an appropriately chosen annealing scheme can robustly prevent mode collapse. Finally, we present numerical evidence that these theoretical tradeoffs qualitatively extend to neural network based models, RealNVP normalizing flows, providing guidance for designing annealing strategies mitigating mode collapse in practical variational inference pipelines.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.22756

Lumberjack: Better Differentially Private Random Forests through Heavy Hitter Detection in Trees

Christian Janos Lebeda, David Erb, Tudor Cebere, Aurélien Bellet

原文摘要

Random forests are widely used in fields involving sensitive tabular data, but existing approaches to enforcing differential privacy (DP) typically degrade performance to the point of impracticality. In this paper, we introduce Lumberjack, a differentially private random forest algorithm that achieves substantially higher utility by constructing large random decision trees and then applying aggressive, privacy-preserving pruning to retain only sufficiently populated nodes. A key component of our approach is a novel $(\varepsilon,δ)$-DP heavy hitter detection algorithm for hierarchical data, whose error is $O_{\varepsilon,δ}(\sqrt{\log h})$ for trees of height $h$ and may be of independent interest. This favorable scaling enables the use of significantly deeper trees than in prior work, leading to improved expressiveness under privacy constraints. Our empirical evaluation on benchmark datasets shows that Lumberjack consistently outperforms prior DP random forest methods, establishing a new state of the art. In particular, our approach yields substantial improvements in the privacy-utility trade-off for practical privacy budgets. Our findings suggest that carefully designed DP random forests can close much of the utility gap, highlighting a promising and underexplored direction for future research.

cs.LG · cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.06343

Prism: Bidirectional Self-Teaching for Unified Multimodal Models

Peng Zhang, Qian Chen, Xianyin Zhang, Yimin Tian, Ruite Fei, Dongyi Lv, Lifan Guo, Chi Zhang 等 9 位作者

原文摘要

Unified Multimodal Models (UMMs) aim to support visual understanding and generation within a single model. Existing post-training methods either use understanding as a fixed teacher to improve generation, or rely on ground-truth trajectories to supervise both understanding and generation. Prism instead derives bidirectional supervision from self-generated interleaved rollouts, constructing training targets according to the reliability of their text and image chains. We propose Prism, a bidirectional self-teaching post-training method for UMMs. Like a prism decomposing mixed light, Prism decouples a coupled interleaved trajectory into a text chain and an image chain, assesses the reliability of each chain, and constructs a corresponding training target from their reliability states. Experiments on both SenseNova-U1 and BAGEL show that Prism improves both understanding and generation. On the generation side, GenEval improves from 85.8 to 89.2 (+3.4), and DPG improves from 86.1 to 87.3 (+1.2) on SenseNova-U1. On the understanding side, the total MME score improves from 2282.6 to 2311.6, and MMVP improves from 58.0 to 62.0. Consistent improvements are observed on BAGEL. These results highlight that Prism enables coordinated improvements in generation and understanding by constructing reliability-guided self-training targets from self-generated trajectories, without relying on an external verifier or externally annotated corrected trajectories during target construction. Code is available at https://github.com/aliyun/qwen-dianjin/tree/master/DianJin-Prism.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2511.02442

Emerging consecutive pattern avoidance

Nathanaël Hassler, Sergey Kirgizov

原文摘要

In this note we study the asymptotic popularity, that is, the limit probability to find a given consecutive pattern at a random position in a random permutation in the eighteen classes of permutations avoiding at least two length 3 consecutive patterns. We show that for ten classes, this popularity can be readily deduced from the structure of the permutations. By combining analytical and bijective approaches, we study in detail two more involved cases. The problem remains open for five classes.

math.CO · cs.DM

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2604.20133

EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation

Aimin Zhang, Jiajing Guo, Fuwei Jia, Chen Lv, Boyu Wang, Fangzheng Li

原文摘要

Large language model (LLM) agents increasingly rely on reusable skills, but skills are usually written by hand, and letting an agent change them on its own calls for explicit user control. We report on EvoAgent, an evolvable agent framework built for a foreign trade assistant, and share the engineering choices behind it. We organize the agent as a harness of four components (reasoning, context engineering, tools and state) and confine self-improvement to the user's persistent state: profile, memory and skills. Skills are multi-file packages with lazily loaded references, matched in three stages (keyword, embedding, LLM). The main agent can delegate to sub-agents with their own context, and long histories are compressed while an index of recoverable resources is kept. An offline loop reviews completed sessions to update the profile and memory and to propose skills; in the open-source release a skill changes only after the user confirms the proposal. On 172 foreign trade test cases scored by an LLM judge on five dimensions, GPT-5.2 with EvoAgent scored about 28% higher than GPT-5.2 called directly with only the final query. This is a single run judged by the model under test, so it measures the harness as a whole rather than any one mechanism, and swapping in GPT-4.1 or Qwen3.5-35B-A3B lowered the scores relative to calling those models directly. Several mechanisms described here were added after the version we evaluated and are not evaluated. The evaluation data is proprietary, so the results are for reference only. An open-source release of the code, which is not the evaluated business version, is available at https://github.com/Focus-AI-Center/Mentarc-EvoAgent

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2611.04804

GSPIM: A Temporal-Locality-Aware 4D Gaussian Splatting Accelerator with Polymorphic PIM and Multi-Frame Rendering Dataflow

Zirui Ma, Zhihua Fan, Haibin Wu, Dongrui Fan, Xiaochun Ye, Wenming Li

原文摘要

4D Gaussian Splatting (4DGS) enables high-quality real-time novel-view synthesis for dynamic scenes, supporting free-viewpoint video, mobile XR, and autonomous systems at the edge. Methods using explicit 4D distributions, keyframe interpolation, or anchor binding share two GPU data-movement bottlenecks. Temporal filtering follows model record loading, wasting LPDDR5 bandwidth on inactive data. Frame-isolated execution also overlooks highly overlapping active sets and depth relationships across adjacent frames, reloading shared attributes when working sets exceed on-chip cache capacity. To address these bottlenecks, we present GSPIM, a temporal-locality-aware 4DGS accelerator for PIM-enabled edge devices. Polymorphic PIM adapts a shared near-memory datapath to representation-specific field layouts and selection procedures. It filters and compacts valid data into contiguous inputs before the GPU accesses complete attributes, reducing ineffective transfers. Multi-Frame Rendering Dataflow reuses active attributes and stable depth relationships within a temporal window, reducing repeated work across frames. Hybrid Dataflow Scheduling overlaps near-memory data preparation with GPU rendering to reduce waiting. Evaluation combines a GPU-PIM model calibrated to Jetson AGX Orin 64 GB with a 1z DRAM physical implementation of the added circuits. Across three 4DGS methods and six dynamic scenes, GSPIM achieves a 4.15x geometric-mean speedup and a 4.99x geometric-mean energy-efficiency improvement over a fully optimized frame-by-frame GPU baseline. The maximum scene-level PSNR difference is 0.011 dB, and the added physical footprint is 18.7172 square millimeters across 32 LPDDR5 dies.

cs.AR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.07591

Topology Obstructs Pure Foundation Neural Quantum States

Timothy Heightman, Elena Orlova, Philip Mantrov, Aleksei Ustimenko

原文摘要

Foundation models for ground states in spin-1/2 systems are a promising method for problems ranging from quantum chemistry to identifying new phase diagrams. Nearly all such models are currently pure-states that condition on the Hamiltonian's parameters, whose Monte Carlo samples give energy estimates according to the variational principle. In this contribution, we show that this representation is topologically obstructed. For any gapped Hamiltonian family whose ground-state bundle is non-trivial, every continuous normalized state-vector model has zero fidelity with the ground state at some parameter value in the Hamiltonian family. For that value, the energy is at least one spectral gap, $Δ$, with an $O(Δ)$ gap in an open-neighbourhood of that point. We show that this is a sufficient no-go also in the case of degenerate ground-state manifolds, time dynamics, and periodic systems with mixed space-time topology, demonstrating these obstructions on one- and two-qubit systems. We discuss how this causes a spike in the fidelity susceptibility, giving a numerical signature of a phase-transition where there is none. Finally, we show that operator-valued models canonically avoid these obstructions and preserve topological information, implying a structural necessity in representation for foundation neural quantum states.

quant-ph · cond-mat.dis-nn · cond-mat.str-el · cs.AI · math-ph

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.35028

VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation

Hanxun Huang, Yutao Wu, Qizhou Wang, Silvia Montaña-Niño, Yige Li, Xiang Zheng, Elif Buse Doyuran, Phoebe Matich 等 12 位作者

原文摘要

Large language models (LLMs) have made misinformation inexpensive to produce but not to verify, creating a growing asymmetry in the information ecosystem. Under tight time, labor, and budget constraints, media organizations, platforms, and fact-checkers rely on screening to prioritize which content to verify. We introduce VEX-Bench, a unified benchmark for evaluating the verification complexity of LLM-generated misinformation, as perceived during screening, across models and generation methods. Verification complexity is assessed along multiple dimensions derived from journalistic and fact-checking practices, capturing checkability, harm potential, source credibility signals, imposter legitimacy, and expected verification effort. We define the VEX score as an integrated measure combining elicitation yield and verification complexity to quantify how generated content consumes limited verification capacity. We construct a benchmark spanning two misinformation categories, 6 high-stakes domains, and 60 real-world topics, and evaluate 7 frontier LLMs and 7 generation methods, yielding 5{,}880 articles. We employ an LLM-as-judge for scalable evaluation and validate it using content-analysis methodology, including ordinal Krippendorff $α$ for inter-annotator reliability, complemented by fact-checking agents for verification. Our findings show that no single method dominates all dimensions, underscoring the need for multi-dimensional evaluation. LLMs can generate high-VEX misinformation at 3$\times$ to 169$\times$ lower cost than agent-based verification. Such content is often prioritized during screening, consuming scarce verification resources and introducing a systematic risk of misallocation in resource-constrained verification systems. The code is publicly available in our \href{https://github.com/HanxunH/VEX-Bench}{GitHub repository}.

cs.LG · cs.AI · cs.CL · cs.CY · cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.41260

SketchDirector: Complex Scene Sketching via Agentic Layout Reasoning and Detail Refinement

Yiqi Liang, Xiaodong Cun

原文摘要

Existing sketch generation methods often rely on image guidance and are largely limited to individual objects or simplified scenes, leaving text-guided complex scene sketching underexplored. We present SketchDirector, an agentic framework that mimics the human sketching workflow for automatic multi-concept scene sketching. Given a scene-level text prompt, SketchDirector first employs a large language model~(LLM) to decompose the scene into multiple draft assets, where each is represented by a set of Bézier curves. Then, an agentic reasoning loop iteratively plans and executes their spatial arrangement, guided by self-evolving memory. Finally, a detail refinement module leverages diffusion priors to enhance sketch quality while preserving geometric structure. To support future research and applications in multi-concept scene sketch generation, we further introduce the MCSketch8K dataset, comprising editable vector assets, compositional layouts, and object-level manipulation annotations. Extensive experiments show that SketchDirector outperforms state-of-the-art baselines in semantic and compositional quality while effectively preserving overall contour organization during refinement.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.05841

SnapScope: A Platform for City-Scale Collection and Exploration of Public Snap Map Data

Mohammed Almukaynizi, Fahad Alhaqbani, Khaled Almarzoug, Sultan Alanbari

原文摘要

Snapchat's Snap Map is an ephemeral stream of geotagged public video and image stories. The platform documents no API for it, no prior work describes a reproducible way to collect it at city scale, and no tool exists for exploring what is collected. We present SnapScope, which pairs a collection back end with a web front end. The back end builds a geographic query grid, sweeps it on a schedule, and deduplicates at ingestion; the front end supports scraper management, interactive exploration, neighborhood comparison, and export. Deployed over Riyadh, Saudi Arabia, it collected 515,364 unique public snaps across 23 days (17 September-9 October 2024) on a 1 km grid of 2,740 query points. A saturation probe over 21 consecutive runs found 94.8% of returned observations already stored, indicating that successive passes mostly return already-captured content. We release a privacy-safe aggregate dataset of tile-level hourly counts under CC BY 4.0. The platform is city-agnostic: redeployment requires only new grid coordinates and boundary polygons.

cs.SI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2312.16336

Learning temporal formulas from examples is hard

Corto Mascle, Nathanaël Fijalkow, Guillaume Lagarde

原文摘要

We study the problem of learning linear temporal logic (LTL) formulas from examples, as a first step towards expressing a property separating positive and negative instances in a way that is comprehensible for humans. Given positive and negative words, the goal is to find a smallest formula satisfied by the positive words and not by the negative ones. We study the computational complexity of this problem for all fragments of negation-free LTL built from the operators F (eventually), G (globally), X (next), $\wedge$ (conjunction), and $\vee$ (disjunction), without the until operator. We show that the problem is in NP for all fragments, that it is in polynomial time for the fragments containing none of the pairs $\{X,\wedge\}$, $\{X,\vee\}$, $\{F,\wedge\}$ and $\{G,\vee\}$, and that it is NP-complete for all other fragments, already for alphabets with two or three letters. We also show that the fragment with only X and $\wedge$ has a polynomial time 3-approximation algorithm, but no polynomial time approximation scheme unless P = NP. These results motivate the search for efficient heuristics.

cs.LG · cs.AI · cs.FL · cs.LO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.31153

BIAS-ID: A Framework for Analyzing Transformation Biases in AI-Generated Image Detectors

Jonas Ricker, Asja Fischer, Erwin Quiring

原文摘要

Given the surge of harmful AI-generated imagery online, reliably distinguishing authentic images from generated ones has become an urgent research topic. While many proposed detection methods demonstrate high accuracy in controlled settings, their performance often degrades substantially when tested on real-world data. A potential root cause is subtle bias in the detectors' training data. As a result, detectors may rely on spurious correlations instead of learning true forensic artifacts. While recent studies have identified this problem and developed countermeasures, there is not yet an established protocol to evaluate how biased a detector actually is. In this work, we therefore take a step back: First, we discuss what it means for a detector to be biased, and how this differs from a lack of robustness. Second, we propose BIAS-ID, a transparent framework for analyzing and quantifying the presence of transformation biases in AI-generated image detectors. We validate our framework by evaluating six detectors across two datasets, revealing that several state-of-the-art detection methods are strongly affected by common, processing-related biases. Our results highlight the importance of bias-aware evaluation for developing reliable AI-generated image detectors. We provide an easy-to-use library and code to reproduce our results at https://github.com/jonasricker/biasid.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.26192

Co-folding model guided by structural proteomics

Alon Shtrikman, Sagie Brodsky, Michal Ran Shchory, Nitzan Simchi, Yaron Ben Shoshan-Galeczki, Eran Seger, Kirill Pevzner

原文摘要

Proximity-inducing drugs, including PROTACs, represent a promising therapeutic modality. Their activity is driven by the geometry of the assembled ternary complex, which determines whether the target is ubiquitinated. Co-folding models perform poorly in these cases due to scarcity of training data and the dynamic nature of such complexes. Structural proteomics can supply the missing geometric information and steer the model towards an accurate prediction. However, current models accept only positive signals, while a differential structural mass-spectrometry experiment also reports negative signals. We introduce AIMS-Fold, an inference-time guidance layer built on Boltz-2 that requires no retraining and accepts repulsive constraints alongside attractive ones. We tested AIMS-Fold on 28 PROTAC, glue and antibody complexes that Boltz-2 fails to predict. From only five generated models, guidance recovers the correct conformation in 64% of cases. The gap does not close with scale: across 100 models and 20 seeds, unguided Boltz-2 reaches 14% while AIMS-Fold reaches 86%. Repulsive constraints alone recover the correct conformation on some systems, occasionally exceeding the matched attractive constraints. Taken together, these results demonstrate the strength of utilizing the full structural proteomics signal, positive and negative, to steer generative models toward the correct conformation, addressing a central problem in rational degrader design.

cs.LG · cs.AI · q-bio.BM

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.13674

Weakly Supervised Segmentation as Semantic-Based Regularization

Stefano Colamonaco, Andrei-Bogdan Florea, Jaron Maene

原文摘要

Weakly supervised semantic segmentation (WSSS) trains dense pixel-level segmentation models from partial or coarse annotations such as bounding boxes, scribbles, or image-level tags. While recent work leverages foundation models such as the Segment Anything Model (SAM) to generate pseudo-labels, these approaches typically depend on heuristic prompt choices and offer limited ways to incorporate prior knowledge or heterogeneous labels. We address this gap by taking a neurosymbolic perspective: integrating differentiable fuzzy logic with deep segmentation models. Weak annotations and domain-specific priors are unified as continuous logical constraints that fine-tune SAM under weak supervision. The refined foundation model then produces improved pseudo-labels, from which we train a second-stage prompt-free segmentation model. Experiments on Pascal VOC 2012 and the REFUGE2 optic disc/cup segmentation dataset show that our logic-guided fine-tuning yields higher-quality pseudo-labels, leading to state-of-the-art segmentation accuracy that often exceeds densely supervised baselines.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.07148

Agentic Planning with Reasoning for Image Styling via Offline RL

Subhojyoti Mukherjee, Stefano Petrangeli, Branislav Kveton, Trung Bui, Franck Dernoncourt, Arko Mukherjee

原文摘要

Direct prompt-based editing often fails on complex transformations because vague and subjective prompts often require nuanced understanding of what should be changed in the image. Our core intuition is that leveraging compositional image editing tools rather than direct prompting profits from structured agent-level planning with explicit reasoning, leading to better results. This structured planning framework enables efficient offline RL post-training on quality-scored trajectories to improve performance. We present a tool-based agentic RL post-training framework that addresses this through structured planning with chain-of-thought reasoning. Our key contributions include: (1) A tool-based agentic planning methodology that combines a compositional library of orthogonal primitive transformations, structured context representation, and explicit per-step reasoning to decompose complex styling into interpretable tool sequences. (2) A synthetic data generation pipeline producing three large-scale datasets (each $\sim$10K trajectories) with reasoning chains, plans, and quality scores, as no existing datasets provide such supervision. Our datasets and code are publicly available at the HuggingFace repository. (3) Offline RL training methods for learning planners with reasoning as our core algorithmic contributions, which consistently improve over the Edit-Only baseline in visual quality and instruction following. (4) Comprehensive evaluation across 4B and 8B parameter Qwen3-VL models showing that our methods outperform other baselines in the majority of compositional tasks, validated by human evaluations.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.38983

Beyond atol and rtol: Sound Test Oracles for Low-Precision GPU Kernels

Xinyi Shi

原文摘要

Low-precision GPU kernels are commonly tested against a reference using hand-picked absolute and relative tolerances. Legitimate numerical error varies with the input, format and precision plan, so a fixed tolerance trades false alarms for missed faults. We present numoracle, which derives per-element acceptance regions from precision-annotated reference programs. Its calculus tracks shared rounding errors, provenance-ordered products, block-scaled quantizers and calibrated math-library errors. A rounding-interval check detects faulty stores that symmetric bounds can admit. Soundness is conditional on explicit rounding, hardware, domain and implementation assumptions; a fixed-input mode removes the zero-mean rounding assumption. We evaluate 13 Triton operators from Liger-Kernel, Unsloth and vLLM on two GPU generations. The main campaigns produce no false alarm on 33,960 correct-kernel and behavior-preserving-variant runs per GPU. Under input shift, the GPU campaigns record no false alarm while tuned tolerances flag up to 30% of correct runs; final-version reference checks identify inputs without complete finite-range certificates. On the RTX PRO 6000, numoracle kills 116 of 124 effective mutants, versus 59-83 for four fixed baselines. Among 400 tuned tolerance configurations, requiring at most 1% false alarms in every evaluated Liger input group permits at most 31 of 53 main-mutant kills, versus numoracle's 50. Historical replays expose accuracy faults in eight change pairs without rejecting their matched corrected controls; a ninth change concerns rounding parity.

cs.MS · cs.PL · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2506.16129

Neurosymbolic Object-Centric Learning with Distant Supervision

Stefano Colamonaco, David Debot, Giuseppe Marra

原文摘要

Neurosymbolic learning can use symbolic rules to provide supervision for latent concepts from weak labels, but it commonly assumes that the entities referenced by these rules are already specified. Object-centric models decompose images into slot-like representations; however, such slots are not necessarily aligned with the predicates required for symbolic reasoning. We investigate object-centric neurosymbolic learning under distant supervision, where the object-level arguments of a logic program are learned directly from images using only global task labels. We introduce DeepPbjectLog, a probabilistic neurosymbolic model that integrates a slot-based perceptual encoder with a probabilistic logic layer. The encoder predicts objectness and class probabilities for candidate object representations, while the logic layer marginalizes over latent objectness and class assignments to compute the likelihood of the observed label. This formulation provides a differentiable task-level learning signal for object-centric perception without requiring per-object labels, masks, bounding boxes, or heuristic set matching. Evaluations across diverse visual reasoning tasks demonstrate that DeepObjectLog achieves superior out-of-distribution generalization to compositional, object-count, and rule shifts compared to neural object-centric and standard neurosymbolic baselines.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.09128

SocialGym: Evaluating LLM Social Intelligence through Verifiable Multi-Agent Games

Keyu He, Xuhui Zhou, Maarten Sap

原文摘要

Large Language Model (LLM) agents are increasingly deployed in multi-agent social settings where they must cooperate, negotiate, and adapt to other agents. Measuring these social skills is hard because most social interactions offer no objective ground truth. Evaluations often fall back on LLM judges, which are costly, subjective, and noisy. We introduce SocialGym, an environment of 22 multi-agent social games, from matrix games to hidden-role deduction, with verifiable outcomes determined by game rules. We benchmark ten LLMs across all games and roles using an Elo tournament. Our results show that no model is best in every game, and rankings shift across game families and sides. Secret keeping correlates more strongly with theory-of-mind and privacy benchmarks than with general knowledge benchmarks. Half of the models give away their side's secret in Chameleon and Spyfall, and the smallest models are not reliably better than chance at voting for hidden opponents in most hidden-role games. Finally, we examine whether models can improve their play by reflecting on self-play and writing strategy playbooks, finding mixed results across models and games. SocialGym provides verifiable measures for diagnosing LLM social capabilities across settings and roles.

cs.CL · cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v6arXiv:2512.01946

Guardian: Detecting Robotic Manipulation Failures with Vision-Language Models

Paul Pacaud, Ricardo Garcia, Shizhe Chen, Cordelia Schmid

原文摘要

Robust robotic manipulation requires reliable failure detection and recovery. Although recent Vision-Language Models (VLMs) show promise in robot failure detection, their generalization is severely limited by the scarcity and narrow coverage of failure data. To address this bottleneck, we propose an automatic framework for generating diverse robotic planning and execution failures across both simulated and real-world environments. Our approach perturbs successful manipulation trajectories to synthesize failures that reflect realistic failure distributions, and leverages VLMs to produce structured step-by-step reasoning traces. This yields GuardianFail-36k, a large-scale failure reasoning dataset built upon the RLBench simulator and the BridgeDataV2 real-robot dataset. Using GuardianFail-36k, we train Guardian, a multi-view reasoning VLM for unified planning and execution verification. Guardian achieves state-of-the-art performance on three unseen real-world benchmarks: RoboFail, RoboVQA, and our newly introduced UR5-Fail. When integrated with a state-of-the-art LLM-based manipulation policy, it consistently boosts task success rates in both simulation and real-world deployment. These results demonstrate that scaling high-quality failure reasoning data is critical for improving generalization in robotic failure detection. Code, Data, and Models are available at https://www.di.ens.fr/willow/research/guardian/.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2412.12227

Embedded Decomposed Transformer for explainable multivariate time series forecasting

Sanjay Chakraborty, Ibrahim Delibasoglu, Fredrik Heintz

原文摘要

Time series forecasting is an important problem with diverse real-world applications. This paper introduces the Embedded Decomposed Transformer (EDformer) for multivariate time series forecasting. EDformer decomposes the input signal into seasonal and trend components using two complementary strategies: time-domain Average Pooling (AP) based on moving-average smoothing and Frequency-Aware (FA) decomposition based on low-pass filtering in the Fourier domain. The reconstructed multivariate seasonal component is embedded across inverted dimensions, after which attention captures cross-variate correlations and a feed-forward network learns nonlinear representations for each variable. The trend component is forecast through projection and combined with the seasonal prediction to produce the final forecast. We evaluate both decomposition variants on several real-world datasets, showing that EDformer achieves competitive performance, while their relative effectiveness varies across datasets, experimental settings, and temporal characteristics. We further conduct an ablation study isolating the contribution of decomposition, inverted embedding, and the frequency cutoff ratio; a hyperparameter sensitivity analysis over learning rate and batch size; and a statistical significance analysis using Friedman and Wilcoxon signed-rank tests to substantiate the reported performance differences. Finally, model explainability techniques are explored to improve interpretability and provide insights into the features and time steps influencing the forecasting results.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.19861

PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents

Seongjae Kang, Taehyung Yu, Sung Ju Hwang

原文摘要

Customer-service LLM agents must follow organizational policy when acting on a user's behalf. Compliance failures arise from either forbidden actions, such as granting an ineligible change, or omitted procedural requirements, such as identification or confirmation. Runtime safeguards can intervene on risky actions, but action-local checks do not guide an agent through a multi-step procedure. Workflow-following systems support prescribed process execution, but primarily target workflow completion rather than safeguarding agent behavior. PolicyGuide instead compiles each domain policy into a workflow graph and invokes a proactive verifier at user-turn boundaries. From persisted graph state, the verifier reconciles open requests and returns step-specific remediation along a policy-compliant path. Across the $τ^2$-bench airline, retail, and telecom domains with a GPT 5.4 agent and verifier, PolicyGuide raises mean $\mathrm{Pass}^4$ from $0.42$ to $0.62$, with the largest gain on telecom ($0.19$ to $0.61$), the most workflow-structured domain. The same workflows transfer to Claude Sonnet 4.6 and Gemini 2.5 Pro agents. Complementary evaluations find the lowest observed attack-success rate under adversarial users and the strongest procedural compliance in an independently validated workflow-level audit.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.29225

PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents

Seongjae Kang, Taehyung Yu, Sung Ju Hwang

原文摘要

LLM agents handle user requests on behalf of organizations through tool calls and must follow the company policies stated in their system prompts. Prior work approaches this as a safeguarding problem -- external checks that block non-compliant agent actions. We argue that policy adherence is broader: real workflows unfold across many turns, require explicit user confirmation and prerequisite reads, and hinge on dialogue rather than on any single argument value. We introduce PolicyGuard, a sub-agent verifier that shares the agent's view of the dialogue, reasons over the policy in context, and returns actionable remediation. On $τ^2$-bench airline across GPT 5.4, Claude Sonnet 4.6, and Gemini 2.5 Pro, PolicyGuard improves $\mathrm{Pass}^4$, the fraction of tasks successful in all four trials, by +12.0 / +6.0 / +12.0 pp; pooled paired tests support an overall cross-vendor effect. We further evaluate PolicyGuard on the full retail and telecom base splits, covering all three $τ^2$-bench customer-service domains. Further analyses show that PolicyGuard improves reliability beyond agent self-checking, catches more policy violations with fewer blocks than argument-level guards, and preserves its refusal accuracy under three adversarial probes.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2506.09569

The Rabin cryptosystem over number fields

Alessandro Cobbe, Andreas Nickel, Akay Schuster

原文摘要

We extend Rabin's cryptosystem to general number fields. We show that recovery of a random plaintext from its ciphertext is as hard as the integer factorisation problem, provided the modulus in our scheme has been chosen carefully. We investigate the performance of our new cryptosystem in comparison with the classical Rabin scheme and a more recent version over the Gaussian integers.

cs.CR · math.NT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.29098

UNIVERS: Learning UNIversal Voxel-wise Embedding via Randomized Synthesis for generalizable one-shot landmark localization

Derong Yu, Qingsong Zhao, Yanbing Yue, Yikai Li, Zhi Zhang, Guoyan Zheng

原文摘要

One-shot landmark localization in volume scans with varying fields of view (FOVs) is challenging. While existing self-supervised learning methods have shown promising performance, they rely on contrastive learning built upon augmented views of the same image, which inherently limits their generalization in cross-modality scenarios. This motivates research on cross-modality embedding learning using paired multi-modality images. However, existing methods suffer from not only limited training data, but also the requirement of multi-stage iterative training. To address these limitations, we propose UNIVERS, an end-to-end trainable framework that learns UNIversal Voxel-wise Embedding via Randomized Synthesis. Our framework leverages diverse pseudo-data synthesized from organ shape templates, with randomization applied to semantic layout, visual appearance, FOV, and spatial pose. Coupled with cross-domain discriminative voxel-wise contrastive learning, this domain randomization strategy forces the network to disregard domain-specific biases and learn features that are robust against variations in imaging contrast, resolution, and spatial context. Consequently, the trained model enables one-shot landmark localization in multi-modality volume scans with arbitrary FOVs. In this study, the efficacy of the proposed method is demonstrated by applying it to the task of localizing the adrenal glands, which are paired, small, and irregular endocrine organs. In particular, comprehensive experiments are conducted on three challenging adrenal gland datasets. The experimental results demonstrate that UNIVERS consistently outperforms the state-of-the-art (SOTA) one-shot landmark localization approaches, with particularly prominent advantages in cross-modality scenarios. The source code is publicly available at https://github.com/Kendra9999/UNIVERS.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2312.05586

Generalized Influence Functions for Better Model Change Estimates

Hyeonsu Lyu, Jonggyu Jang, Sehyun Ryu, Hyun Jong Yang

原文摘要

Influence functions (IFs) approximate the effect of removing or reweighting training data on a trained model, but their linear approximation often lacks the accuracy required for reliable post hoc model editing. We identify two culprits and propose generalized influence functions (GIFs) and pseudo-LiSSA (p-LiSSA) to address each in turn. First, classical IFs update all parameters indiscriminately, leading to unnecessary updates to data-irrelevant parameters. GIFs instead restrict edits to a data-relevant subspace and leave the remaining parameters fixed. We theoretically show that GIFs achieve a tighter error bound than classical IFs when the parameter subset is properly selected, and that effective subspace selection requires avoiding low-curvature directions while retaining a sufficiently large component of the target gradient. Second, LiSSA iterations are destabilized by negative Hessian eigenvalues, which existing methods handle via $\ell_2$ damping, at the cost of a biased inverse-Hessian-vector product (iHVP) estimate. p-LiSSA eliminates this bias by solving the restricted inverse-Hessian problem without such damping. We further show that the presence of low-curvature directions slows p-LiSSA convergence, and that the data-relevant subspace selected by GIFs mitigates this. Across five image and text unlearning benchmarks, GIFs update only 10% of the parameters yet preserve accuracy up to 2.12 percentage points better than IF-based baselines, while improving unlearning performance by up to 2.73 percentage points. Moreover, p-LiSSA improves restricted iHVP estimation by reducing the residual by 9.6$\times$ over existing iHVP baselines, while using 19.8% less memory with comparable computation time. Code is available at https://github.com/hslyu/GIF.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2412.18212

Accelerating AIGC Services with Latent Action Diffusion Scheduling in Edge Networks

Changfu Xu, Jianxiong Guo, Wanyu Lin, Haodong Zou, Yuzhu Liang, Xiaowen Chu, Jiannong Cao, Tian Wang

原文摘要

Artificial Intelligence Generated Content (AIGC) has gained significant popularity for creating diverse content. However, current AIGC models primarily focus on content quality within a centralized framework, resulting in a high service delay and negative user experiences. The workload of an AIGC task is determined by model complexity and multi-layered encoder architectures, posing significant challenges for its modeling, deployment, and scheduling within resource-constrained edge networks. We model an offloading problem among edges for providing real AIGC services and propose \textbf{LAD-TS}, a novel Latent Action Diffusion-based Task Scheduling method that orchestrates multiple edge servers for expedited AIGC services by leveraging the diffusion model's conditional guidance capability and the reinforcement learning's environment interaction ability. We first design an innovative Latent Action Diffusion Network (LADN) model based on traditional diffusion models. We then incorporate the LADN model into deep reinforcement learning, forming an effective LAD-TS method for task scheduling in distributed edge networks. Meanwhile, we design a latent action diffusion strategy to achieve near-optimal decisions quickly by utilizing historical action probabilities instead of Gaussian noise. Furthermore, we implement a refined AIGC model and develop \textbf{DEdgeAI}, a prototype edge system with the refined AIGC model deployment to evaluate our LAD-TS method. DEdgeAI provides a real AIGC service for users, demonstrating up to $7.36\%-18.11\%$ and $34.07\%-94.96\%$ shorter service delays than the state-of-the-art methods and representative commercial platforms, respectively. We release our open-source code at https://github.com/ChangfuXu/DEdgeAI/

cs.LG · cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.07779

Flexible Piezoelectric Tactile Sensing System for Intelligent Object Recognition

Razan Khalifeh, Mohamad Yaacoub, Christian Gianoglio, Moustafa Saleh, Maurizio Valle, Yahya Abbass

原文摘要

Tactile sensing provides information about object properties that can improve robotic grasping and manipulation. However, accurate object recognition during the early stages of grasping remains challenging, particularly under strict real-time constraints. This study presents a flexible, distributed piezoelectric tactile sensing system for early-stage object recognition. The system was experimentally evaluated using six everyday objects and three recognition approaches: feature-based classification using support vector machines (SVMs), raw-signal classification using 1D convolutional neural networks (1D-CNNs) and convolutional recurrent neural networks (C-RNNs), and spatiotemporal heatmap classification using a 2D-CNN. The effects of sensor count and temporal window size on recognition accuracy and real-time feasibility were systematically investigated. Increasing the number of sensing elements improved recognition performance across all approaches. The best-performing method, based on spatiotemporal heatmaps and a 2D-CNN, achieved F1-scores of 0.9796, 0.9846, and 0.9903 using 16, 24, and 32 sensors, respectively. The optimal configuration, comprising 32 sensors and a 100-ms temporal window (50 samples), was deployed on an embedded edge platform, achieving an end-to-end recognition latency of approximately 101 ms from contact onset and an energy consumption of 63.8 microjoules per inference. These results demonstrate the potential of distributed piezoelectric tactile sensing for accurate, energy-efficient, and real-time object recognition during robotic grasping.

cs.RO · eess.SP

查看论文
arXiv ↗PDF ↗