跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

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

统计口径与数据新鲜度

统计 2026-11-21 06:27 — 2026-11-22 06:27(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

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

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 21,490 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
新论文 · v1arXiv:2611.20765

STA: A Split Temporal Adversary Method for Evaluating Robustness of Multimodal RL-based Driving Policies

Shenghao Xiong, Xiaolin Chang

原文摘要

Multimodal reinforcement learning (MRL) offers a promising paradigm for autonomous driving by jointly leveraging complementary sensor observations to learn effective decision-making policies. However, its effectiveness critically depends on temporal alignment across modalities, making temporal inconsistency a fundamental vulnerability. Even subtle misalignment or latency can corrupt fused representations and ultimately lead to decision failures. Existing studies have explored adversarial attacks to induce cross-modal temporal inconsistencies, thereby enabling systematic evaluation of the temporal robustness of MRL policies. However, existing methods remain limited in generality, realism, and adaptivity. To address these limitations, we propose the Split Temporal Adversary (STA), which formulates multimodal temporal attacks as a unified decision process that jointly optimizes attack timing and modality selection under realistic policy-aware and budget-constrained settings. STA includes two mechanisms: a) a unified multimodal temporal perturbation mechanism that delays observations via historical states, removing the need for modality-specific noise; b) a split multimodal adversarial decision mechanism that jointly optimizes attack timing and modality selection through adaptive optimization while leveraging the victim policy's clean actions to identify sensitive decision patterns. We provide a theoretical analysis of the induced distribution shift and a modality selection principle. Experiments in the CARLA simulator show that STA more than doubles the collision rate of the strongest baseline against PPO while using 17.8\% fewer attack attempts, and that it generalizes to a VLM-based driving policy. These results reveal temporal consistency as a critical vulnerability, highlighting temporal robustness as essential for safe autonomous driving.

cs.CR · cs.LG · cs.RO

版本更新 · v2arXiv:2609.11900

MindTopo: Can Foundation Models Reason in Topological Space?

Yunfei Ge, Anbang Liu, Qineng Wang, Johnalbert Garnica, Jianwen Lyu, Zihan Wang, Reuben Tan, Jianfeng Gao 等 12 位作者

原文摘要

Spatial reasoning depends not only on metric properties such as distance, angle, and shape, but also on topological relations that remain invariant under continuous deformation. Cognitive science identifies these relations as foundational to spatial understanding, yet foundation-model evaluations largely focus on metric or viewpoint-dependent relations. We introduce MindTopo, a benchmark of topological intuition across five properties grounded in cognitive science and formal topology, namely continuity, separation, order, enclosure, and knots. MindTopo evaluates each property at two cognitive levels. Reasoning asks a model to identify topological relations or infer how they change. Planning instantiates a foundation model as a closed-loop agent whose policy selects environment actions. MindTopo provides a Core Set of 3,900 instances across 13 procedurally generated task types, split into an Easy and a Hard level, and an Extended Set of 11,035 original instances. On the Core Set, we benchmark 13 multimodal large language models (MLLMs) and study agent configurations augmented with image and video generation, covering seven video generative models in planning settings. Every MLLM performs better on reasoning than on planning. On the Easy level, where human scores are available, the strongest model trails humans in both reasoning and planning. On Qwen3-VL-2B-Instruct, supervised fine-tuning and reinforcement learning improve reasoning more than planning. Generated observations retain local cues and reach solved endpoints, yet none of the 1,890 evaluated video rollouts passes all process-validity checks.

cs.AI · cs.CL · cs.CV

版本更新 · v3arXiv:2410.07158

quanda: An Interpretability Toolkit for Training Data Attribution Evaluation

Dilyara Bareeva, Galip Ümit Yolcu, Anna Hedström, Niklas Schmolenski, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin

原文摘要

Training data attribution (TDA) methods estimate the influence of individual training samples on a model's predictions, offering a principled lens for interpreting neural networks. Despite rapid methodological progress, TDA evaluation remains scattered across papers and rarely reproducible, making fair comparison between methods challenging. We introduce quanda, a Python toolkit that standardizes TDA evaluation. quanda features a comprehensive collection of evaluation metrics and ready-to-use benchmarks spanning image classification, text classification, and language modeling, alongside a uniform interface for integrating diverse TDA implementations. We showcase quanda through a comparative study of existing TDA methods and find that no approach excels uniformly across metrics, with clear trade-offs between ground-truth faithfulness and downstream task performance. By consolidating the tooling around TDA, quanda equips the community to evaluate attribution methods rigorously and reproducibly. The toolkit is thoroughly tested, documented, and available as an open-source library on PyPI and at https://github.com/dilyabareeva/quanda.

cs.LG · cs.AI

新论文 · v1arXiv:2611.20759

Instant Weight-Space Consolidation for Long-Term Memory in LLMs

Manan Suri, Dinesh Manocha

原文摘要

Agentic memory systems give LLMs persistent memory by extracting experience into text and retrieving it at query time, but the model itself does not evolve: however many interactions it has had, it starts each query the same. Extraction errors compound, implicit cross-session patterns that no single fragment states cannot be surfaced, and the construction cost grows with every conversation. Fine-tuning on past interactions does change the weights, but requires backpropagation at serving time and degrades on long histories. We introduce CLAM (Carried Latent Adapter Memory), which combines the strengths of both: a recurrent hypernetwork performs parametric consolidation, compiling a stream of session activations into a low-rank adapter in a single forward pass with no gradient steps and no language-model generation calls, while a complementary episodic buffer supplies verbatim detail at inference. A gated latent state carries knowledge across sessions in fixed size, so the parametric memory accumulates without growing. On LoCoMo and LongMemEval-S across three open models (2-7B parameters), CLAM leads all agentic baselines by 1-45 points and all gradient-based parametric methods by 10-45 points, while requiring zero generative LLM calls, zero gradient steps, and 3-151x less wall-clock time than extraction systems to build its memory. The two channels are complementary: the consolidated adapter adds 12-15 accuracy points when the episodic buffer misses the gold evidence, and still adds 4-5 points even with an oracle buffer.

cs.CL

版本更新 · v2arXiv:2607.18727

Formal Verification of an Out-of-Order Multiprocessor against an In-Order Weak-Memory ISA

Janggun Lee, Jeehoon Kang

原文摘要

Out-of-order multiprocessors are critical components of modern hardware, and their verification is desirable as they are difficult to correct once shipped. Existing literature simplifies and improves instruction set architectures (ISAs) for such processors, but they assume the processor correctly implements the ISA rather than proving it. We present the first formal verification of an out-of-order multiprocessor $\text{Core}_{\text{Impl}}$ against an in-order, weak-memory RISC-V ISA, RISC-V$_{\text{prom}}$. Our central component is $\text{Core}_{\text{InO}}$, an in-order one-instruction at a time core specification, enabling us to confine out-of-order reasoning to a single core. We decompose the main proof into two refinements. The core refinement proves that $\text{Core}_{\text{InO}}$ is a correct specification for $\text{Core}_{\text{Impl}}$. The system refinement shows that RISC-V$_{\text{prom}}$ is a correct specification for multiple $\text{Core}_{\text{InO}}$ connected with shared memory, leveraging the simplicity of $\text{Core}_{\text{InO}}$ in the proof. All of our proofs are mechanized in Rocq, with large language model agents heavily used to automate proof writing. We synthesized $\text{Core}_{\text{Impl}}$ into the Bluespec hardware description language, and validated it produces the intended weak behaviors and adheres to the official RISC-V test suite.

cs.PL · cs.AR

新论文 · v1arXiv:2611.20758

UniGraph: A Unified Graph-based Index for Dynamic Hybrid Dense-Sparse Vector Retrieval

Keyu Chen, Xiaoyao Zhong, Jiabao Jin, Peng Cheng, Wangze Ni, Jingkuan Song, Heng Tao Shen

原文摘要

Hybrid dense-sparse vector retrieval combines semantic signals from dense representations with lexical signals from sparse representations, typically ranking items by a query-dependent weighted sum of dense and sparse vector distances. Existing systems commonly search separate dense and sparse vector indexes and rerank the union of their candidates, incurring two retrieval passes and potentially discarding items that rank highly only after the semantic and lexical signals are combined. Constructing a graph-based index directly under a hybrid distance can mitigate this premature candidate loss. However, because varying the hybrid weight alters the underlying neighborhood relationships, a single static graph built at a fixed weight cannot accommodate dynamic query-specific weights. Therefore, we propose a Unified Hybrid Graph (UniGraph), which merges neighbor sets computed at multiple hybrid weights into a single bounded-degree graph index, enabling hybrid vector retrieval with different query-specific weights without index reconstruction. We further develop an adaptive weight-guided search framework that chooses between sparse- and dense-guided entry points according to the query weight, together with a dense-first hybrid distance pruning strategy that avoids unnecessary exact sparse distance computations. Extensive experiments show that UniGraph provides a favorable Recall-QPS trade-off across different query weights. In the mixed-weight setting, UniGraph delivers 27.6%~52.3% higher QPS than the fastest baseline on each dataset at Recall@100 greater than or equal to 0.95. UniGraph has been deployed at scale in Ant Group's production environment, where hybrid retrieval with query-dependent weights is in strong demand.

cs.IR · cs.DB

版本更新 · v4arXiv:2602.10085

CODE-SHARP: Continuous Open-ended Discovery and Evolution of Skills as Hierarchical Reward Programs

Richard Bornemann, Pierluigi Vito Amadori, Antoine Cully

原文摘要

A core quality of general intelligence is the ability to open-endedly expand and evolve its set of mastered skills autonomously. While recent Foundation Model (FM) driven approaches have shown promising results towards this goal, they typically rely on significant human-in-the-loop engineering, limiting their transferability to novel environments. To address this, we introduce Continuous Open-ended Discovery and Evolution of Skills as Hierarchical Reward Programs (CODE-SHARP), a framework that leverages FMs to open-endedly grow and evolve an archive of Python programs encoding skills to train a generalist agent policy entirely from scratch via reinforcement learning, directly from source code. These programs, termed Skills as Hierarchical Reward Programs (SHARPs), each encode a local success condition and a set of prerequisites delegated to previously discovered SHARPs. At runtime, SHARPs dynamically route the agent through their prerequisite chain based on the current state, rewarding each completion along the way, requiring the agent to learn only the marginal behaviour each new SHARP introduces, enabling efficient learning of long-horizon skills without any pre-defined rewards. On Craftax-Classic and XLand-MiniGrid, agents trained fully autonomously by CODE-SHARP outperform previous works by 6x and 2.7x in median performance and are the only agents capable of crafting iron tools and mining diamonds. On AI2-THOR, CODE-SHARP achieves 66.7% median success versus 0% for ELLM and OMNI, using only the initial environment state instead of the full source code. Scaled to Craftax-Extended, CODE-SHARP trains a generalist agent on over 90 discovered SHARPs, enabling the agent to solve challenging long-horizon tasks zero-shot, matching agents trained on ground-truth rewards.

cs.AI

版本更新 · v3arXiv:2603.05963

Skeleton-to-Image Encoding: Enabling Skeleton Representation Learning via Vision-Pretrained Models

Siyuan Yang, Jun Liu, Hao Cheng, Chong Wang, Shijian Lu, Hedvig Kjellstrom, Weisi Lin, Alex C. Kot

原文摘要

Recent advances in large-scale pretrained vision models have demonstrated impressive capabilities across a wide range of downstream tasks, including cross-modal and multi-modal scenarios. However, their direct application to 3D human skeleton data remains challenging due to fundamental differences in data format. Moreover, the scarcity of large-scale skeleton datasets and the need to incorporate skeleton data into multi-modal action recognition without introducing additional model branches present significant research opportunities. To address these challenges, we introduce Skeleton-to-Image Encoding (S2I), a novel representation that transforms skeleton sequences into image-like data by partitioning and arranging joints based on body-part semantics and resizing to standardized image dimensions. This encoding enables, for the first time, the use of powerful vision-pretrained models for self-supervised skeleton representation learning, effectively transferring rich visual-domain knowledge to skeleton analysis. While existing skeleton methods often design models tailored to specific, homogeneous skeleton formats, they overlook the structural heterogeneity that naturally arises from diverse data sources. In contrast, our S2I representation offers a unified image-like format that naturally accommodates heterogeneous skeleton data. Extensive experiments on NTU-60, NTU-120, and PKU-MMD demonstrate the effectiveness and generalizability of our method for self-supervised skeleton representation learning, including under challenging cross-format evaluation settings.

cs.CV · cs.AI

新论文 · v1arXiv:2611.20755

GPRM: Global Perspective Process Reward Model

Zifan Zhang, Zhengbo Jiao, Shaobo Wang, Jing Zhou, Guoyi Li, Jiayi Chen, Wei Wang, Bing Zhao 等 13 位作者

原文摘要

Process Reward Models (PRMs) are widely used for step-level evaluation of multi-step reasoning in large language models, but existing methods are often limited by weak historical dependency modeling and insufficient global awareness. They typically fail to leverage prior step evaluations for coherent judgment and lack visibility into subsequent reasoning, leading to suboptimal assessment of intermediate steps. To address this issue, we propose the Global Perspective Process Reward Model (GPRM), which jointly models the problem, previous reasoning steps and their evaluations, the current step, and future steps to enable history-aware and globally informed process evaluation. We further introduce a structured evaluation framework along four dimensions---look back, look ahead, self-check, and goal alignment---to assess prior consistency, future plausibility, step validity, and task alignment. Based on this framework, we construct datasets for supervised fine-tuning (SFT) and reinforcement learning (GRPO). Experiments show that, despite using less training data and smaller model sizes, GPRM outperforms strong baseline models by 7.8 and 5.4 points on PRMBench and ProcessBench, respectively. GPRM also generalizes well across tasks, surpassing the GPT-4.1 baseline on Agent Error Bench, improving strong baselines by around 4 points under test-time scaling (TTS), and achieving competitive performance on PPE.

cs.CL

版本更新 · v3arXiv:2604.14548

VoxSafeBench: Not Just What Is Said, but Who, How, and Where

Yuxiang Wang, Hongyu Liu, Yijiang Xu, Qinke Ni, Li Wang, Wan Lin, Kunyu Feng, Dekun Chen 等 12 位作者

原文摘要

As speech language models (SLMs) transition from personal devices into shared, multi-user environments, their responses must account for far more than the words alone. Who is speaking, how they sound, and where the conversation takes place can each turn an otherwise benign request into one that is unsafe, unfair, or privacy-violating. Existing benchmarks, however, largely focus on basic audio comprehension, study individual risks in isolation, or conflate content that is inherently harmful with content that only becomes problematic due to its acoustic context. We introduce VoxSafeBench, among the first benchmarks to jointly evaluate social alignment in SLMs across three dimensions: safety, fairness, and privacy. VoxSafeBench adopts a Two-Tier design: Tier1 evaluates content-centric risks using matched text and audio inputs, while Tier2 targets audio-conditioned risks in which the transcript is benign but the appropriate response hinges on the speaker, paralinguistic cues, or the surrounding environment. To validate Tier2, we include intermediate perception probes and confirm that frontier SLMs can successfully detect these acoustic cues yet still fail to act on them appropriately. Across 22 tasks with bilingual coverage, we find that safeguards appearing robust on text often degrade in speech: safety awareness drops for speaker- and scene-conditioned risks, fairness erodes when demographic differences are conveyed vocally, and privacy protections falter when contextual cues arrive acoustically. Together, these results expose a pervasive speech grounding gap: current SLMs frequently recognize the relevant social norm in text but fail to apply it when the decisive cue must be grounded in speech. Code and data are publicly available at: https://amphionteam.github.io/VoxSafeBench_demopage/

cs.SD · cs.LG · eess.AS

新论文 · v1arXiv:2611.20753

UIAnchor: Anchoring UI Perception and Action Execution for Reliable Service-Composed Mobile Task Automation with GUI Agents

Wentao Zhou, Sicong Liu, Zimu Zhou, Yimeng Duan, Yongyan Cai, Weiye Wu, Teng Li, Daqing Zhang 等 9 位作者

原文摘要

Mobile task automation aims to streamline multi-step, cross-app interactions on smartphones and in-vehicle systems. Recent LLM-based GUI agents have advanced rapidly, yet reliability remains limited because modern mobile workflows are increasingly service-composed (app switching, forms, pop-ups/permissions, copy-paste), requiring fine-grained operations on dense, dynamic, and heterogeneous UIs, often in distraction-sensitive contexts (e.g., hands-busy or attention-limited use). Through an in-the-wild failure analysis of deployable GUI agents, we identify two dominant bottlenecks: agents often miss or misread actionable UI elements, and they execute actions without verifying target correctness or outcomes. We present UIAnchor, a modular multi-agent system that improves mobile GUI automation by anchoring both perception and execution. UIAnchor combines a two-stage UI parser for high-recall element capture and context-aware semantics with a meta-controller that performs pre-action verification, post-action outcome perception, per-step state tracking, and targeted recovery. We further introduce an L1-L5 task taxonomy based on step length, cross-app scope, and UI granularity, showing that L5 remains beyond today's practical frontier. On the hardest practical tier, L4 tasks (20-30 steps, multi-app, targets < 100 x 100 px, ~5 mm on typical phones), UIAnchor improves success by 31.5% over GPT-4o and 16.6% over Mobile-Agent-v3. With edge/cloud assistance, UIAnchor runs at ~2 s per step, comparable to human operation, while reducing per-step latency by up to 75.5% and energy by 52.4%. It also generalizes to unseen apps and cross-platform GUIs.

cs.HC

新论文 · v1arXiv:2611.20752

Who Benefits from Telemonitoring? Uplift Modelling of a Nationwide Home Blood Pressure Monitoring Programme

Connie Kou

原文摘要

Home blood pressure (BP) telemonitoring programmes are being deployed at national scale, yet enrolment resources are finite and the benefit of telemonitoring is unlikely to be uniform across patients. We study the Primary Technology-Enhanced Care for Hypertension (PTEC-HT) programme, a nationwide telemonitoring programme for hypertensive patients in Singapore. Using retrospective data on 16,694 patients registered between August 2020 and May 2024, we first estimate the average treatment effect of the programme on 6-month BP control against a propensity-score-matched non-participant cohort, finding an absolute improvement of 5 percentage points in the rate of BP control (74% vs. 69%, $p = 3\times10^{-12}$), rising to 12 percentage points (63% vs. 50%, $p = 1\times10^{-15}$) among patients with uncontrolled BP at baseline. We then move beyond the average effect and apply uplift modelling to estimate individual treatment effects. Across five uplift learners evaluated with 5-fold cross-validation and Qini curves, an uplift random forest performed best on the full cohort and an S-learner on the uncontrolled-baseline subcohort, although performance bands overlapped across learners. On held-out patients, realised uplift was largest in the top predicted-uplift groups and declined across the ranking. These patients had higher baseline BP grade, more recent hypertension diagnosis and lower medication and diagnosis burden, a profile we offer as hypothesis-generating for targeted enrolment. A handcrafted rule built from these features was competitive with the learned models, outperforming all of them on the uncontrolled-baseline cohort, suggesting that uplift models are useful for discovering heterogeneity that can be distilled into simple enrolment criteria for directing limited care team capacity.

cs.LG

版本更新 · v2arXiv:2610.10044

CANDO: Cooperative Agentic Network for Layout Design Optimization

Athanasios Masouris, Zheng Jing, Benjamin Sam Chandler, Hadi Jamali-Rad

原文摘要

Layout generation for real-world facilities is a challenging problem, requiring reasoning over irregular site boundaries, heterogeneous orientations, access-aware placements, and motion-planning feasibility. Yet, most existing layout benchmarks in the generative AI space target simpler placements over rectangular domains and rely on distributional metrics such as FID and IoU that reward conformity to dataset priors, thus discounting design innovation. Motivated by these gaps, we introduce ALPS-Bench, a benchmark of $1,000$ professionally annotated real-world facility layouts paired with an instance-specific scoring protocol grounded in a structured design manual. As a strong baseline for ALPS-Bench, we propose CANDO, a training-free multi-agent framework in which specialized agents iteratively refine layouts through a verification-grounded loop, concentrating reasoning on strategic spatial decisions. We demonstrate that CANDO surpasses state-of-the-art trained and LLM-based baselines on the widely adopted PubLayNet, RICO, and PKU-PosterLayout benchmarks, establishing cooperative agentic design as a broadly effective recipe for constraint-aware layout synthesis. Code and benchmark are available through our project page: https://shell-oss.github.io/cando/

cs.MA

版本更新 · v2arXiv:2609.00883

iPINN for Broadband CARS Phase Retrieval: A Framework for Function Approximation and Inverse Modeling Problems in Nonlinear Spectroscopy

Ravi Teja Vulchi, Carl Messerschmidt, Mohammadsadegh Vafaeinezhad, Rajendhar Junjuri, Tobias Meyer-Zedler, Juergen Popp, Thomas Bocklitz

原文摘要

Broadband coherent anti-Stokes Raman scattering (BCARS) records chemically specific vibrational spectra, but the measured signal mixes the resonant, Raman-like response of the sample with a non-resonant background that changes from one measurement to the next. Recovering the resonant response, known as phase retrieval, is an ill-posed inverse problem. We present iPINN, an inverse physics-informed neural network that predicts the positions, amplitudes, and widths of Lorentzian vibrational bands directly from a BCARS spectrum. A transformer network estimates these band parameters, and a differentiable analytical model of the resonant susceptibility rebuilds the Raman-like spectrum from them as a sum of physically defined bands. We train the network on simulated spectra in which the bands of each reference compound stay fixed while the shape and strength of the background and the noise vary. Training also encourages similar band predictions for the same compound across these variations. On a public benchmark of toluene and dimethyl sulfoxide spectra, the network reached a mean absolute error about one third of that of the best of five deep-learning baselines. Its error for dimethyl sulfoxide stayed nearly constant across three noise levels. We also used 28 spectra of seven solvents, recorded at four focal depths with different background strengths. For five of the seven solvents, the mean absolute error changed little with depth, while it varied more for the other two. These results indicate that this approach keeps phase retrieval stable for most of the tested solvents when the background changes.

cs.LG · physics.data-an

版本更新 · v2arXiv:2608.08049

Parameter-Dependent LMI Synthesis for Semi-Global Differential ISS Trajectory Tracking of Nonholonomic Mobile Robots Under Multiplicative Wheel Slip

Mohammad Sabouri

原文摘要

This paper presents a parameter-dependent linear matrix inequality (LMI) synthesis framework for trajectory tracking of nonholonomic mobile robots subject to multiplicative wheel slip. A sampled polytopic convex formulation jointly targets four design objectives on the variational dynamics in Kanayama coordinates: a prescribed exponential decay rate, an H-infinity disturbance-to-error gain, regional pole placement, and a weighted gain bound acting as a design-time actuator budget. The inverse metric and the auxiliary gain are parameterized affinely in the reference linear and angular velocities. A Slip-to-Disturbance Lemma provides an explicit closed-form upper bound on the additive disturbance equivalent to bounded multiplicative wheel slip in Kanayama coordinates, connecting the physical slip mechanism to the convex synthesis. The dissipation inequality is established at the sixteen vertices of the parameter-rate polytope, and a Lipschitz-based residual condition is given as a sufficient criterion for extending feasibility to interior points; the regions where the criterion succeeds for the synthesized controller, and where it does not, are both reported. An integral representation of the Kanayama residual lifts the variational certificate to a pointwise exponential-plus-ISS bound on the trajectory error directly from the LMI. The certified envelope is the semi-global ball at sigma_bar = 0.10; variable-terrain tests at slip ratios up to plus-minus 50% are reported as empirical observations outside that envelope. In the certified regime, the LPV controller and a fixed-gain LMI baseline produce quantitatively similar tracking records; on the severe-slip probes, the parameter-dependent design retains modest reproducible margins over both the fixed-gain and the classical Kanayama baselines.

eess.SY · cs.RO

版本更新 · v2arXiv:2610.16656

RFWeave: Generalizable Wireless Propagation Prediction Across Scenes and Transceiver Configurations

Shurui Xu, Xiao Ye, Yijie Bian, Junjie Ai, Yuxuan Chen, Weicong Chen, Wei Guo, Wankai Tang 等 10 位作者

原文摘要

Wireless propagation modeling is foundational to the evaluation and design of modern communication systems. While recent learning-based methods have shown promising generalization across transceiver positions and unseen scenes, they remain largely confined to a fixed configuration of array size, receiver orientation, and transmit beam. In this work, we introduce RFWeave, a unified feedforward model for wireless propagation prediction across scenes, transceiver positions, and transceiver configurations. Its core innovation is a flexible antenna representation that accommodates varying array structures while capturing spatial relations between transmitter and receiver elements. Our conditioning mechanism allows the model to use a shared Transformer backbone across diverse transceiver configurations, enabling joint prediction of received power and the angle-of-arrival spatial spectrum. Trained on a large-scale simulated dataset spanning 10,000 indoor scenes and more than 5 million channel records, RFWeave achieves state-of-the-art performance across a wide range of generalization settings, improving spatial spectrum structural similarity by up to 15.6% and reducing received power mean absolute error by up to 35.4% over the strongest baselines on unseen scenes. Additional experiments on measured DICHASUS data and in beam management further demonstrate RFWeave's broader applicability to real-world channels and downstream wireless tasks.

eess.SP · cs.LG

版本更新 · v2arXiv:2501.13946

Hallucination Mitigation using Agentic AI Natural Language-Based Frameworks

Diego Gosmar, Deborah A. Dahl

原文摘要

Hallucinations remain a significant challenge for Generative AI, undermining trust in AI systems and their reliability. This study investigates how orchestrating multiple specialized AI agents can mitigate hallucinations, with a focus on systems that use Natural Language Processing (NLP) for agent interaction. We design a pipeline that feeds 310 prompts, purposefully crafted to induce hallucinations, into a front-end agent; its outputs are reviewed and refined by second- and third-level agents that detect unverified claims, add explicit disclaimers and clarify speculative content. We introduce four novel Key Performance Indicators (KPIs) - Factual Claim Density, Factual Grounding References, Fictional Disclaimer Frequency and Explicit Contextualization Score - aggregated into a Total Hallucination Score (THS) and assessed by a dedicated fourth-level evaluator agent. Inter-agent context is carried by the Open Floor Protocol (OFP, formerly OVON, Open Voice Network), whose structured JSON messages let each reviewer pass its assessment of hallucination likelihood, and the reasons behind it, to the next stage. Across the 310 prompts, THS improves by a mean of -0.131 per prompt from the front-end agent to the final reviewer (Cohen's d = 2.38), with lower scores on 302 of 310 prompts. The gain is carried mainly by explicit disclaimers and contextualization, making speculative content more transparent and clearly demarcated from factual claims. The results show that multi-agent orchestration with structured, NLP-based exchange of meta-information can substantially strengthen the epistemic framing of AI-generated responses and improve their explainability.

cs.CL · cs.AI · cs.MA

新论文 · v1arXiv:2611.20745

A Seismic Foundation Model for Dense Feature Extraction

Zhixiang Guo, Xinming Wu, Yimin Dou, Hui Gao, Siyao Zhao, He Huang, Wei Liu

原文摘要

Deep-learning-based seismic interpretation is constrained by scarce high-quality annotations, and most existing models are trained separately for individual tasks. We present SeisDFE, a 7B-parameter seismic foundation model for dense feature extraction, pretrained on 5.34 million 2D images derived from more than 500 seismic volumes. A three-stage pretraining strategy, combining discriminative self-supervised learning, Gram feature anchoring, and multi-resolution adaptation, improves feature discriminability while preserving spatial coherence. With its encoder frozen, SeisDFE supports seismic facies classification, salt detection, fault detection, and relative geologic time estimation. It outperforms existing seismic foundation models on all four tasks and a natural-image-pretrained model on all but fault detection, with the largest gains under scarce supervision: using only two annotated sections of the F3 dataset, it improves whole-volume mIoU by 12-19 percentage points over the baselines. The learned features remain effective with task-specific decoders and extend to synthetic-to-field transfer and sparse 3D geobody interpretation. These results show that large-scale seismic pretraining organizes geological information into dense representations that are directly reusable across interpretation tasks.

cs.CV

新论文 · v1arXiv:2611.20741

Robotic Reward Models in the Foundation-Model Era

Guoqiang Liang, Yiqi Lin, Shangchen Zhou, Wenzheng Zeng, Yanzhe Chen, Zechen Bai, Mike Zheng Shou

原文摘要

Robotic reward models (RRMs) use foundation models to replace per-task reward engineering with reusable, task-conditioned evaluation. Yet under one name, their outputs answer different questions, from whether a task succeeded to which execution is better. This survey organizes 114 methods into five semantic families by the question their native outputs answer: Outcome, Absolute Progress, Relative, Temporal Value, and Hybrid. Within this taxonomy, we review how model design determines what an evaluator can judge, how raw experience becomes supervision, and how existing evaluation practice tests the result. The review exposes a gap: agreement with demonstration order and downstream policy gains do not show whether a reward tracks task fulfillment. We therefore introduce RRM-Bench-1K, 1,117 real-robot videos of closed-loop executions with task-state and camera-evidence labels, and four contrast suites that separate the credited condition from its usual cues. A unified study of 27 evaluators shows that the strongest final scores rank whole executions well enough for selection and filtering. Dense credit, however, follows the progression of an execution more closely than its task state, and no evaluator signals when the decisive view is missing. How much fidelity a reward model needs therefore depends on the decision it drives. We outline directions from real-failure supervision to metrics that separate task state from chronology, and open-source RRM-Hub, a toolbox in which 14 existing RRMs can be readily applied and new evaluators tested on the same capabilities.

cs.RO · cs.CV

版本更新 · v5arXiv:2610.02236

Cartesian Byte-Bank Models and Warp Lag Screening for GPU Lossless Compression

Zeyu Jia

原文摘要

Headerless multi-channel 16-bit streams degrade unit-lag differencing, byte shuffling, and chunked GPU codecs when adjacent words belong to distinct sensors. On even-length 16-bit tiles (<= 16 MiB), GPX6 pairs a 32-lane CUDA warp lag screen with a threshold-free 3 x 2 Cartesian conditional byte-bank range Asymmetric Numeral Systems (rANS) coder and OpenMP Zstandard-1 framing. Across 30 subject-disjoint waveform files (88.90 MB, N = 27 subjects), GPX6 compresses to 26,449,754 B (29.75% aggregate; 42.68% subject mean; 40.74% six-cohort mean across 338.25 MB) at 424.1/279.0 MB/s host-to-host on RTX 4080 Laptop GPU and 266.9/166.4 MB/s on A100-80GB, reaching 474.1/482.3 MB/s (4.81/5.98 GB/s resident) on 30-tile A100 batches. Completing GPX4 into GPX6 saves +2.59 pp subject mean, localized to step-quantized BIDMC telemetry (+6.24 pp vs. +0.20 pp on smooth cohorts). Under 1-payload screening, GPX6 saves +10.59 pp ([+8.09, +13.28] pp) over faster zero-order GPU nvCOMP ANS, beats 16-bit MANS and 64 KiB nvCOMP Zstd (2.17x-2.49x faster encode), and maps CPU, audio, and 2D boundaries.

cs.AR

版本更新 · v2arXiv:2611.17442

Racing the Clock: Teaching VLNs Budget-Conditioned Object Search

Maitree Meher, Siming He, S. Shankar Sastry, Jitendra Malik, Claire Tomlin, Jonas Frey

原文摘要

How do action budgets shape vision-language navigation (VLN) exploration, and what expert supervision best teaches budget-aware search? We study budget-conditioned object search: finding as many distinct instances of a requested category as possible within a budget, with discovery defined geometrically by camera field of view and proximity. Distinct discoveries provide a denser evaluation signal than single-target success. We cast expert design as a choice of scene abstraction: a single budget-indexed Bellman recursion, applied to different abstractions of the full environment, yields experts that differ in what they know. An object-level Bellman expert is given every target location and reduces search to budgeted routing. A room-level Bellman expert retains observed room connectivity, doorway evidence, and cross-scene semantic priors but withholds the contents of unexplored rooms, so it must search for targets that its student also cannot see. We distill both experts into Uni-NaVid under matched training conditions and also evaluate greedy-frontier supervision on held-out HM3D scenes. Changing only the stated budget changes learned trajectories. Despite higher object-level expert return, room-level supervision achieves the highest mean collection among evaluated VLNs at every tested budget. At 2000 steps, it finds 72.7% of reachable targets, versus 68.5% under greedy-frontier supervision, 65.5% under object-level supervision, and 44.8% for the pretrained VLN. These results show that expert-return rankings need not predict supervision quality for VLN exploration, and motivate choosing an expert's abstraction with the student's information in mind rather than by expert return alone.

cs.RO · cs.AI · cs.CV · cs.LG

版本更新 · v2arXiv:2607.05133

UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation

Mengmeng Liu, Diankun Zhang, Jiuming Liu, Jianfeng Cui, Hongwei Xie, Guang Chen, Hangjun Ye, Francesco Nex 等 10 位作者

原文摘要

World Action Models (WAMs) can improve action generalization in autonomous driving by learning scene dynamics through dense future-video supervision. However, deploying such models often requires costly future-video generation, while architectures that bypass video rollout typically separate video and action parameters or alter their learned dependencies at inference. We introduce UNIVERSE, a unified video-action model built on a single mask-modulated Diffusion Transformer (DiT) that combines shared-parameter learning with modality-independent inference. Its Modality-Decoupling Visibility Mask allows future video and trajectory tokens to attend to a common historical context while blocking mutual attention between the two future modalities. As a result, future-video supervision directly updates the parameters used for trajectory denoising, yet video tokens can be omitted at test time without changing the trajectory branch's training-time attention dependencies. The same model supports trajectory-only, video-only, and joint video-action generation. Trajectory-only inference achieves a 4.3x speedup over coupled video-action rollout with comparable planning accuracy. UNIVERSE achieves 91.0 PDMS on NAVSIM, compared with 89.6 for a Two-DiT variant, and demonstrates strong zero-shot transfer to nuScenes and Bench2Drive without target-domain fine-tuning. Controlled ablations further support the complementary benefits of shared parameters, dense video co-training, and modality-decoupled visibility.

cs.CV

新论文 · v1arXiv:2611.20737

CLIFT: Contrastive LiDAR Instance Features for 3D Pedestrian Tracking

German Devchich, Timur Akhtyamov, Denis Fatykhoph, Gonzalo Ferrer

原文摘要

A social robot has to keep track of the people around it over time to plan its motion, a task handled by 3D multi-object tracking. For the LiDAR modality, trackers usually sit on top of a detector and link its detections across frames with a separate motion model or re-identification network. We instead show how a 3D LiDAR detector itself can be turned into a tracker by adding an instance-level contrastive objective on its intermediate voxel features. Each embedding is read from the voxels inside a detected box, and boxes are matched across frames by cosine similarity and the Hungarian algorithm, without a motion model. The detector backbone is fine-tuned together with this objective, which learns identity-aware features while leaving detection accuracy essen- tially intact. Because the method uses only the voxel features that Li- DAR detectors already produce, it is backbone-agnostic. On the JRDB 3D tracking leaderboard our LiDAR-only tracker ranks first on HOTA (38.58) and IDF1 (37.99), 13.04 and 9.30 points above the next pub- lished method, and second on MOTA and OSPA. Code is available at https://hermak56.github.io/CLIFT/.

cs.CV

新论文 · v1arXiv:2611.20736

GainCtrl: Predicting Remaining Gains for Efficient LLM Agent Execution

Kangwen Zhao, Jianfeng Cai, Ruopei Sun, Mingxiao Feng, Peng Zhang, Wengang Zhou, Houqiang Li

原文摘要

Large language models (LLMs) are widely used to power agents that interact with tools and environments to solve complex tasks. Repeated attempts improve the quality of tool-using agents, but continued execution incurs additional costs even when it is unlikely to improve the best result ultimately returned. This raises the question of when to stop an attempt to reduce execution cost while preserving task-level Best-of-N quality. To address this question, we introduce GainCtrl, a gain-based execution controller for LLMs. In GainCtrl, a lightweight CPU predictor uses interaction histories to estimate expected positive gains over retained scores, which are then used to guide stopping decisions with calibrated thresholds to limit the loss in mean Best-of-N task quality. We evaluate the controller through trajectory replay across three environments and three LLM actors. Comparisons of interpolated quality-cost Pareto frontiers show that GainCtrl generally uses fewer tokens than baselines at matched target quality. Fixed policies also achieve quality close to that of full execution while substantially reducing token consumption. The predictor runs at millisecond latency on a single CPU thread, supporting repeated monitoring without access to LLM internals.

cs.AI

新论文 · v1arXiv:2611.20734

Can LLMs Give Good Product Advice? A Framework for Diagnosing Failures

Assaf Hallak, Yftah Ziser, Gal Chechik

原文摘要

Evaluating product advice from a language model requires assessing whether the recommendation meets the user's needs and identifying where the model falls short when it does not. However, matching a product mentioned in an online reply cannot answer either question on its own: several products may be suitable, and the recorded answer may itself be poor advice. When shown a community-listed alternative alongside their own sampled car recommendation, six models prefer the alternative in 1.9 to 6.5 percent of eligible disagreements, consistently across both source-blind presentation orders. We propose a diagnostic framework that separates the user's stated needs, the model's added assumptions, candidate generation, filtering, and final choice, with 19 possible failure modes and the evidence needed to assess them. We apply this framework to product-advice data and to a separate product-selection task with externally assigned relevance labels. The experiments distinguish naming a community-listed product from selecting it and show how answer extraction and candidate-list construction affect the outcome.

cs.CL

新论文 · v1arXiv:2611.20730

Selective Sensor Acquisition for Multimodal Place Recognition

Margaux Edwards, Tobias Fischer, Michael Milford

原文摘要

Multimodal Place Recognition (PR) can improve robustness, but most systems rigidly read and process every sensor for every query, even when the primary sensor is sufficient, with implications for energy consumption, second sensor update rate, and domain-specific considerations such as passive stealth. We introduce selective, controllable sensor acquisition, where a user specifies a desired second sensor usage rate and the system acquires the additional sensor only when the primary sensor's estimated performance is sufficiently poor. An online threshold adjustment achieves the requested usage rate by adapting to recent primary sensor performance, directing additional sensing towards queries where fusion is most likely to help without calibration specific to sensor modality, PR method, or environment. The approach requires only a PR method that produces a match score and applies to both single-frame and sequence-based PR. Our system, across multiple datasets, PR descriptors, and sensor combinations, recovers 55% of the available PR performance gain while using the second sensor on only 25% of queries, and 81% while using it on 50%. We further analyse alternative acquisition decision mechanisms and usage-rate control methods, and examine performance when the second sensor is stronger than, comparable to, or weaker than the primary sensor.

cs.RO · cs.CV

版本更新 · v2arXiv:2605.09636

PDEAgent-Bench: A Multi-Metric, Multi-Library Benchmark for PDE Solver Generation

Zhen Hang, Yushan Yashengjiang, Junhui Li, Huanshuo Dong, Yang Wei, Zhezheng Hao, Jiangtao Ma, Songlin Bai 等 24 位作者

原文摘要

PDE-to-solver code generation aims to automatically synthesize executable numerical solvers from partial differential equation (PDE) specifications. This task requires not only understanding the mathematical structure of PDEs, but also selecting appropriate discretization schemes and solver configurations, and correctly implementing the resulting formulations in finite-element method (FEM) libraries. Existing code generation benchmarks mainly evaluate syntactic correctness, or success on predefined test cases. To our knowledge, there is currently no publicly available benchmark specifically for PDE-to-solver code generation, and general-purpose code benchmarks do not fully capture the unique challenges of numerical PDE solution, such as ensuring solver accuracy, efficiency, and compatibility with professional FEM libraries. We introduce PDEAgent-Bench, to the best of our knowledge, the first multi-metric, multi-library benchmark for PDE-to-solver code generation. PDEAgent-Bench contains 645 instances across 6 mathematical categories and 11 PDE families, with common FEM libraries for DOLFINx, Firedrake, and deal.II. Each instance provides an agent-facing problem specification, a reference solution on a prescribed evaluation grid, and case-specific accuracy and runtime targets. PDEAgent-Bench adopts a staged evaluation framework in which generated solvers must sequentially pass executability, numerical accuracy, and computational efficiency checks. Experiments with representative LLMs and code agents show that models can often produce runnable code, but their pass rate drops substantially once accuracy and efficiency requirements are enforced. These results indicate that current agents remain limited in producing numerically reliable and efficient PDE solvers, and that PDEAgent-Bench provides a reproducible testbed grounded in the practical requirements of numerical PDE solving.

cs.AI

新论文 · v1arXiv:2611.20728

ANCHOR: Cluster-Grounded 5W1H Extraction via Large-Small Model Collaboration

Hongyu Jiang, Chenang Cai, Lei Gao, Zhao Kang, Ling Tian, Jinchuan Zhang

原文摘要

Deep semantic understanding of events requires recognizing related events and distinguishing why an event occurs from how it is carried out. 5W1H extraction provides a structured foundation for such understanding by organizing event information around six fundamental questions. However, single-event slot filling provides limited support for these distinctions. We propose ANCHOR, a cluster-grounded framework that combines a large language model (LLM) with a small language model equipped with discriminative heads for accurate 5W1H extraction. The LLM proposes candidate events and generates their initial 4W records, which guide the selection of an event cluster and the subsequent anchoring of its main event. A shared document encoder provides evidence for joint 4W refinement, and two separate sets of boundary and role-scoring heads then extract why and how under event-specific constraints, respectively. Document representations are reused across events and stages, and unsupported roles can remain empty. Following the same principles, an agent-and-skill annotation workflow constructs a benchmark of 26,110 documents from ten source corpora covering three languages and seven domains. We select nine of the resulting datasets to evaluate ANCHOR against strong baselines using four open-weight LLMs. ANCHOR achieves competitive performance. The datasets and code are available at https://github.com/revolution6575/ANCHOR-5W1H.

cs.CL

新论文 · v1arXiv:2611.20726

PEETS: Preference-aware Embeddings with Explicit Tree Structure for Auxiliary Product Bundling

Maolei Huang, Jing Tian, Dexuan Duan, Yan Chen, Huawei Cao, Shuhan Song

原文摘要

Auxiliary products such as flight protection and flexible-change services are recommended alongside primary travel purchases. This setting creates a granularity ambiguity: SKUs within one product type share semantics but differ in price and coverage, while rejecting one offer does not imply disinterest in the entire type. We present \textbf{PEETS} (\textbf{P}reference-aware \textbf{E}mbeddings with \textbf{E}xplicit \textbf{T}ree \textbf{S}tructure), a training-time framework for auxiliary product bundling. PEETS regularizes an existing click--conversion predictor through two conditional comparisons. Hierarchical Contrastive Loss uses the pair's common ancestor as a reference; Negative Contrastive Loss conditions structural sampling and comparison shifts on logged rejection events. Both act on shared SKU representations during training. This separates catalog relatedness from individual preference supervision and leaves the predictive serving path intact. PEETS achieves 78.20\% AUC, exceeding TWIN V2 by 0.90 percentage points and the matched base model by 1.15 points. In a 14-day online evaluation, gross auxiliary GMV per exposed user-day improves by 8.20\% over Policies, 3.06\% over Base, and 0.84\% over TWIN V2, with all three user-bootstrap 95\% intervals above zero. Bundling rate is 0.51 points below Policies. The cancellation interval's upper limit exceeds the prespecified margin. PEETS adds no auxiliary-loss computation to serving and records 42.1~ms p95 latency, compared with 42.0~ms for Base.

cs.AI

新论文 · v1arXiv:2611.20722

Scaled boundary finite elements for FFT-based computational micromechanics

Flavia Gehrig, Carolin Birk, Matti Schneider

原文摘要

We introduce a matrix-free FFT-based solver for three-dimensional linear elastic homogenization problems discretized by the scaled boundary finite element method (SBFEM) on a voxel grid. Owing to its analytical solution in the radial direction, the SBFEM discretization is inherently softer than fully integrated voxel finite elements, whereas its displacement-based formulation remains symmetric, conforming, and supports arbitrary stiffness anisotropy. These properties make SBFEM an attractive candidate for porous and highly heterogeneous microstructures, where existing voxel-based FFT discretizations offer no generally reliable choice: Reduced-integration hexahedral elements, equivalently the rotated staggered grid discretization, may suffer from hourglass instabilities in the presence of voids, whereas fully integrated hexahedral elements are often too stiff. The proposed discretization uses hexahedral SBFEM cells on the full voxel mesh of a regular periodic grid, retaining the simplicity of a fixed-resolution voxel representation without requiring adaptive mesh coarsening. The main contribution is a preconditioner based on the homogeneous SBFEM stiffness operator. We show that this preconditioner may be applied locally in Fourier space and that the condition number of the preconditioned system is bounded by the material contrast, independently of the grid resolution. This result enables a fully matrix-free implementation of the SBFEM-discretized problem, without assembling or storing the global stiffness matrix. Numerical experiments on a short-fibre reinforced composite, a polyurethane foam and a sand-based binder jet microstructure demonstrate robust convergence and competitive accuracy compared with established voxel discretizations. In particular, SBFEM remains stable for porous microstructures, for which reduced-integration hexahedral elements become unstable.

cs.CE · math.NA