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

+0新增论文
+0其中 AI 相关
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 14:31 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 14:53 — 2026-11-08 14:53（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：2026-11-08 14:31最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,057 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 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 14:29（北京时间）
新论文 · v1arXiv:2611.02891

Gibbs Variational Last Layers for Long-Horizon Dynamics Learning

Paul Brunzema, Henrik Hose, Sebastian Trimpe

原文摘要

Accurate long-horizon probabilistic predictions of dynamical systems are a prerequisite for model-based decision-making. Variational Bayesian last layers (VBLLs) are an attractive model class for this setting, offering tractable uncertainty at near-deterministic cost, yet they are trained exclusively with single-step likelihood objectives that may be insufficient for reliable multi-step rollouts. We revisit VBLLs through the lens of Gibbs variational inference, which decouples posterior inference from the choice of training loss. Building on this perspective, we introduce a family of multi-step training losses that progressively incorporate long-horizon structure, robustness via continuous ranked probability scores (CRPS), and training on full autoregressive rollouts. Our approach retains the simplicity of VBLLs while directly optimizing for multi-step predictive quality. Across illustrative synthetic environments, a diverse suite of chaotic dynamical systems, and real-world data, we show that multi-step, CRPS-based objectives substantially improve long-horizon accuracy and distributional fit, consistently outperforming single-step likelihood training.

cs.LG · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2505.15212

Group Distributionally Robust Optimization with Flexible Sample Queries

Haomin Bai, Dingzhi Yu, Shuai Li, Haipeng Luo, Lijun Zhang

原文摘要

Group distributionally robust optimization (GDRO) aims to learn models that perform well across $m$ distributions simultaneously. Existing methods either (i) query $m$ samples per round, which imposes strict implementation requirements, or (ii) query only a single sample per round, which requires many rounds to converge and therefore leads to long runtime. To avoid these limitations, we introduce a novel setting called \emph{flexible sample queries} (FSQ), which allows the number of samples that can be queried to vary across rounds. Under the FSQ setting, we cast GDRO as a two-player game: one performs non-oblivious online convex optimization, while the other tackles a non-oblivious prediction with limited advice (PLA) problem. In this game, the first player updates its decision using follow-the-regularized-leader with stochastic gradients. For the second player, we develop a new PLA method equipped with an adaptive exploration strategy that can leverage an arbitrary per-round sample size. We then establish the \emph{first} high-probability regret bound for non-oblivious PLA. By integrating these components, we develop an anytime GDRO algorithm that supports FSQ, and derive a high-probability optimization error bound of $O\left(\frac{1}{t}\sqrt{\sum_{j=1}^t \frac{m}{r_j}\log m}\right)$, where $r_j$ is the sample size at round $j$. This result demonstrates that the optimization error decreases as the per-round sample sizes increase, and implies the same near-optimal sample complexity of $O(m\log (m)/ε^2)$ for any fixed sample size $r\in[m]$.

cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2508.06352

Leveraging generative AI for human understanding: meta-requirements and design principles for Explanatory AI as an emerging paradigm

Christian Meske, Justin Brenne, Erdi Uenal, Sabahat Oelcer, Ayseguel Doganguen

原文摘要

Artificial intelligence (AI) systems increasingly support decision-making across critical domains, yet explainable AI (XAI) approaches prioritise algorithmic transparency over human comprehension. While XAI reveals computational processes for model validation, end users require explanations integrating domain knowledge, contextual reasoning, and professional frameworks. This disconnect reveals a design challenge: existing approaches fail to address how practitioners need to understand and act upon AI recommendations. This paper introduces Explanatory AI as an emerging complementary paradigm where AI systems leverage generative and multimodal capabilities to serve as explanatory partners for human understanding. Unlike traditional XAI, which answers 'How did the algorithm decide?' for validation purposes, Explanatory AI addresses 'Why does this make sense?' for practitioners making informed decisions. Through theory-informed design, we synthesise multidisciplinary perspectives from cognitive science, communication research, and education with empirical evidence from healthcare and AI expert interviews. Our analysis identifies five dimensions distinguishing Explanatory AI from XAI: explanatory purpose, communication mode, epistemic stance, adaptivity, and cognitive design. We derive five meta-requirements and formulate ten design principles prescribing how to build such systems, illustrated through five UI mockups exemplifying implementation. Explanatory AI operates standalone or combined with XAI, serving distinct purposes in creating systems that genuinely support human reasoning and decision-making.

cs.AI · cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02889

Tug of Watts: A study on the Energy - Accuracy Trade-off of Large Language Models on Medical Question Answering Tasks

Viju Sudhi, Giulio Billi, Andreea Scrob, Regina Stodden, Philipp Cimiano

原文摘要

Large Language Models (LLMs) are increasingly used in medical question answering (QA) systems. While recent works aim at incrementally improving the downstream task accuracy, an empirical estimation of the models' energy consumption and the associated carbon footprints is often overlooked. In this study, we demonstrate how practitioners can estimate energy consumption and arrive at reliable emission estimates for medical QA tasks available in the OpenMedical-LLM leaderboard by investigating 13 LLMs from 3 model families ranging from 270M to 14B parameters. We discuss how one can critically interpret energy versus accuracy trade-offs for a set of models for a given task. With this work, we underline that reporting disjoint energy and accuracy metrics alone does not suffice for careful trade-off assessments, but it also demands systematic construction and interpretation of joint trade-off metrics. We envisage such studies aiding practitioners in adopting better and more efficient models for their task and helping them become active participants in building sustainable LLM pipelines.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.28270

Every9D-22M: Large-Scale Real-World 9D Canonicalization of Everyday Objects

Leonhard Sommer, Emil Akopyan, Adam Kortylewski

原文摘要

Estimating the 9D pose of everyday objects from a single real-world image remains challenging. This is largely due to the lack of large-scale supervision. Most existing datasets either rely heavily on synthetic renderings or provide limited coverage of real-world objects. We address this gap with Every9D-22M, a dataset of 9D pose annotations for 22.8M real-world images from 114K object-centric videos spanning 630 everyday object categories, making it nearly two orders of magnitude larger than any prior real-world 9D pose dataset in at least one of category, object, or image count. To achieve this scale, we leverage object-centric videos by reconstructing object-level point clouds via multi-view geometry and aligning similar instances into a shared canonical coordinate frame. Canonical poses are manually annotated for only a small set of reference objects (fewer than 0.01% of all images) and propagated to the remaining instances via cross-instance alignment. All propagated canonical poses are then verified from multiple viewpoints. We further introduce cross-category orientation rules that induce category-level symmetries, enabling symmetry-aware evaluation. Beyond establishing dedicated training and evaluation splits as a benchmark for 9D pose foundation models, we show that training on Every9D-22M generalizes better to other datasets than training on existing datasets, and outperforms prior foundation models in rotation accuracy on all benchmarks except the viewpoint-biased ImageNet3D, where joint training with ImageNet3D surpasses them as well. Data and code are available at https://github.com/GenIntel/Every9D.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.29362

Compositional neural networks for multimodal X-ray and neutron scattering inversion

Valentin Munteanu, Alexander Hinderhofer, Dmitry Lapkin, Vladimir Starostin, Frank Schreiber

原文摘要

X-ray and neutron scattering are indispensable for structural characterization across condensed-matter physics and materials science. Yet, because scattering experiments generally record intensities without phase information, distinct structures can yield similar scattering patterns, rendering the corresponding inverse problems non-unique. This ambiguity can be reduced by combining complementary measurements, but their integration into machine-learning frameworks remains challenging. Here we introduce a modular framework for probabilistic multi-measurement analysis based on prior-amortized flow matching. Single-observation posterior estimators are trained separately for individual observation types or physical probes and combined only at inference time through a compositional sampler. This late fusion approach allows pretrained single-observation models to be reused without dedicated joint retraining. As a case in point, we consider reflectometry, which provides depth-resolved, nanometer-scale information about thin films and interfaces. Our single-observation demonstrations span X-ray, time-of-flight neutron and polarized neutron reflectometry. In separate co-refinement studies, task-matched estimators enable homogeneous composition across multiple neutron contrasts and heterogeneous multimodal composition of X-ray and neutron measurements. Together, these results establish compositional flow matching as a modular approach to uncertainty-aware inversion and co-refinement, with potential applicability to other scattering problems in which multiple observations constrain a common physical structure while retaining measurement-specific parameters.

cs.LG · cond-mat.mtrl-sci · physics.app-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02888

A Universal Policy Wrapper With Guarantees

Georgiy Malaniya, Anton Bolychev, Pavel Osinenko

原文摘要

Many control tasks require driving the system into a prescribed goal set and subsequently keeping it there. The considered setting assumes that a working controller is available that provably reaches and maintains the goal, albeit with suboptimal performance. This controller is referred to as the fallback policy. Conversely, although state-of-the-art reinforcement-learning (RL) algorithms can discover policies with impressive empirical performance, the neural networks at their core act as opaque black boxes learned through data-driven exploration and, as such, provide no theoretical mechanism to guarantee that the system will ever reach---and stay within---the prescribed goal set. This article presents CALF-Wrapper, a method that combines the fallback policy with a pretrained RL base policy and uses the critic estimate associated with the base policy to select between them during deployment. The theoretical analysis establishes that CALF-Wrapper inherits the goal-reaching property of the fallback policy under the stated assumptions and provides probability bounds for the settling time and the maximum distance from the goal set over a prescribed time interval. The experimental study evaluates CALF-Wrapper in four simulated control environments of different complexity. Comparisons include the base policy, fallback policy, and constrained reinforcement-learning methods formulated for the same objective. Sensitivity and ablation studies provide direct hyperparameter recommendations. The experiments show how CALF-Wrapper can provide effective task performance while attaining the maximum possible observed goal-reaching rate. CALF-Wrapper requires no additional dynamics model, online learning, or constrained optimization during execution.

cs.LG · eess.SY · math.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2509.04192

Domain size asymptotics for Markov logic networks

Vera Koponen

原文摘要

A Markov logic network (MLN) $\mathbb{M}$ determines a probability distribution $\mathbb{P}_n^\mathbb{M}$ on the set $\mathbf{W}_n$ of structures, or ``possible worlds'', with domain $\{1, \ldots, n\}$. We study the properties of such distributions as $n$ tends to infinity. We show that with mild assumptions on an MLN $\mathbb{M}$ with one soft constraint with an arbitrary positive weight the distribution $\mathbb{P}_n^\mathbb{M}$ will behave quite differently from the uniform distribution $\mathbb{P}_n^{uni}$ on $\mathbf{W}_n$ for all sufficiently large $n$. For a language with only one relation symbol $R$ which has arity 1 we give an almost complete characterization of the possible asymptotic behaviours of $\mathbb{P}_n^\mathbb{M}$ as $n \to \infty$, where $\mathbb{M}$ may be any MLN for this language. The asymptotic behaviour depends on the soft constraints and weights of the MLN. This characterization is used to show that if the language under consideration contains at least one relation symbol of arity 1 then the following holds: (a) There is an MLN $\mathbb{M}$ such that for every lifted Bayesian network (LBN) $\mathbb{G}$ there are infinitely many $n$ such that $\mathbb{M}$ and $\mathbb{G}$ determine different distributions on $\mathbf{W}_n$. (b) There is an LBN $\mathbb{G}$ such that for every MLN $\mathbb{M}$ there are infinitely many $n$ such that $\mathbb{G}$ and $\mathbb{M}$ determine different distributions on $\mathbf{W}_n$. We also show that, in the limit, the weight dimension and the domain size dimension may behave completely differently.

cs.AI · cs.LO · math.LO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02884

AnchorHEC: Targetless Hand-Eye Calibration of Wrist and Fixed Cameras

Guebin Hwang, Taeyeop Lee, Yeonseo Lee, Hyosup Shin, Sungho Jo

原文摘要

Recent robot systems combine wrist and fixed cameras, requiring camera-to-robot transforms for both. Most hand-eye calibration methods rely on targets or robot-body observations. Scene-based methods using 3D reconstruction require neither but address only wrist cameras. We introduce AnchorHEC, a targetless hand-eye calibration framework for wrist and fixed cameras in a single procedure using RGB images, forward kinematics (FK), and known camera intrinsics. We initialize both camera types using FK and a shared 3D foundation model reconstruction. FK-constrained wrist-image bundle adjustment reduces the impact of reconstructed pose and scale errors. If this refinement fails or retains too few inliers, we relax the constraints on potentially inaccurate FK poses and lens parameters. We use the refined wrist transform and FK to triangulate metric points and estimate fixed-camera poses. Across three backbones, calibration errors in simulation decrease by 86.4% in translation and 71.6% in rotation, averaged over both camera types, relative to reconstruction-based baselines. We also validate AnchorHEC on a physical robot. Project page: https://hwanggb.github.io/AnchorHEC/

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02883

Integrating Domain Adaptation and Retrieval-Augmented Generation for Saline-Alkali Land Reclamation Planning

Zuguang He, Congcong Zheng, Wanyue Chen, Wenya Zhou, Zaijin Yang, Long Long, Yucheng Zhang, Shuqin Gao

原文摘要

Reclamation of saline-alkali land requires management plans that account for soil and water conditions, treatment evidence, and financial constraints. This study develops Wenyao, an agricultural decision-support system integrating domain adaptation with retrieval-augmented generation. A bilingual corpus of 8,664 research papers was processed using a 110-indicator schema to construct SA-Bench, comprising 4,860 paper-level planning instances. A QwQ-32B model was adapted through low-rank supervised fine-tuning and combined with case retrieval for budget-conditioned planning. Evidence extraction achieved an F1-score of 0.83 on 300 expert-annotated papers. Without retrieval, Wenyao achieved 95.83% accuracy on 936 source-disjoint multiple-choice questions, compared with 87.93% for the strongest general-purpose baseline; removing explanatory supervision reduced accuracy to 89.42%. Matched-evidence comparisons across 69 region-budget cases supported complementary contributions from adaptation and retrieval. In a blind assessment by 31 experts, Wenyao with retrieval obtained the highest mean scores for objectives and projected outcomes, whereas GPT-5 scored highest for cost estimates. These findings support literature-informed reclamation planning with professional review, while ongoing field monitoring will assess soil and crop responses.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02880

Extending Aircraft Coverage of the Poll Schumann Model Using Public Data

Gabriel Jarry, Ramon Dalmau, Philippe Very

原文摘要

The Poll Schumann model requires airframe and engine parameters, but published tables cover only part of the fleet. Applications must obtain missing parameters, substitute another aircraft type or exclude unrepresented types. We reconstruct parameters using geometry from certification documents and manufacturer manuals, together with ICAO engine records. Published equations supply the physical parameters, regression estimates the propulsion efficiency scale. The inventory covers 90 type designators, including 22 absent from the direct pycontrails table and 18 without a listed substitute. Across 68 types, mean absolute percentage error (MAPE) against pycontrails was 7.38% for drag and 3.14% for design Mach. Across 66 types in 21 families, efficiency regression achieved 3.91% MAPE with the evaluated family excluded from input selection and fitting. On 100 recorded A320 flights, a type already represented in the published tables, cruise fuel flow MAPE for reconstructed and published parameter sets was 4.50% versus 4.68%, while mean absolute percentage error in integrated fuel over covered airborne intervals was 7.19% versus 6.82%. Public technical records can therefore extend Poll Schumann parameter coverage, with quantified agreement against published coefficients and comparable fuel prediction errors on the evaluated A320 flights.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2607.18168

A Forward-Backward Weight Analysis of INW for Permutation Branching Programs

Gil Cohen, Dean Doron, Noam Goldgraber

原文摘要

We construct an $\varepsilon$-error PRG for permutation read-once branching programs of length $n$ and width $w$ with seed length \[ O\left((\log w+\log(1/\varepsilon))\cdot \log n\right). \] This gives an exponential improvement in the dependence on $w$ compared with the constructions of De (CCC 2011) and Steinke (ECCC 2012). Compared with the work of Braverman, Rao, Raz, and Yehudayoff (FOCS 2010; SICOMP 2014), which applies more generally to regular branching programs and already achieves the optimal dependence on $w$, our result improves the dependence on the length $n$, attaining the optimal logarithmic dependence. The generator itself is the classical INW PRG of Impagliazzo, Nisan, and Wigderson (STOC 1994). We show that, for permutation branching programs, the INW generator can be instantiated with expanders whose degrees are polynomial in $w$ and $1/\varepsilon$ and, crucially, independent of $n$. To prove this, we analyze error propagation using program-dependent seminorms tailored to the branching program at hand. These seminorms build on the weight function introduced by Braverman et al. The key point is that, when measured in these adapted seminorms, the error does not accumulate throughout the recursion. Since our analysis relies only on the spectral expansion of the underlying expanders, our seed length tightly matches the recent lower bound for spectral analyses of the INW generator due to Hoza, Pyne, and Vadhan (Algorithmica 2024).

cs.CC · cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02877

ProtoFusion: Protocol-Guided Prompt Refinement for Generative Infrared and Visible Image Fusion

Pengwei Liang, Junjun Jiang, Junhui Hou

原文摘要

Infrared and visible image fusion integrates complementary information from both modalities to provide a more comprehensive representation of the scene. We propose ProtoFusion, a protocol-guided generative framework for infrared and visible image fusion. Instead of relying on fixed fusion operators, hand-crafted objectives, or manually specified one-shot prompts, ProtoFusion formulates fusion as protocol-constrained generation. It represents fusion intent with a structured protocol, consisting of environment state cards, grounding principles, and a style profile, which explicitly specifies which evidence should be preserved or suppressed and which properties the fused result should satisfy. To optimize this protocol, we introduce protocol-guided prompt refinement, a closed-loop learning framework that iteratively performs generation, evaluation, and revision under multimodal evidence. Once learned, the optimized protocol is fixed at inference time and directly guides fusion generation. To address residual source inconsistencies, we further incorporate structured belief construction, which organizes modality reliability, scene evidence, and cross-modal conflicts into a structured representation for conservative correction after generation. Extensive experiments on standard benchmarks show that ProtoFusion improves quantitative performance, achieves favorable results in aesthetic evaluation, and produces visually coherent fusion outputs. Project Page: {https://erfect2020.github.io/ProtoFusion/}.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02876

Identifiable Signed Causal Learning via Latent Stochastic Differential Equations for Inferring Brain Dynamic Effective Connectivity

Yiding Wang, Chen Qiao

原文摘要

Understanding how brain regions interact to support cognitive tasks requires characterizing directed causal influences among them, known as effective connectivity (EC). As inter-regional coupling changes over time, a dynamic EC (dEC) estimate is required to track this temporal variation. Existing dEC learning methods typically lack a causal rationality guarantee or an identifiability analysis, and output unsigned connectivity that cannot distinguish excitatory from inhibitory influences, which limits further study of brain mechanisms. We propose ISCL, a latent stochastic differential equation framework that derives dEC from latent dynamics through a causal influence operator defined in observation space. As established by a rationality theorem, the operator captures a directed interventional response at each brain state, and under invariance assumptions the operator is identifiable from data, with its signed output separating excitatory from inhibitory influences. On synthetic benchmarks, \model recovers the causal structure on Lorenz96 and achieves the lowest mean structural Hamming distance among compared methods on NetSim, while preserving signed influence structures that distinguish excitatory from inhibitory interactions. Applied to HCP Social Cognition task-fMRI, ISCL reveals a signed architecture whose stability across seeds supports the identifiability guarantee, identifies dominant source and target networks consistent with social-cognition systems, and shows that condition-specific training strengthens causal outflow from the default-mode and frontoparietal networks during theory-of-mind processing. In this task, the recovered signed structure reveals network-level excitatory and inhibitory organization, with the dorsal-attention network as the only consistently positive out-strength source.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02875

AGiR: Mitigating Gift Over-Reliance in Mixed-Motive Games

Woohyeon Byeon, Seongmin Kim, Jiwon Jeon, Woojun Kim, Youngchul Sung

原文摘要

In this paper, we consider mixed-motive games (MMGs) which model various real-world multi-agent scenarios where self-interested agents must both cooperate and compete. We identify an issue with existing gifting methods, where agents become overly dependent on incoming gifts and fail to learn reward-yielding behaviors, a phenomenon we call gift over-reliance. To address this, we propose a refusal-augmented gifting framework that balances cooperation and competition in MMGs. Our approach introduces an adaptive refusal mechanism that allows agents to selectively reject a portion of received gifts from their policy-update signals, thereby mitigating gift over-reliance and preventing the agents from being exploited by other agents. This mechanism is gifting-method-agnostic, serving as a plug-in for existing schemes while enabling decentralized learning. We demonstrate that across diverse MMG environments and gifting schemes, our mechanism consistently reduces gift over-reliance and prevents lock-in to sacrificing policies, improving $α$-fairness as a result, without necessitating major changes to existing training pipelines.

cs.MA · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02872

Design and Experimental Validation of the Separation and Deployment System for the CHERI Lunar Micro-Rovers

Ahmet Mustafa Kangal, Oğuzhan Şahan, Teoman Efe Aycan, Görkem Egemen Güloğlu, Halil Ersin Söken, Ali Emre Turgut, Uluç Saranlı, Mustafa Mert Ankaralı

原文摘要

Reliable separation mechanisms are critical for planetary micro-rovers, which must withstand launch vibrations and then eject the vehicle clear of the lander. This paper presents the design, optimization, and testing of the separation system of the CHERI (Challenging Environment Exploration Rovers for Intelligence) lunar micro-rovers. Sized for a 5 kg vehicle, the assembly comprises an aluminum ground plate, a central non-explosive hold-down and release mechanism, and an asymmetric four-spring ejection array. Initial separation trials revealed a velocity deficit caused by energy absorption in the flexible wheel-legs and chassis during the ejection stroke. This loss was represented as equivalent chassis damping in a multi-body dynamic model, and the springs were re-optimized accordingly. Early hardware iterations failed vibration testing, first through spring jamming in the guide housings and then through a 34 Hz fundamental mode of the flat ground plate. A density-based topology optimization raised the fundamental frequency to 84 Hz, above the 70 Hz requirement of the lander, within a 1.6 kg mass budget. The final configuration passed acceptance-level sinusoidal vibration, random vibration, and shock testing without structural degradation. Separation tests with a weight-matched one-sixth mass model, tracked by optical motion capture, confirmed clearance of the lander and reproduced the simulated free flight to within the run-to-run variation of the measured ejection velocity. These tests further showed that landing outcome is dominated by touchdown and settling dynamics, indicating that the residual pitch rate is the main controllable design parameter and confirming self-righting recovery as an integral element of the deployment architecture.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02871

ReGATE: Recurrent Gated Visual Fusion for Reactive Humanoid-Object Interaction

Hao Zhu, Jorge Peña-Queralta

原文摘要

Humanoid loco-manipulation requires coordinating object acquisition, transport, and release from onboard sensing while responding to user commands and incomplete visual observations. We present ReGATE, a whole-body controller that combines egocentric depth, proprioception, and online locomotion and contact commands. Built on a teacher-student framework, ReGATE integrates interaction-state estimation through a recurrent adapter that predicts object geometry and physical contact without an external object-pose estimator. Head-wise and global gates regulate visual updates to a proprioceptive pathway. A visual-grounding and corruption curriculum trains the adapter, while phase-aware initialization increases coverage of brief contact transitions. In simulation, ReGATE achieves 85.2% success across 330 static-object acquisition trials, compared with 48.5% for VisualMimic under the same protocol, and 85.9% across 440 moving-object acquisition trials. Deployment on a Unitree G1 demonstrates commanded grasp-transport-release sequences and acquisition of laterally displaced boxes. A qualitative hardware experiment further demonstrates successful box acquisition when the camera is occluded after an initial observation and before the contact command. To the best of our knowledge, this is the first work to extend recurrent gated fusion of onboard depth and proprioception from perceptive locomotion to humanoid loco-manipulation under interrupted visual sensing.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.17009

MaskSense: Confronting the Visual Exploration Trap in Masked Image Generation

Yawen Shao, Jie Xiao, Kai Zhu, Yu Liu, Hongchen Luo, Xueyang Fu, Yang Cao, Wei Zhai 等 9 位作者

原文摘要

Reinforcement learning (RL) has shown strong potential for aligning generative models with human intent, but adapting RL to masked generative models (MGMs) remains largely underexplored. Existing approaches that directly adapt Group Relative Policy Optimization (GRPO) to MGMs leave a foundational conflict unaddressed: MGMs' exploitative decoding nature is inherently at odds with the exploratory diversity that GRPO presupposes. In this work, we reveal a structural decoding bias termed the visual exploration trap: confidence-based sampling trades the exploration of diverse subject realizations for the greedy resolution of low-uncertainty background regions, causing premature collapse of the generative exploration space and starving GRPO of the rollout diversity it depends on. To this end, we propose MaskSense, a novel RL framework for MGMs that confronts the visual exploration trap at both the sampling and optimization stages. Specifically, we introduce a semantic anchored routing sampling mechanism that leverages semantic priors to preserve high-entropy subject token exploration while amplifying intra-group reward variance through exploratory-exploitative routing to yield more discriminative advantage estimates. Furthermore, we design a global entropy transition anchoring strategy to identify the most consequential decoding steps and concentrate gradient updates on them. Extensive experiments on multiple text-to-image benchmarks demonstrate that MaskSense substantially improves upon the base model, with GenEval accuracy improving from 54% to 86% and HPS from 28.89 to 36.39, achieving state-of-the-art performance.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.30266

Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and Generation

Bertram Taetz, Hugo Albuquerque Cosme da Silva, Gabriele Bleser-Taetz

原文摘要

Motion-language agents must possess the bidirectional capability to both understand human movement (motion-to-text, M2T) and generate it from natural language (text-to-motion, T2M). While foundational models have achieved strong performance in static settings, autonomous agents operating in dynamic environments must continuously incorporate new motion concepts -- such as novel athletic styles or specialized gestures -- without catastrophic forgetting of previously acquired skills. We investigate the stability-plasticity trade-off in bidirectional motion-language learning under sequential task exposure. Building on a frozen large language model backbone, we introduce low-rank adaptation (LoRA) variants designed to mitigate inter-task interference. We specifically propose mixture-of-experts architectures that utilize an autoencoder-based router to select task-specific experts at inference time, so that no task-label is needed. To evaluate these methods, we establish a reproducible five-task benchmark derived from HumanML3D through semantic clustering of motion descriptions. Our experimental results demonstrate near-zero forgetting across both M2T and T2M directions while maintaining high generation and captioning quality. Furthermore, we show that hard expert selection via routing significantly outperforms soft expert blending in quality metrics, indicating that preserving expert isolation is critical for maintaining performance in our continual learning setting. Finally, we observe that a divergence between token-level accuracy and downstream generation quality may occur, highlighting the need for more comprehensive evaluation protocols in future research on lifelong motion-language agents.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02866

TensorLOB: Structure-Preserving Tensor Learning for Limit Order Book Forecasting

Yuxuan Gu, Danilo Mandic

原文摘要

The limit order book (LOB) records outstanding buy and sell orders across multiple price levels. Its state evolves over time across market side, price level, and order attribute, naturally forming a multiway structure. However, existing LOB models typically flatten these dimensions into a matrix model, thus obscuring the existing structural relationships. Starting from first principles and the market-microstructure intuition of the LOB, we design TensorLOB to operate entirely in the tensor domain. TensorLOB uses mode-wise tensor contractions for feature extraction and directly contracts the learned representation with low-rank class-weight tensors for prediction, retaining the distinct roles of time, side, level, and attribute modes. Experiments on the FI-2010 benchmark show that TensorLOB achieves the highest accuracy, recall, and F1 score across all four evaluated horizons. This proof of concept highlights the potential of high-dimensional modelling of multi-way latent information intrinsic to financial markets, which has so far been largely overlooked.

cs.LG · q-fin.ST

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.17772

Inferring Stochastic Dynamics Reveals Atypicality and Irreversibility in Social Change

Youngkyoung Bae, Hajime Shimao, Seungwoong Ha, Luna Yang, David Wolpert

原文摘要

Human social systems bear striking similarities, yet similar conditions can give rise to markedly different historical trajectories. A central challenge for quantitative social science is therefore to use time-series data to identify features common to the evolution of different social systems without obscuring the variation distinguishing individual histories. Here, we address this challenge by fitting stochastic differential equations (SDEs) to ensembles of observed trajectories through spaces of socially relevant variables. Importantly, the SDE allows the average tendency and variability of change to depend on the current state of the system. This flexibility allows us to use the SDE to analyze myriad aspects of social dynamics. Specifically, the fitted SDEs identify regions of the state space where stochastic variability is greater, allowing a broader range of plausible subsequent changes. The fitted SDE also allows us to quantify the dynamical irreversibility of observed trajectories and how that irreversibility depends on the values of the social variables. In addition, we show how the SDEs can be used to identify statistically atypical transitions in individual trajectories, indicative of exogenous perturbations impacting the associated society. We apply these tools to three domains: modern political economy, quantitative history, and cultural analytics. This reveals state-dependent change in the organization of modern political-economic systems; a broad but stochastic tendency toward increasing social complexity in historical societies; and time-dependent reorganization of lexical dynamics in English. Looking forward, we argue that our framework provides a set of powerful quantitative tools that can be used to investigate a broader range of longitudinal social phenomena.

cs.SI · cond-mat.stat-mech · physics.soc-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02862

Performance evaluation of super-resolution techniques for characterization and phenotyping of commodity crops using multispectral imagery

Abhiram Karukayil, João F. C. Mota, Mateo Vásquez-Guevara, Tito Arevalo-Ramirez, Fernando Auat Cheein

原文摘要

Multispectral imagery provides spectral information beyond the visible range for vegetation monitoring, but it typically suffers from limited spatial resolution, which can obscure fine crop structures and affect vegetation-index (VI) estimates.} This study evaluates whether single-image super-resolution (SISR) methods developed for red, green, and blue (RGB) imagery can enhance the spatial resolution of red, green, and near-infrared (RGN) crop images while preserving spectral fidelity. Eight pretrained methods are applied directly to RGN images without fine-tuning: bicubic and nearest-neighbor interpolation, Real-ESRGAN, HAT, HiT-SR, SRFormer, ResShift, and StableSR. Reconstruction at $4\times$ and $16\times$ is evaluated for whole images and manually segmented leaf regions. Reconstruction quality is assessed using mean absolute error (MAE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), spectral angle mapper (SAM), and erreur relative globale adimensionnelle de synthèse (ERGAS). Eight VIs, computed from reference and super-resolved images, are evaluated using MAE, PSNR, and SSIM. Transformer-based methods \modification{significantly} outperform GAN- and diffusion-based approaches in both evaluation settings \modification{($p < 0.001$)}, with \modification{HAT, HiT-SR, and SRFormer forming the highest-performing statistical tier}. These findings indicate that RGB-trained SISR can enhance spatial detail in RGN crop imagery while maintaining spectral consistency and VI reliability for high-resolution crop phenotyping.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02858

Evaluating autonomous self-healing against persistent cyber-attacks

Bart Gijsen, Stefano Nieuwenhuizen, Lucien Yap, Georgi Spasov, Erwin de Haan, Mahira Ali, Shari Finner

原文摘要

The need for autonomous cyber resilience (ACR) is strongly accelerating. The boost in cyber capabilities of advanced AI is speeding up the attacker-defender rat race to an unprecedented pace. As a result, the field of ACR must progress from early design and experimentation to hands-on evaluation and deployment. To illustrate what is needed for this transition, we put TNO's autonomous immune system-inspired Self-Healing for Cyber Security (SH4CS) software to the test. Our analytic and experimental evaluation results demonstrate that effective cyber resilience is achieved with SH4CS for (repeated) web application vulnerability exploits. Remaining challenges of SH4CS revolve around finding the right balance between predictable resilient behaviour, and adaptiveness to the large variety of cyber threats and applications-to-be-protected.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02857

Solv3R: 3D Looped Transformer as a Multi-view Solver

Jeong-gi Kwak, Andrea Tagliasacchi, Sho Kagami, Yuki Ono, Kwang Moo Yi

原文摘要

Classical structure-from-motion reconstruction proceeds iteratively, refining camera poses and scene geometry from a current estimate. This allows maps to easily expand without recomputing already computed views, or geometry estimates to improve as more observations are provided. Most geometric foundation models, however, predict entire geometry in a single forward pass or update a recurrent state as frames arrive sequentially, making this expansion and refinement non-trivial. We introduce Solv3R, a looped transformer that learns to continue solving multi-view geometry from its current state. Importantly, its update operator is independent of the iteration count, allowing previously refined and newly introduced views to be jointly updated regardless of how ``solved'' they are. We train the operator to preserve accurate reconstructions under continued iteration and correct inaccurate states, enabling refinement of fixed image collections and integration of new observations. Representations of solved views can also be cached once and reused as geometric context across iterations, enabling compact and efficient key-value caching. We analyze the solver dynamics and compare it with the state-of-the-art, demonstrating that a single learned solver supports offline reconstruction, incremental reconstruction, relocalization, and streaming without task-specific training or modules. The code and models will be made publicly available at https://ubc-vision.github.io/solv3r/.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02856

Kolmogorov-Arnold Networks vs. Multi-Layer Perceptrons: A Rigorous Statistical Benchmark on Clinical Tabular Data

Rafał Wodziński, Paweł Szczerbiak

原文摘要

Kolmogorov-Arnold Networks (KANs) have recently been proposed as a promising alternative to Multi-Layer Perceptrons (MLPs). However, empirical evaluations on structured medical datasets remain scarce, and commonly reported metrics like AUROC can yield overly optimistic performance estimates on imbalanced clinical cohorts. In this study, we present a standardized benchmark comparing eleven architectures - nine KAN variants (FastKAN, WavKAN, ReLUKAN, ChebyKAN, TaylorKAN, GramKAN, JacobiKAN, LegendreKAN, and TabKAN), a tuned StandardMLP, and a Random Forest baseline - across seven heterogeneous medical tabular datasets spanning oncology, cardiology, nephrology, neurology, endocrinology, and obstetrics. Our experimental protocol employs a 3x5 Repeated Stratified K-Fold cross-validation scheme with nested Bayesian hyperparameter optimization and evaluates discrimination via Area Under the Precision-Recall Curve (AUPRC), calibration through the Brier Score, and computational efficiency. Formal equivalence testing is conducted using the Bayesian Correlated t-Test with a Region of Practical Equivalence (ROPE) at +/- 0.01. The results indicate that on datasets with severe class imbalance, dedicated KAN architectures (particularly TabKAN and ReLUKAN) can improve minority-class detection and achieve higher AUPRC than standard MLPs. Nevertheless, across pooled datasets, KAN variants demonstrate comparable overall predictive discrimination rather than a systematic advantage, while requiring 1.20x to 1.48x longer inference latency per sample and up to 12.5x more trainable parameters. Consequently, StandardMLP remains a strong baseline on the efficiency Pareto frontier, while KAN variants provide a viable alternative when precision on rare positive cases is the primary clinical objective. The code for reproducing the results is available at https://github.com/rafalwodzinski/kan_mlp_comparison.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02854

Task Adaptation Through Guidance in Frozen Feature Upsampling

Pingan Wang

原文摘要

Adapting features before upsampling can improve dense prediction, but the gains may arise from changes in feature values, spatial aggregation, or both. We investigate this ambiguity by comparing matched residual adapters before and after a frozen JAFAR upsampler under a shared parent. We construct a readout-null intervention that preserves a frozen linear classifier's coarse logits while allowing spatial attention weights to adapt. Guidance/value exchanges on trained models and retrained fixed-guidance controls test the utility of this adaptation route. In three-seed experiments on PASCAL Visual Object Classes (VOC) and Cityscapes, adaptation before upsampling improves mean intersection over union (mIoU) by 0.807 and 1.413 percentage points, respectively, over adaptation after upsampling. Across both datasets and the JAFAR and AnyUp upsamplers, readout-null adaptation produces mean gains of 1.379-1.987 points over the corresponding frozen linear baselines. Retrained controls further support the benefit of adaptive spatial guidance. These findings explain how dense predictions can improve despite unchanged coarse classifier outputs and identify spatial guidance as a useful target when adapting frozen feature upsampling systems.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02853

Scaling Action-Free Video Latent Prediction for Transferable Representations in End-to-End Autonomous Driving

Xingtai Gui, Xubin Zhou, Yucheng Zhou, Dongqian Guo, Jiahao Gong, Feiyang Tan, Jianbing Shen

原文摘要

End-to-end autonomous driving policies require effective visual representations that capture both spatial scene structure and temporal dynamics. Video latent prediction has emerged as an effective paradigm for learning spatiotemporal visual representations, yet it remains unclear whether scaling this objective with action-free driving videos can yield representations that benefit end-to-end planning. We study action-free video latent prediction as a scalable pretraining objective and introduce ScaleDrive, a driving-oriented framework pretrained exclusively on large-scale internet open-world driving videos, without action annotations or benchmark-specific data. We keep the pretrained video encoder frozen during downstream end-to-end planning training to isolate the transferability of representations learned from internet driving videos. Ego-motion and depth probes show that scaling action-free video pretraining progressively strengthens the temporal and geometric information encoded in the frozen representation. We systematically study the visual representation transfer across different end-to-end driving policies and closed-loop benchmarks, where ScaleDrive consistently improves downstream performance and demonstrates that scaling action-free video latent prediction yields representations that generalize across both planning policy architectures and evaluation scenarios and protocols.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02852

Value-Conditioned Proposal Acquisition for Test-Time Reasoning

Zeyan Li, Jianfeng Xu

原文摘要

Sampling and selection spend test-time compute inside a candidate pool, but they cannot recover a correct answer that never enters it. We introduce ValueFormation, a test-time policy that decides after each primary-model draw whether to stop, continue sampling, or acquire one proposal from a heterogeneous reasoning specialist. The three actions are compared on one cost-regularized value scale learned from vote-state features; the calibration is frozen across tasks and primary models, and acquired proposals are accepted only through a frozen posterior comparison. On held-out MATH-500, one Llama-fitted calibration improves over the strongest of eight identically evaluated baselines by more than fifteen points for each of three 8B primaries and transfers unchanged to Qwen3-14B. Removing acquisition lowers Llama MATH accuracy by 20.43 points, while same-trace and same-access replays attribute the gain to state-conditioned acquisition rather than specialist access alone. Where primary coverage is high, as on GSM8K, acquisition is rare and gains mainly come from cheaper allocation; on MBPP, a fixed code route attains the top accuracy at the lowest interaction cost. Varying the token price monotonically reduces calls without retraining.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.37176

Lossless Compression of Proximity Graph Indexes for Efficient Approximate Nearest Neighbors Search

Francesco Benocci, Leonard Dahlmann, Francesco Gargiulo, Tobias Heuer, Silvio Martinico, Franco Maria Nardini, Cosimo Rulli, Rossano Venturini

原文摘要

Graph-based Approximate Nearest Neighbor (ANN) indexes, such as HNSW, are the backbone of modern vector search. However, their massive memory footprint creates a severe infrastructure bottleneck. While vector quantization is widely adopted to reduce the memory required to store data vectors, the graph's edge structure increasingly dominates total memory usage. Compressing these adjacency lists for online search presents a critical system challenge: because decompression occurs during query processing, i.e., while navigating the graph, memory savings cannot come at the expense of query latency. In this paper, we present a compression technique explicitly tailored for live HNSW routing. By applying offline graph permutations to artificially induce structural locality, we enable the use of SIMD-accelerated integer compressors, such as Stream VByte, for rapid on-the-fly decompression. Evaluated across diverse real-world workloads, we significantly outperform the current state of the art in both compression ratio and query latency. Our experimental results show that we achieve compression ratios up to 52.7% with negligible penalties in latency compared to the uncompressed baseline. Furthermore, our technique has been effectively deployed in production at eBay, achieving up to 44.3% reduction in edge storage with no degradation in query latency.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02849

TLAPS-Bench: Formally Proving Correctness of Real-World System Specifications with TLA+ Proof System

Qian Cheng, Ruize Tang, Saad Mohammad Rafid Pial, Zhizhen Cathy Cai, Yiming Su, Jackson Clark, Munim Thahmid, Mahdiya Rahman Sukanya 等 16 位作者

原文摘要

TLAPS-Bench is a benchmark and execution harness for constructing machine-checked proofs for real-world system specifications in TLA+ with agentic AI. Proving correctness of complex system specifications requires discovering inductive invariants, reasoning about intricate state transitions, and decomposing proofs into tractable obligations. TLAPS-Bench provides a proof harness that supports iterative proof development atop the TLA+ Proof System (TLAPS), where agents are equipped with proof tools and libraries, with safeguards against reward hacking. Using the harness, we have employed AI agents to prove desired properties for important system specifications that were not proved before, spanning cache coherence, Byzantine consensus, and write-ahead logs. TLAPS-Bench contains 265 proof targets (each encodes a property to prove) from 95 TLA+ specifications of real-world systems. We evaluated frontier AI agents, represented by Codex with GPT models, on a subset of 70 proof targets across 12 specifications. The highest-scoring model, GPT-6.1 Sol (max), proved 31 (44.3%) proof targets. The results show challenges and opportunities in end-to-end proof development.

cs.AI · cs.DC · cs.LO · cs.SE

查看论文
arXiv ↗PDF ↗