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

+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:2026-11-22 06:41 · 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 08:29 — 2026-11-22 08:29(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-22 06:41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

论文修订列表

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 8,992 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 06:39(北京时间)
版本更新 · v2arXiv:2609.36472

DisCoMBO: Steering Expert-in-the-Loop Black-Box Optimization via Distributional Conformance

Jonas Seng, Bennet Wittelsbach, Kristian Kersting

原文摘要

Sequential Model-Based Optimization (SMBO) traditionally relies on Bayesian or ensembling surrogates for uncertainty quantification. While historically treated as fully data-driven, SMBO increasingly integrates external domain expertise to accelerate discovery. To overcome the opaque guidance and diminished integration fidelity of standard acquisition re-weighting, Probabilistic Circuits (PCs) have emerged as a generative surrogate alternative, enabling direct knowledge injection via conditional sampling. However, these generative routines lack the formal exploration-exploitation semantics required for rigorous optimization. We introduce the Distributional Conformance Score (DisCo), a novel metric that unifies the flexibility and efficiency of PCs with a formal uncertainty framework. DisCo provides a bounded, $[0, 1]$-normalized measure of model "surprise" that (1) recovers properties comparable to kernel-based uncertainty known from, e.g., Gaussian Processes, while maintaining linear-time inference, and (2) enables accurate assessment of conformance of external knowledge w.r.t. model evidence. We then present DisCoMBO, a framework leveraging these properties for robust, knowledge-aware optimization. We prove that DisCoMBO is a zero-regret algorithm and demonstrate its effectiveness across diverse benchmarks from AutoML, material optimization, and wind park optimization.

cs.LG

版本更新 · v2arXiv:2605.31177

VaViT: Vanilla ViT for Automotive Point Cloud Semantic Segmentation

Gilles Puy, Nermin Samet, Alexandre Boulch, Spyros Gidaris, Tuan-Hung VU, Renaud Marlet

原文摘要

Plain Transformers have become the de-facto architecture for processing text, audio, image, and video, offering a unified backbone for multimodal learning. However, state-of-the-art architectures for point cloud semantic segmentation remain dominated by U-Nets architectures where convolutions are interleaved with local or windowed attentions. In this work, we show how to effectively leverage vanilla, non-hierarchical ViTs for the segmentation of large-scale automotive lidar scenes. We bridge the performance gap thanks to a carefully designed tokenizer, a lightweight decoder segmentation head, and tailored data augmentations. Our approach, VaViT, for Vanilla ViT, matches or exceeds the performance of state-of-the-art methods while maintaining the simplicity of ViT architecture. We provide extensive evaluations on nuScenes, SemanticKITTI, and Waymo Open Dataset to validate the efficiency of our method. Code and pre-trained models are available at https://github.com/valeoai/VaViT.

cs.CV

版本更新 · v2arXiv:2608.12290

Beyond Trial-and-Error: Agentic Optimization for Image-to-Video Adherence

Aman Tyagi, Hemanth Boinpally, Jonathan Chen, Douglas Gebert, Steven Hickson

原文摘要

Modern black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation, yet their lack of fine-grained control and reliability presents significant challenges in professional workflows. Their inherent stochasticity causes minor variations in textual prompts or hyperparameters to yield drastically different outputs often necessitating inefficient, brute-force trial-and-error processes. To address these limitations, we introduce the ``Agentic Self-Improvement" framework, which reframes video synthesis into a closed-loop, goal-directed optimization. Our framework systematically navigates the generation parameter space using a novel two-stage approach. In the first stage, an iterative prompt optimization loop uses a multimodal Large Language Model (mLLM) to refine the input prompt. This refinement implements two automated evaluations: Davidsonian Scene Graph (DSG) queries ensure semantic adherence, and Common Mistake Questions (CMQ) for artifact detection. At the second stage, we use Bayesian optimization to efficiently co-optimize stochastic seeds and CFG scales. This search is guided by a suite of quality metrics, including the novel Video-Text Adherence (VTA) score derived from the DSG and CMQ evaluations. Our framework significantly outperforms unguided search methods: in human preference studies, videos generated via our agentic approach were strongly preferred over baseline outputs, achieving win rates up to 69\%. This work provides a practical and extensible methodology for enhancing the predictability and control of state-of-the-art video generation models, moving the field beyond speculative curiosities toward reliable, production-ready tools.

cs.CV · cs.AI · cs.MM

版本更新 · v4arXiv:2604.10383

Authoring for Living Worlds: Tool-Constrained LLM Agents for Executable Multi-Actor Scenarios

Nicolae Cudlenco, Mihai Masala, Marius Leordeanu

原文摘要

Authoring a multi-actor scenario for a living 3D world, where every action changes its state, and each action's validity depends on the state accumulated before it, demands the freedom of storytelling and the rigor of simulation at once. We author such scenarios with LLM agents, as Graphs of Events in Space and Time (GESTs) that a simulation engine executes deterministically into narrative videos with per-frame spatial, temporal, and semantic ground truth. A staged pipeline driving a flagship LLM, the standard design in video generation, failed outright: the model violates rules stated verbatim in its prompt, and cannot track the dynamic world state. We answer with a constraint-enforcing tool layer: our Director and Scene Builder agents explore the world's capabilities page by page and build every scene through operations checked against simulator state, so every specification they emit is valid by construction. Because we generate each seed text from an existing scenario graph, we can measure reconstruction: the agent authors its own graph from the text alone, yet matches the original at 0.83 F1 on its events, each action with its participants (0.55 for a random scenario of the same kind), and 0.77 on their ordering (0.43 random). End to end: the standard staged pipeline produced 0 executable specifications in 50 attempts; our agents, driving a budget model, execute 20 of 25 (80%), and are, to our knowledge, the first to exercise the full expressive capacity of GEST.

cs.CV

版本更新 · v2arXiv:2601.07413

Adapting Neural Posterior Estimators for Simulation-Based Inference in Agent-Based Models

Junyao Zhang, Jinglai Li, Junqi Tang

原文摘要

Agent-based models (ABMs) are widely used in economics and social sciences. They represent heterogeneous personal behaviors and their interactions by using simulations, whereas their likelihoods are often intractable for parameter estimations. Therefore, most traditional statistical inference techniques are hindered. Driven by recent advances in probabilistic machine learning, recent works have applied neural networks to achieve likelihood-free inference in large-scale ABMs. Specifically, Neural Posterior Estimation using normalizing flows provide amortized Bayesian inference from simulations, yet a pre-trained estimator may become inaccurate when the target task changes. In this work, we investigate the practicality of adapting a pre-trained conditional normalizing flow through a unified sequential neural posterior estimation test-time training (SNPE-TTT) framework. The framework includes four adaptation strategies: full-parameter adaptation, low-rank adaptation, and two update spaces identified from target-task gradients. We evaluate all four methods across economic simulation models with both tractable and intractable likelihoods. These benchmarks demonstrate that the sequential neural posterior estimation test-time training framework can adapt pre-trained posterior estimators to related inference tasks using a limited budget of target simulations. Posterior recovery and computational benefits depend on the task and adaptation strategy, with lower target-stage cost in some settings but no consistently superior posterior accuracy.

cs.LG · cs.MA

版本更新 · v2arXiv:2605.24155

An Interpretable CF-RL-TOPSIS Fusion Model for Skills-Aware Talent Recommendation

Özkan Canay

原文摘要

Effective skills-aware talent recommendation must balance behavioral transition patterns, trajectory-sensitive adaptation, and inspectable occupation-level criteria. Evidence from public benchmarks on how these signals interact, however, remains limited. This study proposes CF-RL-TOPSIS, an interpretable late-fusion model that integrates a transition-aware collaborative branch, a compact reinforcement-style occupation-family bandit, and an entropy-weighted TOPSIS branch constructed from six semantic proxies; the validation-selected fusion coefficients remain auditable. The model is evaluated on two frozen public ICT talent-history benchmarks, JobHop and Karrierewege, using repeated chronological top-5 ranking and paired Wilcoxon tests. On JobHop the full hybrid attains NDCG@5 = 0.3040 +/- 0.0073 and significantly surpasses repeat-last, item Markov, transition-aware collaborative filtering, the CF+TOPSIS hybrid, GRU4Rec, and SASRec (p <= 0.0039 across planned comparisons). On Karrierewege the hybrid remains competitive but does not significantly exceed the strongest Markov baseline, revealing a persistence-dominated setting in which the bandit branch appropriately shrinks to near-zero weight. Proxy-sensitivity, family-level deep Q-network, and runtime checks support this interpretation, and a worked user-level case shows how branch scores, criterion weights, and rank shifts can be inspected for an individual recommendation. The contribution is not a benchmark-agnostic superiority claim, but a reproducible account of the conditions under which transparent late fusion adds value beyond simple continuation heuristics. In semantically rich, non-saturating talent-history regimes the three branches reinforce one another; in persistence-dominated regimes the same architecture remains competitive through its collaborative backbone, with the adaptive branch correctly inactive.

cs.IR · cs.AI · cs.LG

版本更新 · v3arXiv:2610.27936

From Comparison to Selection: Enhancing Cross-Scale Generalization of Pointer Networks Trained with Reinforcement Learning for Capacitated Vehicle Routing Problem

Sofiene Lassoued, Devara Tertia, Stefan Lier, Andreas Schwung

原文摘要

Vehicle routing in delivery and logistics remains challenging as the number of clients varies. Classical approaches based on mixed-integer programming and heuristics can scale poorly or require problem-specific design, motivating learning-based alternatives. Reinforcement learning is particularly promising, provided a single policy can generalise across problem sizes without retraining. Although attention-based Pointer Networks are inherently size-agnostic, their solution quality degrades under both upscaling and downscaling. Using the Capacitated Vehicle Routing Problem (CVRP) as a controlled proxy, we investigate this degradation and identify three contributing factors: shifts in node density, attention dispersion, and dilution of the mean-pooled graph context. We systematically compare architecture-wide, encoder-side, and decoder-side modifications to address these limitations and propose a learned, permutation-invariant graph-context aggregation mechanism, implemented as a weighted average and as Set2Set. Results reveal distinct requirements for transfer in each direction: entropy-based attention scaling reduces the CVRP20-to-CVRP100 performance gap by 1.41 percentage points, while the proposed aggregation methods achieve the largest improvement on the more challenging CVRP100-to-CVRP20 transfer, approximately 0.9 percentage points. Exploiting this complementarity, we introduce an approach selector that chooses the best model for each training-target size pair. The selector reduces cost relative to the reference model across all nine seen train-test pairs and eight of nine pairs involving unseen sizes (CVRP35, CVRP75, and CVRP200), achieving improvements of up to 3.2%.

cs.AI

版本更新 · v2arXiv:2608.22834

Mirror descent algorithms with logarithmic barriers

Alberto De Marchi, Yura Malitsky, Adrien B. Taylor

原文摘要

We derive convergence guarantees for mirror descent and proximal mirror descent with a logarithmic barrier as the distance-generating function. When the solution lies on the boundary, the Bregman divergence blows up and classical guarantees become vacuous. While existing remedies recover $O(\log k/k)$ rates by adapting classical bounds, we propose a more direct route in which the Bregman distance to the solution never appears, and which achieves the same rate with constant stepsize. We also construct an example showing that this rate cannot be improved in general. Finally, we compare the proposed approach with interior-point methods.

math.OC · cs.LG · math.NA

版本更新 · v2arXiv:2610.17690

MedEvo: Medical Reasoning Evolution through Knowledge Navigation

Xiaoliang Wang, Zhuo Chen, Chuanyang Zheng, Quanbin Wang, Jiangwei Lao, Yingao Liu, Jiajia Liu, Jinming Cao 等 14 位作者

原文摘要

Medical multimodal reasoning models are typically trained on teacher-generated rationales, discarding the valid reasoning in students' own failed trajectories, while general-domain correction methods offer little guidance for errors in image reading, anatomical context, or differential diagnosis. We propose MedEvo, which uses medical knowledge, namely a tag taxonomy and error-type diagnosis, to navigate both trajectory repair and data selection. For each failed rollout, a gold-blind auditor locates the first consequential error and provides a minimal, answer-free hint; the same student retains the valid prefix and regenerates the erroneous suffix. After each round, MedEvo identifies capability gaps across medical tags on a held-out feedback set and prioritizes related questions for new rollouts and repairs. With supervised fine-tuning (SFT) alone, MedEvo raises Qwen3.5-9B mean accuracy across seven benchmarks from 65.57% to 69.12% (47.40% to 54.50% on the multimodal track of MedXpertQA (MedXpertQA-MM)), surpassing teacher-distillation SFT (66.93%). It also raises Qwen3.5-35B and Qwen3.5-397B mean accuracy from 67.91% to 73.04% and from 71.83% to 74.95%, respectively. Our analyses show that failed trajectories contain reasoning worth preserving, that repair success does not imply learning value, and that independent feedback is key to sustained improvement.

cs.AI · cs.CV · cs.LG · q-bio.QM

版本更新 · v2arXiv:2610.22630

Choosing models for network-wide freeway speed estimation and forecasting from sparse fixed sensors

Ran Tu, Zihao Li, Arash Mirzaei

原文摘要

Most freeway agencies have fixed detectors on only part of their network but need speeds for all of it. This paper compares methods for estimating current and next-hour speeds on every link from such sparse detectors, using historical probe data for training. The test network is the Dallas--Fort Worth freeway system: 4,127 directional links, of which 643 (15.6\%) carry a side-fire detector. Eighteen methods from five families (non-learned baselines, statistical estimators, tabular learners, road-graph neural networks and models that learn spatial relations) were trained under one protocol with three random seeds. Each neural architecture was also retrained with a parameter-free, direction-aware kernel interpolation of the sensor readings as additional input. Graph neural networks that pass information along the road graph, including a plain graph convolutional recurrent network, reduced the current-hour error on unsensored links by about 17\% relative to the historical average. Models with adaptive graphs, attention or identity embeddings stayed close to the historical average and did not fit the training data well, indicating that they could not learn which detectors matter for which links. With the interpolation features, all ten architectures came within about 0.1 mph of each other. The remaining error depended mainly on coverage: almost all of the improvement was found within about 3 mi of a detector, and very little on tollways without detectors or on links with no road-graph connection to one. The results are summarised as guidance on model choice and detector placement.

cs.LG · cs.AI

版本更新 · v2arXiv:2609.31418

CognitiveReality: Robot-Agnostic Semantic Gaussian Mapping with an LLM Agent for Immersive Collaborative VR Teleoperation

Timofei Kozlov, Dmitrii Maliukov, Andrey Marchenko, Dmitrii Plotnikov, Miguel Altamirano Cabrera, Dzmitry Tsetserukou

原文摘要

A photorealistic 3D view tells a teleoperator where a robot is, but not what the scene contains, how well each object has been observed, or how to turn pointing and speech into robot action. CognitiveReality turns a robot's RGB-D stream into a live, semantically indexed Gaussian-TSDF map shared by an operator in virtual reality and a tool-using language agent. One mapper binary serves any platform through configuration alone: it ingests poses from robot SLAM, joint kinematics, motion capture or an inline visual tracker, bridges localization outages with a shadow tracker and keyframe-anchored PnP, and maintains open-vocabulary instance identities with per-object quality at 2 Hz. Speech and controller rays are grounded against persistent scene objects through validated typed tools and operator-confirmed robot actions. In the controlled agent evaluation, the deployed local Qwen3-VL-8B router reaches 81.24\% tool exact match, while merge-aware replay correctly redirects 101 absorbed object identifiers. On robot data CognitiveReality exceeds a Gaussian-plus-SDF baseline by 2-8 dB; pose error through 5-40 s SLAM outages stays within 1-8 cm. Deployed live on two quadrupeds, the agent executed 26 of 30 navigation requests and 20 of 20 re-observation requests, raising object quality by 2-5 dB.

cs.RO

版本更新 · v3arXiv:2603.02531

Directional Attention Guidance for Diffusion Models via Sparse Hopfield Retrieval

Kwanyoung Kim

原文摘要

Classifier-Free Guidance (CFG) improves sample quality in diffusion models, but its dual-pass inference and null-condition training limit its use in few-step regimes. Attention-space guidance is a single-pass alternative, yet why sparse-versus-dense attention guidance works remains elusive. We analyze attention extrapolation through Modern Hopfield dynamics and establish two directional properties of the sparse-dense discrepancy under shared conditioning that identify it as an acceleration direction toward the dominant stored pattern. Building on this, we propose Directional Attention Guidance (DAG), a training-free, single-pass rule that amplifies only the component of the discrepancy aligned with the retrieval direction; stability follows from a weak contraction property, and an analysis inside real cross-attention layers shows that this alignment is observed throughout sampling. DAG generalizes across UNet and MMDiT backbones and multi-step and few-step regimes, improving text alignment and human-preference scores on every backbone tested, including FLUX.1, FLUX.2, and Qwen-Image, at a small added cost per image over the base sampler.

cs.LG · cs.AI

版本更新 · v2arXiv:2610.17718

ECG-RSI: Recursive Self-Improvement through Targeted Electrocardiogram Waveform Evolution

Xiaoliang Wang, Zhuo Chen, Chuanyang Zheng, Jiangwei Lao, Quanbin Wang, Honglin Lin, Jiajia Liu, Zhihong Lu 等 12 位作者

原文摘要

Electrocardiogram (ECG) models need supervision that targets evolving weaknesses and remains faithful to waveform evidence. We introduce ECG-RSI, a recursive self-improvement framework combining verified waveform synthesis with feedback-guided intervention search. Signal remeasurement verifies waveform edits; construction errors guide generator repair, while learner errors motivate interventions compared on a separate selection set. Across seven benchmarks, three rounds raise Qwen3.5-35B-A3B's mean question-answering accuracy from 34.57% to 56.04% and mean classification F1 from 24.27 to 34.03. Across the retained trajectory, the preferred supervision shifts from direct reinforcement to confusion-focused contrasts. Continued feedback correction yields diminishing external gains. These results motivate separating error diagnosis from intervention selection and checking whether gains on the feedback set transfer to independent benchmarks.

cs.AI · cs.LG · eess.SP · q-bio.QM

版本更新 · v2arXiv:2604.13812

AlphaCNOT: Learning CNOT Minimization with Model-Based Planning

Jacopo Cossio, Daniele Lizzio Bosco, Riccardo Romanello, Giuseppe Serra, Carla Piazza

原文摘要

Quantum circuit optimization is a central task in quantum computing, as current NISQ devices suffer from error propagation that often scales with the number of operations. Among quantum operations, the CNOT gate is of fundamental importance, being the only two-qubit gate in the universal Clifford+T set. Minimizing CNOT gates is therefore particularly important, as these gates exhibit higher error rates and they typically introduce additional routing overhead due to hardware constraints. The problem of CNOT gate minimization has been addressed by heuristic algorithms such as the well-known Patel-Markov-Hayes (PMH) for linear reversible synthesis (i.e., CNOT minimization with no topological constraints), and more recently by Reinforcement Learning (RL) based strategies in the more complex case of topology-aware synthesis, where each CNOT can act on a subset of qubit pairs. We introduce AlphaCNOT, an RL framework based on Monte Carlo Tree Search that effectively addresses the CNOT minimization problem by modeling it as a planning problem. In contrast to other RL-based solutions, our method is model-based, i.e., it can leverage lookahead search to evaluate future trajectories, thus finding more efficient sequences of CNOTs. Our method achieves a reduction of up to 24.62% in CNOT count compared with the PMH baseline on linear reversible synthesis, and a consistent gate count reduction on different topologies with up to 8 qubits, also with respect to state-of-the-art RL-based solutions. Our results suggest the combination of RL with search-based strategies can be applied to different circuit optimization tasks, thus fostering the transition toward the "quantum utility" era.

cs.AI · quant-ph

版本更新 · v2arXiv:2510.16973

Foundation Models in Medical Image Analysis: A Systematic Review and Meta-Analysis

Praveenbalaji Rajendran, Mojtaba Safari, Wenfeng He, Mingzhe Hu, Shansong Wang, Jun Zhou, Xiaofeng Yang

原文摘要

Recent advancements in foundation models (FMs) have catalyzed a paradigm shift in medical image analysis. Unlike traditional task-specific artificial intelligence (AI) models, FMs leverage large-scale datasets to learn generalized representations that can be adapted to downstream clinical applications. Despite the rapid proliferation of FM research in medical imaging, there is a lack of unified synthesis that systematically maps the evolution of architectures, training paradigms, and clinical applications across modalities. To address this gap, this review provides a comprehensive and structured synthesis of FMs in medical image analysis by systematically organizing studies into two primary categories: vision-only foundation models (VFMs) and vision-language foundation models (VLFMs), based on their architectural foundations, training strategies, and downstream clinical tasks. A quantitative analysis was conducted on both VFMs and VLFMs to characterize temporal trends in dataset utilization and application domains, along with pooled performance and subgroup analyses. We also critically discuss persistent challenges, including cross-domain generalization, computational scalability, FM evaluation, fairness, and deployment. Finally, we identify key future research directions aimed at enhancing the robustness, interpretability, and clinical integration of FMs, thereby accelerating their translation into real-world medical practice.

cs.CV · cs.AI

版本更新 · v2arXiv:2610.07359

Evaluate the Stack, Not the Layer: Do Deterministic and LLM Gates for Agent Actions Fail Independently?

Chenglin Yang

原文摘要

Runtime gates for agent tool calls are stacked on the assumption that their errors multiply. We test it on 1,119 labelled agent actions from three corpora, without an adaptive adversary. The stack has one deterministic rule layer and four LLM judges, three of them re-collected with the served model recorded on every call. We read each stack as a number of multiplication-equivalent layers, n_mult, with its floor under perfect coupling. Under the STRICT miss definition (escalation to a human scored as not stopped), any two judges compose to about 1.2 to 1.4 layers (φ median +0.430, 6 of 6 pairs significant, floors 1.02 to 1.17). The rule layer plus one judge composes to 1.86 to 2.09 layers (φ median +0.014, 0 of 4 significant, floors 1.01 to 1.09). Under PRIMARY (escalation scored as caught) the bands are 1.21 to 1.57 and 1.80 to 2.13. Intervals separate on the pooled data, point estimates split on each corpus, and a third-vendor judge lands in the judge band. Solo accuracy does not predict what a layer adds: a cloud rule pack lowers the rule layer's solo miss rate by 20% and adds no new joint coverage. The difficulty share of judge coupling is not identifiable: 31.8% to 61.8% depending on the probe and the miss definition. One judge tier was served by an unrequested model version in 50 of 112 batches, concentrated on the external corpus. That event overturned a pre-declared analysis rule, and the scoring of review verdicts reversed five conclusions. We report both.

cs.AI

版本更新 · v2arXiv:2610.10235

Beyond LLM-GA: Secure Fluid Antenna Systems with ReEvo-Designed Memetic Algorithm

Hanyong Xu, Zhaolai Dang, Tong Zhang

原文摘要

Fluid antenna systems (FASs) offer significant spatial flexibility, yet securing them against eavesdropping is critical for practical FAS deployment in military, satellite, and internet-of-things networks. Although large language model (LLM)-assisted genetic algorithms (LLM-GAs) can address this secure FAS port selection problem, whether further algorithmic improvement is possible warrants deeper investigation. To this end, we propose a memetic algorithm based on reflective evolution (ReEvo). Unlike the state-of-the-art LLM-GAs, which design only crossover or mutation operators with an LLM, our algorithm leverages an LLM to evolve dedicated crossover, mutation, and local-search operators offline. These operators are then embedded into a memetic search framework, thereby obviating any online LLM queries during execution. Simulation results at equal generation counts demonstrate that our proposed algorithm achieves a higher secure sum-rate than the conventional GA and the state-of-the-art LLM-GAs.

cs.IT · cs.AI

版本更新 · v5arXiv:2610.04906

Scaling Verifiable Environments for Long-horizon Work Agents

Jiazheng Zhang, Long Ma, Yunxian Yang, Zhiheng Xi, Zhikai Lei, Yajie Yang, Chenyang Liao, Enyu Zhou 等 26 位作者

原文摘要

Work agents operate over digital artifacts to execute professional knowledge-intensive work, requiring training environments that support long-horizon interaction and trustworthy verification. However, hand-crafted environments incur prohibitive engineering overhead that prevents environment scaling, whereas synthesis methods sacrifice workspace complexity, realism, or grounded verifiability. To bridge this gap, we introduce WorkForge, a scalable synthesis framework for constructing verifiable work-agent environments from real-world resources. Starting from expert workflows, WorkForge first identifies the resources, decisions, and deliverables required by each workflow. It then retrieves relevant real-world files and organizes them into a workspace. WorkForge inspects the workspace to extract concrete, checkable facts about its content. These factual anchors fix which task types the workspace can support and how their outcomes can be verified. Therefore, WorkForge derives each task's instructions, solution plan, and complementary programmatic and semantic verifiers directly from these factual anchors, keeping verification traceable to observable workspace evidence. Furthermore, we construct 16.7K verifiable environments across 40 professional domains, with workspaces collectively covering 60 file types. Post-training Qwen3.5-35B-A3B-Base improves GDPVal from 45.5 to 73.6 and APEX Score from 5.0 to 21.3, while enabling Qwen3.5-27B to achieve highly competitive performance and outperform strong competitors. Our analyses confirm the efficacy of the proposed method and reveal consistent scaling behaviors across both data volume and interaction horizons.

cs.CL · cs.AI

版本更新 · v2arXiv:2607.26409

Can We Trust AI in 6G? Verifiable and Auditable AI-Driven Trustworthy Wireless Networks

Genze Jiang, Yizhou Huang, Kezhi Wang

原文摘要

Mobile network operators are increasingly exploring the use of artificial intelligence (AI) to automate network tasks such as cell selection and mobility management. Current assurance methods for these AI functions are forms of output testing. They check what a function decides, but they cannot show why it decided that way, and two functions can pass the same tests for different reasons. In this paper, we propose mechanistic auditing, which inspects the internal features of an AI function and checks them against machine-verifiable 3GPP specifications. We set out a three-step auditing principle that locates protocol-relevant features, verifies whether decisions depend on them, and audits each decision against them. We then present an audit-native network architecture. In this architecture, a dedicated verification agent certifies each AI function before deployment and audits its decisions during operation. In a case study on a language model for LTE signalling, we find internal features that carry the 3GPP handover concepts. Removing them lowers the model's accuracy on handover tasks from 96% to 0%, while removing the same number of random features changes its accuracy by less than two points. An audit of a handover decision can therefore check whether these features are active when the model makes that decision. We also discuss the open challenges that remain before mechanistic auditing can enter telecommunications practice and standardisation.

cs.NI

版本更新 · v4arXiv:2608.19842

SAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning

Dayang Liang, Lang Feng, Bo An, Yunlong Liu

原文摘要

Agentic reinforcement learning (RL) has emerged as an important post-training approach for enhancing the capabilities of Large Language Models (LLMs). However, existing methods face a trade-off between policy performance and resource efficiency. Conventional Proximal Policy Optimization (PPO) implementations incur substantial memory overhead from a separate critic, whereas critic-free group-relative methods require multiple rollouts and face potential learning bottlenecks on long-horizon tasks. In this work, we propose Single-rollout Autoregressive Policy Optimization (SAPO), an efficient PPO-style framework that unifies policy optimization and value learning within a single causal language model. SAPO exploits the autoregressive structure of LLMs to sequentially generate action and value estimation at distinct causal boundaries with shared parameters, and then jointly optimizes the PPO objectives and an auxiliary on-policy SARSA objective with turn-level generalized advantage estimation, where the latter is designed to facilitate value learning. Extensive experiments on ALFWorld and WebShop with Qwen2.5-1.5B/7B and Qwen3-14B demonstrate that SAPO reduces peak GPU memory usage by 24.8% and per-iteration runtime by 23.1% over strong PPO baseline, while matching or slightly improving task success rate. Our experiments also show that SAPO outperforms Group Relative Policy Optimization (GRPO) and recent cutting-edge variants in both task success and training stability.

cs.AI

版本更新 · v2arXiv:2605.15592

Efficient Image Synthesis with Sphere Latent Encoder

Tung Do, Thuan Hoang Nguyen, Hao Li

原文摘要

Few-step image generation has seen rapid progress, with consistency and meanflow-based methods significantly reducing the number of sampling steps. Despite their low inference cost, these approaches often suffer from training instability and limited scalability. Sphere Encoder is a recent alternative that produces high-quality images in only a few steps; however, it requires repeated transitions between the pixel space and latent space during inference while jointly optimizing reconstruction and generation within a single architecture. This design leads to computational inefficiency and objective conflict between reconstruction and generation. To address these limitations, we decouple the framework into a fixed pretrained image encoder and a separate latent denoising model trained entirely in a spherical latent space. Our approach eliminates repeated pixel-space operations during training and inference, improving efficiency and allowing reconstruction and generation to specialize independently. On Animal-Faces, Oxford-Flowers and ImageNet-1K datasets, our method significantly outperforms Sphere Encoder in both generation quality and inference speed, while achieving competitive results against strong few-step and multi-step baselines.

cs.CV

版本更新 · v4arXiv:2510.14586

Matcha: Multi-Stage Riemannian Flow Matching for Accurate and Physically Valid Molecular Docking

Daria Frolova, Talgat Daulbaev, Egor Sevriugov, Sergei A. Nikolenko, Dmitry N. Ivankov, Ivan Oseledets, Marina A. Pak

原文摘要

Predicting a protein--ligand binding pose is central to structure-based drug design, yet current docking methods still struggle to combine speed, accuracy and physical plausibility. We introduce Matcha, which refines a ligand pose by three flow-matching stages in translation, rotation and torsion space, then minimizes, filters and ranks candidates with GNINA. Across the benchmarks considered, Matcha attains the strongest physical plausibility and runs about $28\times$ faster than modern large-scale co-folding models. Code and benchmarking artifacts are available at https://github.com/LigandPro/Matcha and archived at https://doi.org/10.5281/zenodo.23568093. Model checkpoints are archived at https://doi.org/10.5281/zenodo.23569055.

cs.LG

版本更新 · v2arXiv:2610.32632

Toward Open ISA Supercomputing: A Comparative Study of RISC-V, Arm, and x86 Architectures on HPC Workloads

Emanuele Venieri, Giacomo Madella, Gabriele Ceccolini, Simone Manoni, Federico Ficarelli, Filippo Barbari, Jenny Lynn Almerol, Elisabetta Boella 等 12 位作者

原文摘要

RISC-V is emerging as a candidate architecture for high-performance computing (HPC), but its competitiveness against established x86 and Arm processors remains difficult to assess because existing studies use different platforms, workloads, and methodologies, and rarely consider energy efficiency. Our work provides an evaluation of contemporary HPC RISC-V, Arm, and x86 processors using a common software stack and methodology. We characterize the Sophgo SG2044 and compare it with the NVIDIA Grace CPU Superchip and Intel Xeon Platinum 8480+ across four HPC benchmarks (STREAM, HPL, HPL-MxP, and HPCG) and four representative applications (iPIC3D, PLUTO, OpenFOAM, and llama$.$cpp). The version of HPL-MxP linked to OpenBLAS built and used for this work is made available as open-source software. The SG2044 reaches 8.02 GFLOP/s of FP64 performance and 7.8 GB/s of memory bandwidth per core, increasing to 294 GFLOP/s and 107 GB/s at 64 cores. L2-cache-aware process placement enables near-linear scaling up to 16 cores, beyond which memory-bandwidth saturation limits further gains. Across generations of RISC-V hardware, in the context of the Monte Cimone (MC) project, the SG2044-based MCv3 doubles both single-core performance and peak memory bandwidth relative to MCv2, while improving memory bandwidth, node-level FP64 performance, and energy efficiency by approximately 100x, 158x, and 10x, over MCv1. Against the Arm and x86 systems, the SG2044 shows 8-15x less absolute performance, reflecting its narrower vector resources and less advanced technology node, but delivers competitive scaling and energy efficiency on several workloads. Its most notable result is LLM decode, where 64-core execution provides the highest relative scaling and energy efficiency among the evaluated platforms while exceeding Intel in throughput. Our results show that RISC-V processors are closing the gap with the competition.

cs.DC · cs.AR · cs.PF

版本更新 · v3arXiv:2610.26872

Commanding at the Speed of Sound: Audio-Centric Referring Expression Segmentation for Aerial Scenes

Ziyun Chen, Yijun Wang, Chuanyi Zhang, Liang Yao, Yuexuan An, Xiang Gu, Wei Zhou, Fan Liu

原文摘要

Referring expression segmentation (RES) aims to localize targets at the pixel level guided by human instructions. However, current models predominantly follow a text-centric paradigm that treats discrete text as the primary interaction medium for these human instructions. This assumption is especially limiting in unmanned aerial vehicle (UAV) applications, where rapid response, hands-free operation, and natural communication are often critical. In this paper, we reconstruct UAV referring expression segmentation through an audio-centric perspective. Grounded in information theory, we demonstrate that raw audio provides a higher upper bound for extracting rich semantic features than transcribed text. To achieve this, we construct an audio-driven UAV referring expression segmentation benchmark named Aerial-AudioRES by augmenting VisDrone with synthesized speech, forming "audio-text-image-mask" quadruples. Specifically, we employ an ambiguity filtering mechanism to ensure referential uniqueness, and incorporate eight distinct timbres alongside 4 realistic noises to simulate authentic environments. To drive the paradigm shift from text-centric to audio-centric, we propose the end-to-end Audio-centric Referring Expression Segmentation Network (ARES-Net). Distinct from discrete text-visual matching, our approach learns to establish a direct soft alignment between continuous acoustic manifolds and multi-scale visual representations. Comprehensive experiments show that our method obtains a peak accuracy of 64.23% in oIoU and demonstrates robust generalization on a collected real-human test set. Furthermore, it significantly reduces total interaction latency to one-third of the text-based method. Our code is available at https://github.com/LemonGauss/ARES-Net.

cs.SD · eess.AS · eess.IV

版本更新 · v2arXiv:2605.00913

Missingness-Conditioned Spatio-Temporal Fusion for Human Activity Recognition from Low-Quality Wearable Sensor Data

Jiangtao Fan, Anish Jindal, Amir Atapour-Abarghouei

原文摘要

Body-worn sensor networks capture human activities through complementary views, where nodes, modalities, and axes partially describe the underlying motion. In real deployments, hardware faults, wireless dropouts, and loose attachments often cause entire channels or nodes to go missing, while environmental interference degrades the remaining signals. The common impute-then-recognize pipeline introduces reconstruction errors that cannot be observed or corrected at inference. We propose the Missingness-Conditioned Spatio-Temporal Network (MCSTN), an end-to-end framework for robust activity recognition under imperfect sensing. MCSTN has three components: a structured imperfection generator that simulates point, temporal-block, axis, modality, and node failures, plus noise at varying signal-to-noise levels; a mask-aware representation that conditions node embeddings, attention, and temporal aggregation on the availability mask; and a complete-to-imperfect multi-view learning scheme where an exponential-moving-average teacher guides multiple degraded student views through semantic consistency. The encoder models temporal and cross-feature dependencies in parallel: a bi-directional selective state-space branch captures long-range temporal dependencies, a transposed-attention branch models cross-channel correlations, and adaptive weights fuse their outputs. At inference, the generator, teacher, and consistency loss are removed, so MCSTN predicts directly from the observed window and its mask without reconstruction or noise-level estimation. On PAMAP2, Opportunity, and WISDM, MCSTN achieves average macro-F1 scores of 94.24\%, 91.67\%, and 96.22\% under imperfect observations, the best among all compared methods on each dataset, and the best in every failure mode on Opportunity. It requires fewer than one million parameters, with 3.78~ms inference latency per sample.

cs.CV · cs.AI

版本更新 · v2arXiv:2510.12337

Sliding-Window Signatures as Features for Time Series Forecasting

Nina Drobac, Margaux Br{é}g{è}re, Joseph de Vilmarest, Olivier Wintenberger

原文摘要

The evolution of a time series is often influenced not only by its past values but also by external covariates, giving rise to forecasting with exogenous variables. Nonlinear and delayed effects between covariates and the target series make this task particularly challenging. We propose a forecasting framework based on Ridge regression with sliding-window signature features, combining the computational efficiency of (semi-)parametric models with the flexibility of nonparametric approaches. These features capture complex dependencies between the target and the exogenous variables without relying on prior assumptions about the form of these relationships or the influence of past observations. We establish theoretical guarantees in the discrete-time setting, including universality of approximation and stationarity for the sliding-window transform. To ease implementation, we introduce a novel sequential algorithm that exploits window overlap for efficient signature updates. The method is evaluated on both synthetic and real electricity demand data. Results show that signature features effectively encode temporal and nonlinear dependencies, yielding accurate forecasts competitive with those based on expert knowledge and recent neural network approaches.

stat.ME · stat.ML

版本更新 · v3arXiv:2605.16879

Towards Generalized Image Manipulation Localization via Score-based Model

Yunfei Wang, Bo Du, Zhe Yang, Xin Liu, Zhiyu Lin, Tianxin Xu, Ji-Zhe Zhou

原文摘要

With the rapid evolution of synthetic media, Image Manipulation Localization (IML) has emerged as a critical component in multimedia forensics for ensuring the integrity of digital content. However, generalization remains a core challenge, as existing discriminative methods typically learn a fixed decision boundary that tends to overfit to specific training artifacts and fails to adapt to unseen manipulation types. To address this, we propose DiffIML, a novel framework that introduces score-based generative modeling to IML. Diverging from the direct estimation of hard boundaries, DiffIML approximates the score function, the gradient of the log-likelihood, to capture the intrinsic geometric topology of mask distributions. This paradigm leverages structural priors to iteratively recover coherent masks from noise, thereby circumventing the brittleness associated with discriminative models. Under this formulation, diffusion models serve as an effective numerical solver for the learned score function.To ensure practicality, we respectively resolve the efficiency and stability bottlenecks of standard diffusion by: (1) utilizing a Lightweight Mask-Specific VAE for fast latent-space process and a decoupled architecture with a lightweight denoising UNet, (2) edge supervision and error prior to mitigate error accumulation during sampling. Extensive experiments of two distinct protocols on eight non-generative and three generative benchmarks demonstrate that DiffIML consistently outperforms state-of-the-art methods, yielding remarkable generalization improvements on diverse unseen datasets. The code is publicly available at https://github.com/scu-zjz/DiffIML.

cs.CV

版本更新 · v2arXiv:2608.09438

Unveiling the Secret of AdaLN-Zero in Diffusion Transformer

Jie Zhu, Mingyu Ding, Boqiang Duan, Leye Wang, Jingdong Wang

原文摘要

Diffusion transformer (DiT), a rapidly emerging architecture for image generation, has gained much attention. However, despite ongoing efforts to improve its performance, the understanding of DiT remains superficial. In this work, we delve into and investigate a critical conditioning mechanism within DiT, adaLN-Zero, which achieves superior performance compared to adaLN. Our work studies three potential elements driving this performance, including an SE-like structure, zero-initialization, and a "gradual" update order, among which zero-initialization is proved to be the most influential. Building on this understanding, we propose an analysis-guided initialization strategy, termed adaLN-Gaussian, which serves both as an empirical validation of our analysis and as a practical initialization method that consistently improves optimization efficiency. On the other hand, inspired by the SE-like structure, we introduce an improved conditioning mechanism called SE-adaLN-Zero. Extensive experiments following DiT on four datasets, especially on ImageNet1K, demonstrate the effectiveness and generalization of adaLN-Gaussian and SE-adaLN-Zero. Beyond class-to-image generation, we also evaluate the generalization of the two improved methods on text-to-image generation.

cs.CV

版本更新 · v2arXiv:2606.09396

PriFT: Guiding Supervised Fine-Tuning with Pretrained Priors

Ke Wang, Shuangqi Li, Mathieu Salzmann, Pascal Frossard

原文摘要

Supervised fine-tuning (SFT) is an efficient approach for downstream task adaptation and often serves as the initialization stage for reinforcement learning (RL), but it can show weaker generalization than RL. A key limitation is its off-policy objective: SFT fits fixed demonstrations token by token, including targets poorly aligned with the model's pretrained distribution, which can lead to overfitting. A recent line of work addresses this issue by assigning larger training weights to tokens better aligned with the current model's predictive distribution, with the intuition that fitting these tokens are less distortive to the model's knowledge and representations. However, computing the token weights from the model that is currently fine-tuned entangles token weights with the optimization trajectory, inducing a self-reinforcing loop which concentrates the supervision signal to a narrow set of initially preferred tokens. To address this, we propose PriFT (Prior-support guided Fine-Tuning), which derives token weights from a frozen pretrained reference to obtain a stable reweighting signal unaffected by fine-tuning. This signal estimates prior support: the extent to which each target token is supported by the pretrained distribution. By reweighting tokens according to their prior support, PriFT limits excessive adaptation to targets requiring substantial deviation from the pretrained distribution and improves SFT generalization. We introduce two instantiations: PriFT-prob uses pretrained target-token probability, while PriFT-mass selects tokens by cumulative probability mass under the pretrained distribution. Across mathematical reasoning, code generation, and medical QA, PriFT achieves state-of-the-art results among SFT baselines, while also providing a stronger initialization for subsequent RL.

cs.CL · cs.LG

版本更新 · v2arXiv:2609.19622

Geometric Gain Graph: Zero-Token Graph Construction for Multi-Hop RAG

Zeliang Li, Xiaofen Xing, Kailing Guo, Wenyu Tao, Xiangmin Xu

原文摘要

Existing Retrieval-Augmented Generation (RAG) systems struggle with multi-hop reasoning due to a fundamental inability to balance relevance and novelty. Traditional dense retrievers are constrained by surface-level matching, falling into a homogenized "Similarity Trap". Conversely, emerging Graph RAGs attempt to explore novel documents via heuristic entity extraction, but they introduce prohibitive Large Language Model (LLM) overhead and easily drift into off-topic "Novelty Traps". To fundamentally resolve this contradiction, we propose Geometric Gain Graph (G$^3$RAG), the novel zero-token graph construction paradigm for RAG. G$^3$RAG completely discards the expensive heuristic extraction by LLMs, aiming instead to directly quantify the information gain between nodes through the native document feature space. To this end, we designed a concise edge weight criterion, $\cosθ\cdot \sinθ$, which naturally maps the trade-off between relevance and novelty into a geometric measurement of directional consistency and orthogonality in the vector space, thereby driving the token-free topological construction of the graph. Furthermore, we introduce a topological penalty to suppress the excessive connectivity of high-frequency hubs, forcing the transient diffusion process toward long-tail peripheral nodes that carry critical indirect evidence. Extensive experiments demonstrate that, while entirely eliminating LLM token costs during graph construction, G$^3$RAG significantly outperforms state-of-the-art Graph RAG baselines on complex multi-hop QA benchmarks. The code is available at: https://github.com/deeplearning-LI/G3RAG

cs.IR