跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 16:31 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 18:11 — 2026-11-09 18:11（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-09 16:31最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 02:59

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

18,172 已收录论文15,506 AI 相关4,527 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 18,172 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 16:29（北京时间）
新论文 · v1arXiv:2610.37021

Ground-to-Satellite Knowledge Distillation for Crop Classification under Temporal and Geographic Shift

Miro Miranda, Rocco Sedona, Valerio Marsocci, Gabriele Cavallaro, Claudia Paris

原文摘要

Continuous and up-to-date crop type mapping is essential for agricultural monitoring but is often hampered by limited reference data. The growing availability of ground-level field photographs offers a promising way to address this challenge. When combined with satellite time series, these images provide complementary perspectives on the same parcel, capturing crop characteristics from distinctly different perspectives. However, field photographs are not always available for each satellite pixel at inference time, limiting their potential in scalable crop type mapping. We investigate whether ground photographs can provide privileged supervision for crop classification built on pretrained satellite embeddings. A photo teacher based on frozen CLIP features supervises classifiers trained on AlphaEarth and TESSERA representations; photographs are used only during training. On a paired field photo and satellite imagery dataset with 17 crop classes, knowledge distillation consistently improves over satellite-only classification; for frozen embeddings the margin grows under temporal shift, reaching up to +5.5 macro-F1 points, and widens in geographic holdouts (+3.7 vs +3.0 in-distribution). These results show that ground-view supervision can complement satellite embeddings and improve their robustness without changing inference requirements.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.29433

Exploiting Pinching Antenna Systems in NOMA Covert Communication Networks

Xinwei Yue, Hao Li, Jingjing Zhao, Xianfu Lei, Yuanwei Liu

原文摘要

Pinching antenna systems (PASS) provide flexible transmitter-side radiation reconfiguration for high-frequency wireless communications. This paper applies PASS to non-orthogonal multiple access (NOMA) covert communication networks, where activated pinching antennas (PAs) transmit superimposed signals to a pair of users stochastically distributed within a rectangle. Two passive wardens respectively monitor the downlink transmissions intended for two users. More specifically, we derive the closed-form detection error probability (DEP) expressions for two wardens under bounded noise uncertainty. Then we analytically determine the optimal detection thresholds and minimum DEPs in the worst-case covert detection scenarios. The covert transmission rates of two users are further characterized by taking into consideration ideal successive interference cancellation and non-ideal successive interference cancellation at near user and intra-NOMA interference at far user. Numerical results are presented to confirm that: 1) PASS-NOMA is capable of providing higher covert rates relative to conventional orthogonal multiple access OMA schemes; 2) As the number of activated PAs begun to increase, the near user has ability to obtain a larger covert rate gain than far user; and 3) The DEP of PASS-NOMA networks is larger than that of both PASS-OMA and traditional antenna based NOMA in specific output power regions.

cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33894

WMEval: Evaluating Interactive World Models Grounded on Physical Simulations

Lanxiang Hu, Yixin Huang, Abhilash Shankarampeta, Zilin Dai, Yuyuan Wu, Kun Qian, Junze Liu, Arvind Srinivasan 等 16 位作者

原文摘要

Interactive world models hold immense potential for high-stakes applications in robotics, game engines, and immersive digital twins, yet existing benchmarks primarily focus on perceptual similarity rather than the physical-causal coherence essential for real-world utility. We introduce WMEval, a comprehensive benchmark that evaluates interactive world models against Unity-based physical simulations. By leveraging Unity as a high-fidelity ground-truth oracle, we shift evaluation beyond perceptual visual assessment toward the objective state-based verification required for downstream applications. Spanning 9 diverse scenes, WMEval assesses action controllability, scene and character consistency, prompt adherence, kinematics, fluid mechanics, physical causality, and lighting. By executing matched action sequences in both the simulator and the world model, WMEval enables evaluation at both the perceptual level and the physical-causal level, using simulator-derived states as reference. Experiments on state-of-the-art models reveal significant room for improvement in dimensions that remain hidden by standard perceptual metrics but are vital for real-world deployments. Our code is available at: https://github.com/hao-ai-lab/WMEval.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37018

Linear-Time FPT Rectilinear Planarity Testing of Series-Parallel Graphs

Giacomo Ortali

原文摘要

A planar graph is rectilinear planar if it admits a planar orthogonal drawing without bends. For series-parallel graphs in the variable embedding setting the best known testing algorithm takes $O(n^2)$ time. We show that rectilinear planarity of a series-parallel graph with maximum degree four can be tested in $2^{O(k)}\cdot n$ time, where $k$ is the number of degree-4 vertices; the planar embedding is not fixed. In particular, the running time is subquadratic when $k=o(\log n)$. Each node of the SPQ$^*$-tree stores the set of its admissible spiralities; we show that this set is a union of $2^{O(k)}$ arithmetic progressions of step two. All proofs are in the paper and are additionally verified in Lean 4 with Mathlib.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37015

RePAIR: Inverting Backdoor Attacks in Semantic Segmentation

Arnold Brosch, Kira Maag

原文摘要

Despite significant advances in computer vision, semantic segmentation models remain vulnerable to backdoor attacks, posing a security risk. These attacks redirect pixels of a chosen victim class to an attacker-specified target class when a trigger is present, while preserving clean predictions. Existing defenses are largely derived from image classification, while dedicated segmentation defenses remain scarce and typically require retraining or model modification. We introduce RePAIR, a post-hoc, label-free, attack-unaware defense based on the observation that backdoor-induced shifts can be stronger in the classifier head than in internal representations, leaving recoverable victim-class semantics. RePAIR infers the victim-target relation from an unlabeled, potentially contaminated image pool, constructs a safety-approved semantic reference, and localizes suspicious pixels by comparing head predictions with internal semantic evidence. It then applies feature-space and output corrections toward the inferred victim semantics, while conservative localization and output constraints limit changes to benign predictions. We model the attack as adversarial probability transport and repair as its approximate reversal, deriving bounds and sufficient conditions for localization, residual attack success, clean-side changes, defense-induced target predictions, and attack-unaware pair identification. Experiments across segmentation architectures and attack settings show that RePAIR substantially reduces attack success while largely preserving clean performance.

cs.CV · cs.CR · math.PR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37011

Evaluating Priority Dispatch for Premium Membership in On-demand Taxi-sharing

Nozomi Yamamoto, Hiroki Sakaji, Itsuki Noda

原文摘要

In this paper, we analyze the dispatch-level feasibility of introducing premium membership into an on-demand taxi-sharing service using a sequential optimal insertion method. We propose two dispatch-level methods: deadline shortening for premium users, and deadline shortening with dedicated premium vehicles. We compare them with a baseline dispatch method through SUMO-based simulations under three demand scenarios: steady uniform demand, time-varying demand with a peak period, and urban-focused demand with concentrated peak traffic. Our results show that the suitable priority mechanism depends on operating conditions and premium ratio, suggesting that condition-dependent method switching may provide premium benefits while keeping non-premium-user burden smaller for overall optimization.

cs.MA · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37007

From Ethernet to Wi-Fi: Flow Feature Selection and Construction for Traffic Classification

Francisco Rau, Petia Georgieva, Carlos Herranz, Iñaki Val, Joaquin Perez

原文摘要

Flow-based traffic classifiers trained on Ethernet data may lose accuracy when applied to Wi-Fi traffic. This paper proposes a five-stage procedure for selecting and constructing features that enable Wi-Fi flow classification using models trained only on Ethernet data. The procedure removes the transport protocol identifier, examines rate dependence, compares feature distributions and the information each feature provides for the application classes, reduces redundancy, and constructs normalized packet-size and temporal features. Ethernet and Wi-Fi traffic are simulated in ns-3, with Wi-Fi using Best Effort access category. Labelled Wi-Fi data from six development scenarios are used for feature design, while a separate scenario is reserved for final testing. The evaluation compares feature sets, examines threshold sensitivity, and analyses classification errors under different traffic conditions.

cs.NI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37006

Abstract Lipschitz Continuity

Marco Campion, Isabella Mastroeni, Michele Pasqua, Caterina Urban

原文摘要

We introduce Abstract Lipschitz Continuity (ALC), an extensional property of functions, in particular of program semantics, requiring that bounded differences between properties of two inputs yield proportionally bounded differences between properties of the corresponding outputs. ALC explicitly discerns between two complementary forms of approximation: property-based (or qualitative) approximations, which retain a property of the data and are formalized by upper closure operators as in abstract interpretation, and quantitative approximations, which measure the closeness of data and are formalized by pre-metrics, a weakening of metrics that covers the distances arising in program analysis. Keeping the two forms of approximation explicit has two main benefits. First, it allows us to precisely relate ALC to established extensional properties: ALC is a sufficient condition for partial completeness in abstract interpretation, for partial abstract non-interference in language-based security and, with a null Lipschitz constant, for abstract robustness in machine learning. Second, it supports reasoning about ALC of program semantics by induction on the syntax of programs: we present a sound deductive system, parametric in the property-based approximations and in the pre-metric of interest, that reduces a proof of ALC for a program to proofs for its basic commands and to some explicit side conditions, which isolate what makes ALC compositional across sequential composition, non-deterministic choice and iteration.

cs.PL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37005

Compote: Collapse-Resistant Multiple Hypothesis Learning For Sequential Recommendation

Louis Castres Saint Martin, Clement Calauzenes, Alain Rakotomamonjy, Patrick Gallinari

原文摘要

Next-item prediction is inherently ambiguous: a single interaction history often admits multiple plausible continuations across distinct catalogue regions. Standard sequential recommenders compress these alternatives into a single prediction, conflating user intents. We introduce COllapse-resistant Multiple hyPOThesis lEarning (COMPOTE), a multi-hypothesis transformer trained with an annealed objective that transitions from uniform supervision to a winner-takes-all assignment. This mechanism forces hypotheses to specialize into distinct catalogue regions, while inference relies on an efficient, normalizer-free max-similarity rule. Theoretically, we show that in the population case, the optimal solutions partition the conditional next-item distribution according to a max-entropy quantization principle, while pooled scores preserve the Bayes-optimal ranking. We also prove a generalization bound scaling logarithmically with the number of hypotheses. Across three Amazon Reviews 2023 benchmarks, COMPOTE outperforms strong ID-based, generative, and multi-interest baselines using item IDs alone. Matched-capacity ablations confirm that performance gains stem directly from the annealed objective, preventing the head collapse observed in conventional multi-head architectures, rather than added capacity, ensembling, or routing.

cs.LG · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37001

Meta Models: Models that Model Learning

Peihang Li, Ziming Liu

原文摘要

Every neural-network training run produces not only a model, but also evidence about how models learn. Can these accumulated experiments enable us to predict and compare new training runs before executing them? We study meta-models: models that predict the learning behavior of other models. From this perspective, final-performance prediction, learning-curve prediction, and hyperparameter selection are different queries to the same training response function. We take a first, humble empirical step toward this goal: treating real language-model training records as native numeric data, we find that an off-the-shelf tabular in-context learner, TabPFN, can match or outperform a fine-tuned LLM meta-model in multiple evaluated settings. Whereas recent work fine-tunes LLMs on tokenized configurations at a cost of tens to hundreds of GPU-hours, TabPFN requires seconds of fit-and-predict time without task-specific weight updates. We argue that meta-modeling is better treated as its own numeric modality rather than as a text task for LLMs. Going one step further, augmenting TabPFN with Kolmogorov-Arnold Networks (KANs) further improves accuracy on selected prediction tasks. Finally, we pre-registered a forecast of the Marin Hero Run, a 535B-parameter public training run, whose ground truth is revealed point by point as training progresses, putting meta-model predictions to the test against training outcomes not yet observed at the time of forecasting.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36999

Online gas classification at the edge

Ton Juny Pina, Hugh Greatorex, Elisabetta Chicca

原文摘要

Field applications in chemical sensing, from portable safety monitors to mobile robots, require models that are lightweight, fast to respond, and can be recalibrated from limited labelled data. Current gas classification pipelines assume controlled sampling cycles and offline feature extraction, and rely on computationally expensive models. With a few thousand neurons and sub-milliwatt power consumption, insects reliably classify odours in open environments. Inspired by the insect olfactory system, we present a neural network architecture that classifies raw sensor array readings using a sparse, high-dimensional binary representation. We evaluate it on random sequences of single gases and binary mixtures, introducing new samples dynamically and classifying gas identity from the transient sensor response. In this setting, the architecture out-performs a linear \gls{svm} on gas mixtures and matches an optimised non-linear \gls{svm}, while maintaining online class-level frequency estimates that distinguish familiar from novel stimuli. It relies exclusively on binary weights and Hebbian-based local learning, remaining computationally lightweight and well suited to ultra-low-power neuromorphic processors. We demonstrated the network on-chip with a hazardous gas detection experiment running on the mixed-signal neuromorphic chip TEXEL. The on-chip classifier yielded an accuracy of 74.6\% while running at 482 $\unit{\nano\joule}$ per inference and 27 \unit{\micro\watt} of static-power.

cs.ET · cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.29927

Does The Way You Plan Matter? An Empirical Study of Planning Representations for LLM Web Agents

Alejandra Zambrano, Sara Vera Marjanovic, Imene Kerboua, Xing Han Lù, Leila Kosseim

原文摘要

Despite recent advances, LLM-based web agents still struggle with limited exploration, omission of critical steps, and sensitivity to task constraints. Prior work suggests that many of these failures stem from weaknesses in planning, yet the impact of alternative natural language plan representations remains unexplored. To address this, we introduce PlanAhead, a static planner-executor framework that evaluates the impact of plan representation on agent performance. We first automatically categorize WebArena tasks into 3 difficulty levels, enabling consistent difficulty grading without human annotation. Then we systematically evaluate 4 different plan representations on the tasks categorized as hard: sequential subgoals, narrative, pseudocode, and checklist; across different families of multimodal LLM-powered agents(OpenAI, Alibaba, and Google). To account for stochastic variability, we introduce a novel decomposition of agent Success Rate (SR) into 2 interpretable evaluation metrics: Achievement Rate (AR) and Solved-Task Consistency (STC). Our results show that both, the plan formulation and the underlying LLM generating the plan, significantly influence web-agent robustness and task success.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.08738

Denoising Hierarchical Representations: Joint Continuous Diffusion for Language Modeling

Mathias Ollu, Nikos Komodakis

原文摘要

Diffusion Language Models (DLMs) hold the promise of order-agnostic, parallel text generation. Recently, continuous diffusion and flow matching models have seen substantial gains, driven by carefully crafted token representations and diffusion/flow spaces. In this work, we introduce Hierarchical Continuous Diffusion Language Models (H-CDLMs), a simple framework that further improves continuous DLMs with minimal compute and parameter overhead. Drawing on the discrete DLM and continuous image diffusion literature on joint diffusion, we diffuse multiple modalities in parallel. These modalities represent tokens at different semantic granularities: in our instantiation, the tokens themselves and coarser clusters obtained by clustering pretrained token embeddings. We propose a general setup that allows per-modality samplers and schedules to enhance the interplay between modalities. Applied to CoBit, this yields H-CoBit, which delivers large empirical gains across benchmarks. At dataset entropy, H-CoBit improves MAUVE and reaches a generative perplexity (GenPPL) of 49.4 on LM1B and 50.4 on OWT, improving on the baseline by 24.2 and 20.7 points and surpassing even discrete DLMs of comparable size. On GSM8K, it reaches 27.4% accuracy, outperforming prior continuous diffusion and flow-based models. We further apply H-CDLM to the flow matching model FLM, obtaining consistent gains with H-FLM and demonstrating that the framework generalizes across continuous generative paradigms. Our code will be made publicly available at https://github.com/matol-16/HCDLM.git .

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36996

Structure-Actuation Co-Design of All-Electric Heavy-Duty Robotic Manipulators

Mohammad Bahari, Amir Hossein Barjini, Jouni Mattila

原文摘要

This paper presents a mixed discrete-continuous multiobjective bilevel framework for the structure-actuation co-design of all-electric heavy-duty robotic manipulators. The upper level optimizes manipulator geometry and actuation topology, while joint-specific lower-level searches construct feasible archives of discrete motor, gearbox, and screw configurations. A system-level coordinator selects actuator packages according to hardware mass, co-design cost, and loss-aware supply energy, and the resulting actuator masses are fed back to the robot model until a mass-consistent fixed point is obtained. Evaluation on a full-pose SE(3) benchmark with a 100-kg tool payload yields eight feasible nondominated designs, all satisfying the 12 prescribed poses. Actuator-mass coupling converges in three iterations for every reported design. A fixed-design ablation shows that one-pass sequential sizing changes hardware mass by up to 2.13%, co-design cost by 10.20%, and supply energy by 9.40% in magnitude. Payload screening further reveals increasing mass-cost-energy demand and changes in competitive mechanism topology with carried load.

cs.RO · eess.SY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2505.18183

FRAME-C: A knowledge-augmented deep learning pipeline for classifying multi-electrode array electrophysiological signals

Nisal Ranasinghe, Dzung Do-Ha, Chathura J. Gamage, Simon Maksour, Tamasha Malepathirana, Sachith Seneviratne, Lezanne Ooi, Saman Halgamuge

原文摘要

Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disorder characterized by motor neuron degeneration, with changes to neuronal excitability being an early phenotype for ALS identified in patients and animal models. Recent advancements in induced pluripotent stem cell (iPSC) technology have enabled the generation of human iPSC-derived neuronal cultures, which, when combined with multi-electrode array (MEA) electrophysiology, provide rich spatial and temporal electrophysiological data. Traditionally, MEA data is analyzed using handcrafted features based on potentially imperfect domain knowledge, which while useful may not fully capture all the relevant characteristics inherent in the MEA data. Machine learning, in particular deep learning has the potential to automatically learn relevant characteristics (features) from raw data, without solely relying on handcrafted feature extraction. However, handcrafted features remain critical for encoding domain knowledge and improving model interpretability, especially in scenarios with limited or noisy data, as is often the case in most experimental studies. This study introduces FRAME-C, a knowledge-augmented machine learning pipeline that combines domain knowledge, raw spike waveform data, and deep learning techniques to classify MEA signals and identify ALS-specific phenotypes. FRAME-C leverages deep learning to extract important features from spike waveforms, while also incorporating handcrafted features such as spike amplitude, inter-spike interval, and spike duration, thus preserving key spatial and temporal information. We validated FRAME-C on both simulated and real-world MEA data from human iPSC-derived neuronal cultures, demonstrating its superior performance compared to existing methods for MEA classification.

eess.SP · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36994

CaLLM: Continual Adaptation of LLMs via Non-Parametric Adapter Routing

Bilge Celik, Anna Vettoruzzo, Joaquin Vanschoren

原文摘要

Continual adaptation of large language models (LLMs) to evolving task distributions while mitigating catastrophic forgetting remains an open problem. Existing strategies often struggle to scale or lack a robust mechanism for zero-shot task-to-expert assignment. We introduce CaLLM, a framework that resolves these tensions by combining metric-based meta-learning with modular parameter isolation via lightweight adapters. First, CaLLM projects each input batch into a task-agnostic embedding space to find its nearest prototype. It then routes the batch to the specific adapter specialized for that data distribution. This formulation provides (i)~controllable cross-task interference by design, (ii)~constant computational complexity regardless of task count, (iii)~seamless integration of novel distributions through prototype expansion, and (iv)~regime agnosticism as the local routing decision enables a unified approach to both online and offline settings. Our experiments demonstrate that this routing mechanism discovers semantically coherent task groupings while facilitating constructive interference between similar tasks, and keeping overhead at a minimum. Across diverse and fine-grained continual learning benchmarks, CaLLM consistently outperforms traditional isolation and replay methods, establishing prototype-based modular routing as a principled and scalable approach to lifelong adaptation of LLMs.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.06745

MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents

Bingfan Zeng, Zhisheng Chen, Zhengwei Xie, Bangde Cao, Yuxuan Li, Jinhan Li, Zheng Lu, Xiangchen Guan 等 11 位作者

原文摘要

Long-horizon agents performing multi-step Web tasks must reuse earlier page observations and interactions to support subsequent actions. However, preserving relevant history does not ensure that it exposes the relations needed for the current decision. We call this gap representation mismatch. To this end, we propose MemPrism, a task-conditioned relational memory framework that separates persistent experience storage from decision-time working memory. MemPrism records interactions as the event stream and dynamically constructs relational views according to the current task context. A lightweight view policy selects the relation structure, evidence range, outcome condition, and granularity, while a deterministic composer and renderer transform historical facts into a temporary optical working-memory view for a frozen task policy. Experiments on long-horizon embodied and web-agent benchmarks show that MemPrism consistently improves the task performance, especially as trajectories become longer, while reducing memory token consumption. Furthermore, the learned view policy transfers across different VLMs without additional adaptation, demonstrating the effectiveness of task-conditioned relational views as a general memory interface for agents.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36990

The State and Fate of Multilingual, Contextual Evaluation in the NLP World

Manan Uppadhyay, Himanshu Beniwal, Prashant Kodali, Sunayana Sitaram

原文摘要

Multilingual evaluation benchmarks are the primary instrument for assessing whether large language models generalize beyond English, yet the adequacy of these benchmarks has received little systematic scrutiny. We present a data-driven audit of 51 recent multilingual benchmarks spanning 242 datasets and 219 languages, organized around three pillars: coverage, representativeness, and rigor. Our analysis reveals that coverage is wide but thin with 36% of evaluated languages appearing in only a single benchmark, entire regions (Oceania, the Americas, Central Asia) are near-zero, and a stark task equity gap leaves low-resource languages evaluated on only 1-3 task categories versus 14 for high-resource languages. Representativeness is structurally compromised: translation from English remains the dominant construction strategy where 56% of all dataset-language instances are translated introducing artifacts and English-centric framing, while culturally grounded content is concentrated in a handful of community-driven benchmarks with narrow language scope. The ecosystem thus forces a trade-off between breadth and validity. Rigor is undermined by benchmark contamination, including translated benchmark leakage and parallel corpus overlap that evade surface-form detection. We synthesize these findings into concrete recommendations for building evaluation frameworks that are natively constructed, culturally grounded, contamination-aware, and designed to serve the communities whose languages they claim to evaluate. The dashboard with all the metadata collected can be found at https://aka.ms/multilingual-evals.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37722

FVH-Bench: Evaluating Image Generator Safety Beyond Overtly Harmful Imagery

Zihao Zhu, Yuhan Liu, Siwei Lyu, Baoyuan Wu

原文摘要

Modern image generators can produce complex visual artifacts, including diagrams, interfaces, and records that combine text, graphics, and layout to convey detailed information. They may refuse requests for overtly harmful imagery yet still generate artifacts that guide dangerous actions or support deception. We call the risk arising from what such images enable, rather than only what they depict, functional visual harm (FVH). Existing safety benchmarks focus largely on overtly harmful content, such as pornography and graphic violence, leaving image generators' safety alignment against FVH insufficiently evaluated. To address this gap, we introduce FVH-Bench, comprising 669 prompts across five harmful visual functions and ten risk domains. The 11 evaluated image generators rarely refuse these requests and frequently generate artifacts that fulfill the targeted harmful functions. High scores for target harm realization and harmful artifact usability further indicate that these outputs can support the intended harmful purposes. A further analysis finds that existing safety detectors also provide limited coverage of FVH, indicating gaps in their ability to recognize harmful visual functions. Together, these findings show that evaluating image-generator safety alignment requires considering not only what images depict, but also what they may enable.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36986

LearnPrunerV2: Learnable Progressive Token Pruning for Vision-Language Models

Rinyoichi Takezoe, Yaqian Li, Weiren Wang, Zihao Bo, Huihong Shi, Anzhou Hou, Mo Guang, Jiale Yan 等 9 位作者

原文摘要

Vision-Language Models (VLMs) have demonstrated remarkable multimodal capabilities but suffer from prohibitive computational overhead due to the massive number of visual tokens. While token pruning is a promising solution, existing methods still suffer from two major drawbacks: 1) unreliable pruning criteria that fail to accurately localize task-specific regions due to inherent attention biases or query-agnostic designs, and 2) suboptimal pruning strategies that employ rigid, non-adaptive schedules, overlooking the dynamic evolution of token redundancy across different model depths. To address these challenges, we propose LearnPrunerV2, which extends the previous two-stage heuristic framework (LearnPruner) into a fully learnable architecture. Specifically, we integrate lightweight learnable modules into every layer of the VLM backbone, which estimate token importance by fusing intrinsic visual saliency with extrinsic query relevance captured via a shadow token. By uncovering a consistent staircase redundancy pattern across VLM layers, we further introduce Budget-Deterministic Pruning (BDP) to establish a hardware-friendly schedule with fixed per-layer budgets. Extensive experimental results across various benchmarks and VLMs demonstrate that LearnPrunerV2 consistently outperform previous state-of-the-art methods. Notably, LearnPrunerV2 preserves 99.8% of the original performance when pruning 77.8% of visual tokens on LLaVA-v1.5, achieving a superior accuracy-efficiency trade-off.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36984

Quantum Evolution Kernel for Node-Attributed Graphs

Manuel Padovani, Alessandra Di Pierro, Claudia Daffara

原文摘要

We present a novel approach to embed node-attributed graphs onto neutral-atom quantum computers, and propose an application to digit recognition. Our approach extends PASQAL's quantum evolution kernel (QEK) by introducing a node-level feature encoding based on three-level quantum states. To this purpose, we present a prototype showing how the resulting embedding can be leveraged to extract correlation-based information for classification tasks. The entire quantum process is simulated using Pasqal's Pulser library, which inevitably imposes constraints on the size of the experimental datasets. We compare our method with classical baselines to evaluate its potential. We show that, for the digit recognition task, our method achieves a higher mean accuracy than the more commonly used Jensen-Shannon distance-based methods by utilizing the Wasserstein distance.

quant-ph · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36983

Advancement or Acceleration? How Data Curation Improves LLM Training

Jiaxing Wang, Zicheng Zhang, Deping Xiang, Jin Xu, Yong Li, Chao Liu, Pengzhang Liu, Qixia Jiang

原文摘要

While data curation is widely credited with improving large language model training, a basic question remains unresolved: does curation expand what a model can ultimately learn, or merely reach the same solution faster? In this paper, we formalize this distinction between advancement (improving the attainable performance) and acceleration (reaching the same performance with less data). Through an analytic characterization and real-world LLM experiments, we show that advancement requires a correctable train-target gap. When the baseline training and target objectives coincide, no curation policy improves the endpoint, although curation may still accelerate training. This reframes advancement as a property of the curation task rather than the curation method. Under a common gap-centric view of data mixture and selection, we operationalize this condition as the $Δ$-test, an observable discrepancy between the uncurated baseline's training and target losses that is computable prior to expensive curation. Across extensive experiments, an appreciably nonzero $Δ$ predicts persistent gains, whereas gains near $Δ=0$ tend to diminish as the training budget grows. Beyond individual methods, our findings recenter data curation on the task itself and point to target-set construction as a promising direction for shaping what curation can achieve.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36981

GNN-Guided Network Reduction for Centralized Urban Traffic Routing

Nikolai Antonov, Lukáš Chrpa, Andrii Nyporko, Jan Hůla

原文摘要

We consider the centralized traffic routing (CTR) problem, where a central planner assigns routes to origin-destination (OD) vehicle flows to minimize congestion-dependent segment cost. Prior work formulates CTR efficiently as a mixed-integer linear program (MILP), but scaling this formulation to the full road network is computationally prohibitive within an operational time budget. Bounded Routes and Smart Routes speed up optimization using precomputed reduced networks; however, these methods do not account for vehicle information within each OD flow. Motivated by this gap, we propose a learning-based urban network reduction approach. A dedicated graph neural network (GNN) first scores road segments for each OD flow using the road network and vehicle-flow information. Highly ranked segments are then incorporated into complete OD routes, and the original segment-flow MILP is solved on the resulting reduced road network. The GNN thus guides the reduction of the road network, while the solver enforces feasibility and determines the routing. Experiments on four real urban networks -- Prague-Dejvice, London, New York, and Sydney -- show that the proposed approach achieves the smallest relative objective difference to the $30$-second full-graph reference in every city under both traffic regimes. Averaged across cities, this difference is more than six times lower than that of the best competing method. Moreover, traffic simulation results show that the optimization gains of the proposed method lead to more efficient routing, with the highest aggregate arrival rate and a competitive trip duration per arrival percentage point.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.14141

Spatio-Temporal Audio Language Modeling for Dynamic Sound Sources

Oh Hyun-Bin, Kazuki Shimada, Yuhta Takida, Kim Sung-Bin, Toshimitsu Uesaka, Takashi Shibuya, Kyeongyoon Lee, Tae-Hyun Oh 等 9 位作者

原文摘要

Sound events have semantic identities, locations, and trajectories, yet existing audio-language models typically encode clips as global event content. Conversely, sound event localization models track source directions over time but offer limited semantic coverage for language reasoning. To bridge this gap, we introduce ST-AudioQA, a spatio-temporal audio QA dataset and benchmark built from first-order ambisonic (FOA) renderings of static and moving sound sources. Each scene provides source identity, activity, direction, distance, and motion metadata, enabling dense trajectory supervision and QA about what is sounding, where it is, how it moves, and how sources relate. We further introduce ST-Audio Encoder, which jointly learns event semantics and time-resolved source trajectories, and ST-AudioLM, which exposes these audio tokens to an LLM for spatio-temporal audio QA. Experiments show that this representation improves the balance between semantic preservation and localization and yields stronger reasoning than static spatial and localization-oriented baselines. Beyond the controlled benchmark, ST-AudioLM shows zero-shot transfer to real recordings, with further gains after light adaptation. Project page: https://st-audiolm.github.io/.

cs.SD · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.07860

On the Tradeoffs of On-Device Generative Models in Federated Predictive Maintenance Systems

Usevalad Milasheuski, Piero Baraldi, Enrico Zio, Stefano Savazzi

原文摘要

Federated Learning (FL) has emerged as a promising paradigm for preserving client data ownership and control over distributed Internet of Things (IoT) environments. While discriminative models dominate most FL use cases, recent advances in generative models - such as Variational Autoencoders (VAE), Generative Adversarial Networks (GAN), and Diffusion Models (DM) - offer new opportunities for unsupervised anomaly detection in time series analysis, with relevant applications in predictive maintenance (PdM) in critical industrial infrastructures. In this work, we present a comprehensive analysis of VAEs, GANs, and DMs in the context of federated PdM. We analyze their performance and communication overhead under both full and partial federation setups, where only subsets of model components are shared. Building on split-parameter personalized FL, this paper provides an empirical instantiation of shared/private parameter partitioning for unsupervised generative Time-Series Anomaly Detection (TSAD), mapping the split to analysis and synthesis modules across the generative architectures. Our experiments over five clients and two industrial time-series benchmarks reveal distinct trade-offs in model utility, stability, and communication efficiency in heterogeneous cross-silo FL. For the evaluated GAN-based configurations, full federation improves final anomaly-detection utility relative to independent local training, although these models remain less robust than the VAE- and DDPM-based alternatives. For DMs, decoder sharing matches full federation while substantially reducing the communication payload.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36978

Explicit Regional Representations For Video Quality Assessment

Fuyi Yang, Lei Yang, Andrew Liu, Chenyu Wei, Xiaoyi Guo, Ming Kai Hsu

原文摘要

End-to-end video quality assessment (VQA) methods leave the regional evidence underlying their predictions largely implicit. We introduce an explicit pixel-level regional representation for VQA, instantiated as a Quality-Relevance Heatmap (QRH) that combines localized degradation evidence with perceptual priors under vision-language model guidance, without requiring pixel-level annotations. We apply QRH to existing VQA models through two deterministic fragment-sampling strategies: distribution-preserving sampling approximates the original sampler's QRH-score distribution without retraining, while quality-aware sampling prioritizes regions with high QRH scores and is paired with fine-tuning. Experiments with DOVER on multiple benchmarks show that the former closely approximates predictions averaged over random samples, while the latter improves most evaluated metrics across popular VQA benchmarks. These results support explicit regional representations as a useful interface for downstream VQA.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.22506

Kernel Token Contradiction: a Fast and Principled Approach for LLM Claim Uncertainty Quantification

Jérémie Dentan, Alexi Canesse, Mahammed El Sharkawy, Sonia Vanier

原文摘要

Claim-level Uncertainty Quantification (UQ) aims to mitigate the lack of reliability of Large Language Models (LLMs) by evaluating the factuality of each claim in their outputs. We introduce Kernel Token Contradiction (KTC), a lightweight approach to compute claim-level UQ under realistic white-box conditions. KTC represents the candidate tokens involved in LLM generation as a positive semi-definite kernel that integrates both the LLM's conditional distribution and a token contradiction score. We then use the Von Neumann entropy to quantify the uncertainty of this kernel. To estimate token contradiction, we develop a new approach based on frequency statistics from the Wikipedia corpus. Although CPU-only, our approach achieves over an 8.2x speedup compared to state-of-the-art GPU-accelerated methods based on cross-encoders, and over a 65x speedup compared to CPU-only methods with comparable performance. Our evaluation spans two benchmarks across four European languages and 16 different models. KTC not only matches the average performance of existing methods but also outperforms them in high-precision regimes. This combination of computational efficiency and accuracy makes real-time monitoring of LLM outputs practical in production.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36976

Toward Circuit-Aware Mutation Testing for Quantum Programs: Exact Visibility and Execution Planning

Andriy Miranskyy, Jose Campos

原文摘要

Mutation testing assesses test suites by introducing program changes and checking whether tests detect them. In quantum programs, a surviving mutant may leave program behavior unchanged, produce a change hidden by the chosen input or measurement, or remain undetected because statistical evidence is insufficient. We develop a circuit-aware framework to distinguish these causes and guide execution planning and test changes. The framework covers ideal, noiseless programs and mutations that replace one gate or subcircuit. The method traces how a mutation can affect measured outputs and combines established mathematical checks with statistical estimates. For supported cases, we establish conditions under which a test cannot reveal a mutation and exact formulas for its effect when the required state information is available. Under stated assumptions, we bound the mutation score while retaining surviving and unresolved mutants, and identify a restricted circuit family whose mutation effects admit efficient classical classification. The deliverables include a decision procedure, mathematical guarantees, worked examples of test changes and their implementation requirements, and a small-circuit reference implementation for differential expectation tests. These results help testers decide what to execute, what to change, and what remains unknown. The evidence is limited to proofs and executable examples under the ideal model.

cs.SE · quant-ph

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2505.13231

Investigating Active Sampling for Hardness Classification with Vision-Based Tactile Sensors

Junyi Chen, Frederik Heller, Mario Gómez Andreu, Boris Belousov, Tim Schneider, Lisa P. Y. Lin, Katja Doerschner, Knut Drewing 等 10 位作者

原文摘要

Hardness is one of the most important object properties that humans and robots perceive through touch. This paper investigates active sampling strategies for sample-efficient hardness classification with vision-based tactile sensors (VBTS), using information-theoretic measures of model uncertainty. We evaluated three probabilistic classifier models and two active sampling strategies and a random sampling baseline on a hardness classification task, with our own dataset of VBTS samples collected by a robot and a previously published dataset. In addition, we conducted a human study on the hardness classification task with the same objects as our dataset. Our findings indicate that the active sampling approaches, driven by variance and entropy as measures of model uncertainty, perform best with accuracy reaching 90%, compared to human accuracy of 48%, demonstrating the effectiveness of using VBTS for hardness classification. More information can be found at: https://fheller1.github.io/ActiveHardness

cs.RO · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36973

KL-MOPD: Discrepancy-Aware Multi-Objective On-Policy Distillation for Generative Recommendation

Weiqin Yang, Yandong Wang, Yuan Gao, Hao Deng, Jinxin Hu, Jing Cao, Jiawei Chen

原文摘要

Coordinating multiple recommendation objectives (e.g., click and conversion) is critical for real-world generative recommendation (GR). However, since a positive item in GR can be retrieved only when its tokens are successively selected at every decoding step, traditional item-wise methods lack fine-grained token-wise supervision to guide intermediate steps. Motivated by its success in foundation models, we consider introducing multi-objective on-policy distillation (MOPD) into GR to distill two single-objective teachers into a student at each token. Yet, we find that in vanilla MOPD, (i) teachers exhibit unequal distillation difficulty at each token (i.e., token-level imbalance), and (ii) the harder-to-distill teacher varies across tokens (i.e., cross-token inconsistency), leaving each objective poorly learned at certain steps and hindering positive item retrieval for both objectives, leading to suboptimal performance. To address this challenge, we propose KL-MOPD (KL-Weighted Multi-Objective On-Policy Distillation), a simple yet effective distillation method that allocates token-wise teacher weights proportional to the initial student-teacher token-wise KL divergences, thereby strengthening supervision for the harder-to-distill teacher at every decoding step. Despite its simplicity, we theoretically prove that KL-MOPD strictly outperforms vanilla MOPD in the additive joint recommendation objective under mild conditions. Moreover, KL-MOPD is plug-and-play and computationally efficient, requiring only a one-time pre-training weight calibration with negligible training overhead. Extensive experiments on three public benchmarks, a billion-scale industrial dataset, and online A/B tests on our e-commerce advertising platform demonstrate that KL-MOPD significantly improves both individual and joint recommendation performance. The anonymous code is provided for peer review.

cs.IR

查看论文
arXiv ↗PDF ↗