跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

arXiv 最近完成扫描:2026-11-22 08:44 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 11:04 — 2026-11-22 11:04(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-22 08:44最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

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

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

浏览论文库

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

找到 23,345 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 08:42(北京时间)
版本更新 · v2arXiv:2611.24133

Evaluating LIM Trading Agents: A Critical Review of Backtesting Validity and Reporting Practices

Long Xu, Fuyi Wang, Xiaolu Hu, Chao Chen

原文摘要

Large language models (LLMs) are increasingly used in investment research, and many studies report promising historical returns. However, such results are only credible if researchers can demonstrate that the model used only information available at the time, account for how strategies and configurations were selected, and explain how reported returns were generated. We identify six common threats to validity in LLM investment evaluations and apply them to 18 published studies. Across 108 assessments, we find substantial gaps in reporting. No paper fully addresses information timing, model-memory exposure, universe selection, trading costs, or configuration-selection bias. Only four studies provide minimum evidence that results hold across multiple market periods. Our analysis reveals that commonly used safeguards often address different problems than researchers assume. For example, using dated inputs does not guarantee that a pretrained model lacked knowledge of future events, and repeated experimental runs do not correct for strategy-selection bias. We therefore propose an evaluation protocol for future LLM investment research. Rather than judging whether LLMs can generate profits, our study examines whether existing evidence is sufficient to support such claims. We conclude that current reporting practices are generally insufficient for that purpose.

cs.CR

版本更新 · v2arXiv:2610.14988

Mixing Regularization for Average-Reward $Q$-Learning and $Q$-Planning

Julien Roger, Sam Bodmer, Jian Qian, Benjamin Riviere

原文摘要

The average-reward setting for reinforcement learning is challenging because, without discounting, the span-contraction of the Bellman operator depends on the mixing properties of the underlying Markov dynamics. Whereas existing work typically assumes contraction, for instance through environment mixing, we study regularization toward a given reward-agnostic, $m$-step mixing policy to control the mixing properties of the learned policy. Our central mixing lemma quantifies how the reference policy's mixing properties transfer to the resulting learned policies. In particular, a single regularizer-dependent quantity simultaneously controls the contraction of the regularized Bellman operator and the exploration of the resulting policies. A second regularizer-dependent quantity controls the bias introduced by regularization, revealing a trade-off between convergence speed and approximation accuracy. Building on this result, we establish finite-time guarantees for regularized $Q$-iteration, synchronous and single-trajectory $Q$-learning, and $Q$-planning. Under one-step mixing, our bounds for approximating the regularized fixed point match the classical model-query bound for relative value iteration and, up to logarithmic factors, an existing sample-complexity bound for synchronous $Q$-learning. We also establish finite-time guarantees under multi-step mixing. For $Q$-planning, we characterize how the planning horizon trades off boundary bias against sample complexity. Finally, we present numerical studies validating the analysis: (i) knowledge of a strong mixing policy improves convergence and exploration, with larger benefits under more severe bottlenecks; and (ii) the observed rankings of $α$-divergence regularizers by bias and convergence speed are consistent with our theoretical analysis.

cs.LG · cs.AI · math.OC · stat.ML

新论文 · v1arXiv:2611.26235

Physics-Informed Feature Representations and Pretrained Tabular Foundation Models for Generalizable Melt Pool Geometry Prediction

Rafid Enayet, Imtiaz Ahmed, Md Habibor Rahman

原文摘要

Developing generalizable, data-efficient machine learning (ML) models for advanced manufacturing remains challenging because experimental datasets are limited and process-property relationships vary across materials and operating conditions. In laser powder bed fusion (LPBF), melt pool width, depth, and melting mode (conduction, transition, or keyhole) govern process stability and defect formation. Conventional ML models typically use dimensional process parameters, which represent laser-material interactions only implicitly and may limit cross-material transfer. This study evaluates whether two physics-informed dimensionless features, normalized enthalpy and Peclet number, combining laser processing conditions with material thermophysical properties, improve melt pool prediction over raw process parameters. We systematically benchmark seven models: four classical ML methods (Gaussian process, support vector machine, random forest, and XGBoost) and three pretrained tabular foundation models (TabPFN, TabDPT, and TabICLv2). Experiments span 316L stainless steel, IN625, IN718, and combined-material datasets, covering regression of melt pool width and depth and classification of melting modes. Dimensionless features yield comparable or superior predictive performance in most settings, with the largest gains in cross-material depth prediction (R^2 = 0.96). Tabular foundation models generally achieve stronger classification performance than classical baselines, particularly for multi-material datasets. These findings indicate that combining physically meaningful dimensionless representations with pretrained tabular models can improve data-efficient melt pool modeling and support more transferable process-window identification in LPBF.

cs.AI · cs.LG

版本更新 · v2arXiv:2608.16367

Depth-Dominant Skeleton Detection for Natural Scenes

Chengkun Rao, Xinrong Hu, Min Li, Yangjun Ou, Ziwei Luo, Ye Li, Zhaojing Wang, Junwei Tang 等 10 位作者

原文摘要

Existing natural-scene skeleton detectors follow an RGB-representation-based feature encoding paradigm: they locate skeletons within the RGB appearance space, in which the skeleton's shape and topology can only be inferred implicitly from entangled color and texture cues. Despite notable progress, this encoding paradigm degrades markedly on complex scenes such as cluttered or occluded ones, where appearance distractors overwhelm the weak structural signal. We observe that depth images are inherently insensitive to color and texture and provide clear regional contours and inter-region spatial relationships, which naturally eases the difficulty of skeleton detection in complex scenes. Motivated by this, we propose for the first time a novel skeleton detection paradigm built on depth-representation-dominant feature encoding, in which depth dominates and RGB serves as the auxiliary, and present a model, DDSkel, under this paradigm. DDSkel adopts an asymmetric encoder design that fuses the feature representation of RGB images into that of depth images, with the RGB branch containing only 23% of the parameters of the depth branch. DDSkel has a simple structure without intricate designs. Nevertheless, with only about 19% of the trainable parameters of the largest state-of-the-art methods, DDSkel attains the highest F-measure scores on four mainstream benchmarks, namely SK506, SK-LARGE, WH-SYMMAX, and SymPASCAL. Extensive experiments suggest that for natural-image skeleton detection, the depth-dominant paradigm is a more suitable choice than the RGB-based paradigm, achieving better performance with substantially fewer parameters.

cs.CV

新论文 · v1arXiv:2611.26234

Attention Drift Regularization with Adaptive Initialization for Domain-Robust Visual Recognition

Shivangi Rai, Vinod K Kurmi

原文摘要

Source-free domain adaptation (SFDA) adapts a pretrained source model to unlabeled target domains without source data access, yet two critical failure modes remain unaddressed. First, attention drift: source-learned attention maps shift toward spurious or background features under distribution shift, destabilizing feature representations. Second, domain-gap-agnostic initialization: applying a single fixed source model uniformly across all target domains ignores domain gap severity, causing premature overfitting to noisy pseudo-labels under large shifts. We propose DGA-CAFC to address both failures. The Counterfactual Attention-based Feature Consistency (CAFC) module enforces feature stability by minimizing the discrepancy between representations computed under learned attention and those under counterfactual-inspired normalized perturbations, thereby promoting domain-robust features independent of spurious attention shifts. The Domain-Gap Aware Source Model Selection (DGASS) module estimates domain gap severity via target prediction entropy and selects the source model variant whose confidence level best matches the estimated gap, reducing negative transfer and stabilizing pseudo-label quality. Crucially, CAFC transfers beyond SFDA: applied as a lightweight regularizer to standard domain generalization objectives without target data. Extensive experiments across SFDA and DG benchmarks demonstrate that our method consistently improves over recent baselines, demonstrating the effectiveness and generality of the proposed framework. Project page is available at https://visdomlab.github.io/DGA_CAFC

cs.CV

版本更新 · v2arXiv:2606.28666

Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare

Liam Kearns

原文摘要

Agent-based AI has enabled the automation of tasks by exposing application tools and resources to large language models (LLMs). However, to improve scope and accuracy, agents are often given access rights that exceed those of ordinary users, introducing significant security risks and potential regulatory breaches. This paper applies the AI Trust, Risk, and Security Management (TRiSM) framework to a medical report-generation application to demonstrate how an insecure baseline workflow can be transformed into a security-conscious agentic workflow. Both designs were evaluated with five LLMs (Claude Haiku 4.5, GPT-4.1-nano, GPT-4.1-mini, GPT-5.4-mini and Gemini 2.5 Flash) across 800 report generations and 500 attack trials covering RAG poisoning, data-field injection and client-side network injection. The redesign reduced attack success from 31% to 10% for RAG poisoning and from 42% to 25% for data-field injection (McNemar p < 0.001 for both), removed network injection by construction, and raised report accuracy from 72.5% to 86.5%. In an exploratory post-hoc grouping by attack goal, success against attacks aimed outside the report task, such as data disclosure and tool abuse, fell from 21.7% to 2.5% and no patient record was disclosed under the redesign. Attacks altering the reported Covid-19 diagnosis remained effective, accounting for 32 of the 35 successful attacks against the redesign. Least-privilege architecture limits what an injection can reach, but not whether a model follows injected content within its task, so clinical outputs need verification independent of the LLM. No model resisted all three attack vectors, so model selection cannot substitute for secure workflow design.

cs.CR · cs.AI

版本更新 · v2arXiv:2610.39621

The Real Cost of Context: Predicting Compute Time and Energy Consumption in LLM Prefill and Decode Phases

Lars Krupp, Daniel Geißler, Francisco M. Calatrava-Nicolas, Stefan Gerd Fritsch, Paul Lukowicz, Jakob Karolus

原文摘要

The integration of Large Language Models (LLMs) into agentic architectures has substantially increased token consumption, raising concerns about their energy footprint. Yet, estimating the energy consumption of proprietary API-based models remains challenging, and existing approaches focus primarily on generated output tokens while overlooking the impact of the large input contexts characteristic of agentic workflows. To address this gap, we systematically profile compute time and energy consumption across a wide range of prefill (input) and decode (output) token lengths. Using generalized linear models, we show that decode compute time and energy scale linearly with output length, whereas prefill compute time and energy exhibit both linear and quadratic scaling with input length. These findings demonstrate that input context becomes a relevant factor for large-context workloads. Furthermore, we show that compute time serves as a reliable proxy for energy consumption when direct energy measurements are unavailable. Our mapping framework enables precise energy estimation and supports more sustainable deployment decisions for agentic AI.

cs.AI

新论文 · v1arXiv:2611.26232

Time Series Structure Learning with Local Causal Parent Discovery

Jacqueline Maasch, Shu Wan, Hank Zhu, Huan Liu, Zhiguang Wang

原文摘要

Learning and inference on time series can pose significant statistical challenges, including autocorrelated observations, distribution shift over time, and the curse of dimensionality. These challenges complicate the practical application of causal discovery algorithms, which already suffer from high computational and sample complexity in the general case. To mitigate these issues, this work introduces Iterative Temporal Parent Discovery (ITPD): a sound and complete constraint-based procedure for causal structure learning on multivariate time series with causal nonstationarity. ITPD takes a local-to-global learning approach that discovers the global graph by sequentially discovering the parent set for each variable. ITPD exploits temporal structural priors, graph partitioning, and the local Markov condition to swap higher-order conditional independence tests for lower-order alternatives. With an exact oracle, ITPD performed the least number of tests and used the smallest average conditioning set sizes relative to baselines. In benchmarking simulations, ITPD sat on the Pareto frontier with respect to F1 and wall-clock time and was faster than baselines on large graphs ($\geq$ 1000 nodes). For graphs with 2000 nodes, ITPD ran $2.3\times$, $9.1\times$, and $40.9\times$ faster than iterative IAMB, DF-PC, and PCMCI, respectively.

cs.LG · stat.ML

新论文 · v1arXiv:2611.26229

Sharp topological overlap in every dimension

Sergey Norin

原文摘要

For a positive integer $d$ let $c_d^{\mathrm{top}}$ (resp. $c_d^{\mathrm{aff}}$) be the maximum $c$ such that, for every continuous (resp. affine) map from the $n$-dimensional simplex $Δ^n$ to $\mathbb{R}^d$, some point of $\mathbb{R}^d$ lies in the images of at least $(c-o(1))\binom{n+1}{d+1}$ of the $d$-dimensional faces, as $n\to\infty$. We show that \[ c_d^{\mathrm{top}}=c_d^{\mathrm{aff}}=\frac{(d+1)!}{(d+1)^{d+1}}. \] The second equality confirms a conjecture of Bukh, Matoušek, and Nivasch, who established the upper bound. The proof was found by GPT-6 Astra, following the directions of the author.

math.CO · cs.CG

新论文 · v1arXiv:2611.26228

Attention Head Specialization: Phase Transitions in Sample Complexity

Léo Catteau, O. Duranthon, Lenka Zdeborová

原文摘要

Attention heads specialize into distinct functions during training, often emerging in stages together with sharp changes in model behavior. While this phenomenon has mostly been studied as a function of training time, we ask how head specialization depends on the amount of available training data. Empirically, we find that heads specialized to syntactic relations in BERT emerge as the dataset size increases. We then study this phenomenon in a solvable high-dimensional model of multi-head attention and establish that, in this model, head specialization is a genuine phase transition in sample complexity, corresponding to a non-analyticity in the test error and other observables. Depending on data structure and regularization, specialization can follow uninformative head differentiation or occur through a cascade of phase transitions that progressively recover weaker latent features, providing a statistical form of simplicity bias. Finally, we relate these statistical transitions to the stagewise emergence of specialized heads during online learning, disentangling statistical from dynamical origins of head specialization.

cs.LG · cond-mat.dis-nn · stat.ML

版本更新 · v2arXiv:2603.29519

Beyond Dimensionality: Domain Shift and Catastrophic Forgetting in Single- vs. Multi-Vector Retrieval

Archish S, Mihir Agarwal, Ankit Garg, Neeraj Kayal, Kirankumar Shiragur

原文摘要

Recent work by Weller et al. introduced the naturalistic benchmark LIMIT and showed that widely used single-vector embedding models suffer substantial degradation in retrieval quality, attributing this primarily to limited embedding dimensionality. In our work, we revisit this explanation and argue that dimensionality alone is unlikely to account for the observed failures; in fact, results of Alon et al. imply that $2k+1$ dimensions suffice for top-$k$ retrieval over a fixed set of queries and documents. Motivated by this, we investigate alternative drivers of poor performance, including tokenization, linguistic structure, and domain shift. Our empirical analysis shows that tokenization artifacts and linguistic similarity yield only modest improvements, whereas domain shift and misalignment between embedding similarity and task-specific relevance are the dominant factors. While finetuning partially mitigates these issues and improves recall, it introduces catastrophic forgetting: finetuning single-vector models on LIMIT-like datasets reduces their MS MARCO Recall@10 by more than half, whereas multi-vector models forget much less. We observe the same pattern when finetuning on the real-world HotpotQA dataset, and between the single-vector and multi-vector heads of Jina-v4, which share one backbone.

cs.IR

新论文 · v1arXiv:2611.26221

Sightline: Calibrated Data-Flow Summaries for LLM-Integrated Applications

Zihao Xu, Yuekang Li, Ruitao Feng, Haifeng Shen

原文摘要

Programs increasingly call large language models (LLMs), filling prompt placeholders with program values and consuming the output. Such a call crosses the boundary between natural language and programming language (NL/PL). To follow data across it, an analysis needs a data-flow summary of which placeholders the output uses, but no code describes what the model does. Analyses of these LLM-integrated applications therefore taint every output with every input, creating spurious flows, or ask a second model to label each call, which is costly. We prove, and mechanize in Lean 4, that a placeholder flows to the output of a transformer, to first order, only through the attention that reads it (no reading, no flow), and that a faint reading or sensitivity cannot certify that a placeholder does not flow. Unlike reading, the log-probability gradients and Fisher signals of existing methods vanish on confident outputs, and single-span removal fails on duplicated content. Our tool, Sightline, reads a recorded call in one forward pass, learns from labels which reads are uses, and calibrates the pruning to miss at most a chosen fraction $α$ of true flows, on average over call sites, when deployment is exchangeable with calibration. On 2,103 unseen repository families and four models, Sightline is the most accurate summary against the seven closest methods and a hidden-state probe. Calibrated at $α$ = 1%, it misses about 1% of true flows and prunes 43.9-65.6% of spurious flows, 1.6 to 2.6 times as many as the best baseline, and still 43.8-60.1% when calibrated on another collection. Through an open surrogate, it reads models treated as closed about as accurately as they read themselves, without their labels. In the information-flow control of an LLM agent, it removes about half of the labels from inputs that do not flow.

cs.PL · cs.AI

新论文 · v1arXiv:2611.26220

Spherical Tessellation of Circular Arrays for Massive MIMO: Favourable Propagation Conditions and Spectral Design

Geili T A El Sanousi, Tuan Anh Le, Raed A A Abd-Alhameed, Xin-She Yang, Huan X Nguyen

原文摘要

Upper-mid-band XL-MIMO can exploit line-of-sight propagation, but periodic uniform cylindrical arrays may produce grating ridges. We analyse a spherically tessellated concentric circular antenna array with non-separable facet orientations. Under fixed normalised chord spacing and ideal facet visibility, we prove that user channels become asymptotically orthogonal and matched-filter SINR approaches the single-user SNR. Simulations confirm interference decay and SINR convergence. A spectral comparison shows that facet-normal diversity prevents the full-amplitude grating ridges of the cylindrical baseline, with the inter-facet residual decaying with array size.

cs.IT

版本更新 · v2arXiv:2601.04423

Learning Multinomial Logits in $O(n \log n)$ time

Flavio Chierichetti, Mirko Giacchini, Ravi Kumar, Silvio Lattanzi, Alessandro Panconesi, Erasmo Tani, Andrew Tomkins

原文摘要

A Multinomial Logit (MNL) model is composed of a finite universe of items $[n]=\{1,\dots,n\}$, each assigned a positive weight. A query specifies an admissible subset---called a slate---and the model chooses one item from that slate with probability proportional to its weight. This query model is also known as the Plackett--Luce model or conditional sampling oracle in the literature. Although MNLs have been studied extensively, a basic computational question remains open: given query access to slates, how efficiently can we learn weights so that, for every slate, the induced choice distribution is within total variation distance $\varepsilon$ of the ground truth? This question is central to MNL learning and has direct implications for modern recommender system interfaces. We provide both adaptive and non-adaptive algorithms for this task. Our first adaptive algorithm makes $O(\frac{n\log n}{\varepsilon^2})$ queries and learns every choice distribution in total variation distance $\varepsilon$. We also provide a second adaptive algorithm that with $O(\frac{n \log n}{\varepsilon^3})$ queries provides a stronger guarantee: each choice distribution is approximated to a multiplicative $1\pm\varepsilon$ error (except for subsets of mass smaller than $\varepsilon$). We complement these algorithms with lower bounds of $Ω(\frac{n\log n}{\varepsilon^2})$ for total variation distance and $Ω(\frac{n \log n}{\varepsilon^3})$ for the multiplicative error guarantee, showing the optimality of our adaptive algorithms. Our non-adaptive algorithm makes $O\left(\frac{n^{2}}{\varepsilon^{3}}\log n \log\frac{n}{\varepsilon}\right)$ queries to obtain guarantees under the multiplicative error notion. We complement this result with an $Ω(\frac{n^2 \log n}{\varepsilon^2})$ lower bound for any non-adaptive algorithm, showing that our algorithm is almost tight in $n$ (within a $\log n$ factor).

cs.DS · cs.LG · math.ST · stat.ML

新论文 · v1arXiv:2611.26219

CAVQS: Context-Aware Variational Quantum Circuit Synthesis via Unitary Redistribution and Dynamic Reconstruction

Zhilong Liu, Xiangzhen Zhou, Yunqi Huang, Xin Hong, Pengcheng Zhu, Fanxu Meng, Zhenlong Du

原文摘要

Variational quantum circuit synthesis jointly searches circuit structure and continuous parameters to reduce costly two-qubit gates, but block-based workflows typically instantiate blocks independently, limiting simplification across block boundaries. Moreover, fully unitary synthesis does not exploit opportunities created by permitted output measurements and classical feedforward. We present CAVQS, a context-aware variational synthesis framework that combines unitary redistribution and dynamic reconstruction. First, CAVQS uses QR decomposition to transfer unitary factors between overlapping blocks, preserving the overall transformation while reshaping local synthesis targets to enable cross-block reductions. Second, for blocks that precede permitted terminal measurements, CAVQS constructs ancilla-free dynamic implementations with a CNOT-budgeted pre-measurement search and analytic branch-unitary construction, thereby minimizing expected CNOT cost. Across random-circuit targets, CAVQS reduces mean two-qubit gate counts by 28.79%-42.52%, 2.05%-52.62%, and 30.51%-74.64% relative to QFAST, SQUANDER, and Fast-USYN, respectively, on common successful instances. On 4--6-qubit quantum algorithm benchmarks, the corresponding reductions are 27.27%-36.77%, 20.65%-69.10%, and 36.31%-71.88%, respectively.

quant-ph · cs.ET

新论文 · v1arXiv:2611.26218

MixReact: Physics-Based Reactive Humanoid Control from Multimodal Cues via a Discrete-Continuous Mixture of Transformers

Bin Li, Xing Zhu, Jingya Wang

原文摘要

Humanoid agents in everyday environments are expected to react to diverse cues as humans do, with semantically appropriate and physically executable behaviors. Existing cue-driven reaction generation methods support only a narrow range of cue modalities and are limited to purely kinematic generation, leaving the resulting reactions susceptible to physical artifacts. To this end, we present MixReact, the first unified framework for physics-based reactive humanoid control from text, audio, and video cues, integrating a Discrete--Continuous Mixture of Transformers (DisCo-MoT) for state prediction with a History-aware Action Transformer (HAT) for physical execution. DisCo-MoT couples a discrete masked-modeling branch with a continuous autoregressive diffusion branch via one-way mixture attention within a MoT architecture. Guidance from discrete context mitigates collapse into averaged behaviors in one-to-many reaction generation, while direct prediction in continuous state space bypasses the decoding bottleneck of discrete representations. HAT then maps the predicted next state and observed execution history to executable actions, enabling robust closed-loop control in physics-based simulation. Experiments across all three modalities demonstrate consistent improvements over the baselines in fidelity, diversity, and physical consistency, while ablations validate the complementary contributions of the components. Our code will be released to facilitate future research. Project page: https://binlee26.github.io/MixReact_Page/

cs.CV

版本更新 · v2arXiv:2604.12075

OpenTME: An Open Dataset of AI-powered H&E Tumor Microenvironment Profiles from TCGA

Maaike Galama, Nina Kozar-Gillan, Christina Embacher, Todd Dembo, Cornelius Böhm, Evelyn Ramberger, Julika Ribbat-Idel, Rosemarie Krupar 等 21 位作者

原文摘要

The tumor microenvironment (TME) plays a central role in cancer progression, treatment response, and patient outcomes, yet large-scale, consistent, and quantitative TME characterization from routine hematoxylin and eosin (H&E)-stained histopathology remains scarce. We introduce OpenTME, an open-access dataset of pre-computed TME profiles derived from 5,268 H&E-stained whole-slide images across ten cancer types (bladder, breast, colorectal, head and neck, liver, lung, ovarian, pancreatic, prostate, and stomach cancer) from The Cancer Genome Atlas (TCGA). All outputs were generated using HETA (H&E Tissue Analysis), an AI-powered application built on the Atlas family of pathology foundation models, which performs tissue quality control, tissue segmentation, cell detection and classification, tumor zone and tertiary lymphoid structure (TLS) detection, and spatial neighborhood analysis, yielding over 20,000 quantitative readouts per slide at cell-level resolution, including curated features such as tumor-infiltrating lymphocytes, tumor mitotic index, or mature TLS counts. OpenTME is available for non-commercial academic research on Hugging Face. We will continue to expand OpenTME over time and anticipate it will serve as a resource for biomarker discovery, spatial biology research, and the development of computational methods for TME analysis.

cs.CV · cs.AI · cs.LG · q-bio.QM

新论文 · v1arXiv:2611.26212

The Necessity of Acceptance & Rejection in Inferential Reasoning

Khashayar Irani

原文摘要

In this paper, we argue that acceptance and rejection constitute two fundamental positions necessary for inferential reasoning. Our central thesis is that a proposition acquires an inferential role when it is considered from a position of acceptance or rejection, rather than purely understood as propositional content. We distinguish between understanding a proposition, entertaining it hypothetically, and employing it within an inference. Particular attention is given to hypothetical reasoning and suspended judgement, which appear to challenge the necessity of adopting either position. We maintain that these cases do not undermine our thesis, since inferential reasoning can involve provisional acceptance or rejection without requiring personal belief or permanent commitment. Accordingly, the necessity of these positions should be understood as inferential rather than psychological. By examining the relationship between propositional content, inferential positions, and rational commitment, we defend the view that acceptance and rejection provide the fundamental conditions under which propositions can function within reasoning. This establishes a philosophical foundation for understanding inference through opposed rational positions.

cs.LO

新论文 · v1arXiv:2611.26211

SpecWM: Turning Verification into Refinement for Streaming World Models

Jiaming Li, Lingzhen Li, Xiaze Yang, Chenyu Zhu, Kaiqi Liu, Xiaotong Zhao, Songlian Li, Toyota Li 等 12 位作者

原文摘要

Recently, video world models have advanced interactive generation, with large models offering higher quality and smaller models enabling faster inference. Existing speculative methods combine their strengths through fast draft generation and selective target regeneration guided by rewards on decoded frames. However, verification covers only the external scorer's evaluation dimensions and adds decoding and scoring costs. Moreover, these scores provide no correction, requiring costly target regeneration for rejected drafts. To address these limitations, we propose Speculative World Model (SpecWM), a unified, training-free inference framework for streaming world models. It verifies draft chunks using the target's latent velocity field. Verification also yields a reusable correction; two thresholds select Accept, Refine, or Reject. Specifically, one-step refinement reuses it to improve perceptual quality, while three-step refinement strengthens camera following and trajectory consistency. These findings motivate transition-aware refinement. On WBench Navigation, SpecWM improves visual quality at 1.63$\times$ speedup over the target and raises NavScore from the draft's 75.99 to 85.63, achieving the best quality-speed-control trade-off. Additionally, our LongSpecBench shows sustained quality and control over long, multi-turn rollouts, while experiments on Hy-Nomas validate SpecWM across backbones and denoising budgets.

cs.CV

版本更新 · v3arXiv:2607.26921

From Keypoints to Predictive Distributions: Post-Hoc Uncertainty for YOLO-Pose Models

Alexej Klushyn, Juan Rivero Sesma, Florian Seligmann, Richard Kurle, Kinh Tieu, Jayant Sen Gupta

原文摘要

YOLO-Pose models provide efficient multi-object keypoint localization, but do not quantify the associated spatial uncertainty. We introduce a lightweight post-hoc probabilistic extension that augments a trained YOLO-Pose model with calibrated bivariate predictive distributions over keypoint locations, centered at the model's original predictions. Concretely, we train additional probabilistic heads with an importance-weighted negative log-likelihood to predict an input-dependent $2\times2$ dispersion matrix for each keypoint, followed by Gaussian calibration for broad downstream compatibility or Student-$t$ calibration for distributional fidelity. Complementing this, we propose an evaluation protocol that combines a suite of distributional calibration diagnostics with average keypoint precision (AKP), a keypoint-level extension of the COCO AP protocol for assessing reliability rankings. Experiments on COCO with YOLO-NAS-Pose and YOLO26-Pose show that the learned uncertainty estimates enable keypoint-level reliability ranking, Student-$t$ calibration best captures the empirical residual distribution, and uncertainty-based pruning removes unreliable keypoints. In vision-based aircraft landing, calibrated predictive distributions over runway keypoints support uncertainty-aware position estimation and downstream sensor fusion.

cs.CV

新论文 · v1arXiv:2611.26201

Learn, Freeze, and Transfer an Activation Function Across Architectures

Arun Prakash A

原文摘要

Transfer learning typically reuses knowledge acquired by a source network through its learned weights. We investigate whether a learned activation function can also be transferred and remain useful in networks trained from scratch. We study this complementary form of transfer through a learn-freeze-transfer protocol, in which the activation is optimized jointly with a source network in a single training run, and is then frozen and reused in target networks trained from scratch. A pointwise activation with globally shared parameters is independent of layer dimensions and can therefore be incorporated into networks of different architectures trained from scratch. We instantiate this protocol with FAct, a five-parameter activation represented by a two-harmonic truncated Fourier series, initialized from a Fourier approximation of GELU and learned in a Vision Transformer (ViT) on ImageNet-1K. When reused in a ViT of the same architecture trained from scratch on ImageNet-1K, the frozen activation (Frozen FAct) improves top-1 accuracy by 1.46 percentage points over GELU. Across four smaller target architectures (standard ViT, Swin Transformer, linear-attention ViT, and MLP-Mixer) and four image-classification datasets, it achieves the highest mean accuracy among eleven activation functions in 15 of 16 settings under a common training configuration, with improvements of up to 1.71 percentage points over the best conventional activation. When the learning rate and weight decay are tuned separately for each activation under the same search budget, Frozen FAct still ranks first in 11 of the 16 settings, second in four, and fourth in one. These results provide empirical evidence that a learned activation function can retain its usefulness when transferred across vision architectures, independently of the weights with which it was learned.

cs.LG · cs.CV

版本更新 · v2arXiv:2611.19320

Keep it Simple! A Multiple-Choice Task can Benefit Generative Recommendation

Wei-Hsiang Huang, Jyun-Yu Jiang, Pu-Jen Cheng

原文摘要

Sequential recommendation has recently witnessed growing interest in generative retrieval. One of the most popular approaches is to autoregressively generate the semantic identifiers (SIDs) of items as recommendations. Existing efforts mainly rely on semantic alignment, sophisticated architectural designs, and extensive hyperparameter tuning. However, the conventional learning framework for generative models could have foundational limitations. Specifically, most generative models directly predict target items without explicitly learning negative compositions and relative ranking signals. This is not well aligned with the philosophy of Bayesian personalized ranking (BPR), which emphasizes the importance of relative rankings between positive and negative samples. In this paper, we show that adding a simple multiple-choice auxiliary task into the learning objective can effectively address this issue. With minimal adaptation, we introduce Task Identifiers and Candidate Constructions to synthesize training data for the multiple-choice auxiliary task. In addition, we provide theoretical analysis of the fundamental benefits of the multiple-choice auxiliary task from the perspectives of information theory and compositional generalization. Extensive experiments on four publicly available benchmark datasets show that our approach can improve TIGER, a conventional generative recommendation model, by 4.9% to 79% in NDCG@10.

cs.IR

新论文 · v1arXiv:2611.26199

Learning to Think with Images Faithfully via Adaptive Data Selection

Yu Zhao, Jiaxin Zhang, Rohit Saxena, Fazl Barez, Pasquale Minervini, Yiwen Guo

原文摘要

Thinking with images (TwI) empowers vision-language models (VLMs) to overcome perceptual bottlenecks by actively cropping and zooming into fine-grained visual details, promising both higher accuracy and interpretable, region-grounded reasoning. However, our analysis shows that the improved accuracy of TwI models does not guarantee faithful tool use; they frequently invoke tools without actually relying on the zoomed region, undermining the reliability of tool-assisted reasoning. We trace this unfaithful behaviour to the training data: when questions are answerable without zooming, the model can answer correctly while ignoring the returned evidence, and this problem is exacerbated during training as the model becomes better at answering without tools. To keep zooming useful throughout training, we adapt the training data to the model's evolving capability and train on questions where correct zoomed evidence can still help the model answer correctly. This selection is supported by a data synthesis pipeline that localises small objects and constructs verifiable questions about their fine details, and complemented by an adaptiveness reward that favours tool-free answers when zooming is unnecessary. The experimental results show that our method substantially improves reasoning faithfulness and achieves state-of-the-art performance on visual search benchmarks (+11.6% on V*, +7.9% on HR-Bench 4K, and +9.4% on HR-Bench 8K). On multimodal hallucination benchmarks, our model also outperforms the compared TwI baselines. These results suggest that improving TwI faithfulness does not sacrifice accuracy and that both can be learnt from the right training data without directly supervising the reasoning process.

cs.CV · cs.CL

新论文 · v1arXiv:2611.26196

EmbodyAgent: Post-Training Embodied VLM Agents via Distillation, SFT, and RL

Wei Dai, Jinkun Liu, Jiayi Chen, Han Liu, Wenbo Ding, Shaolun Huang

原文摘要

Vision-language models (VLMs) can act as closed-loop robot-use agents (RUAs) by writing and executing control code through tool interfaces. However, turning an open-weight VLM into a high-performing embodied agent requires a complete post-training stack: out-of-the-box open VLMs fail completely at interactive tool contracts, strong frontier teachers are accessible only as black-box endpoints without exposed weights or token probabilities, and supervised imitation alone plateaus under rollout distribution shift. We present EmbodyAgent, an end-to-end post-training framework with three tightly coupled pipelines: (1) a black-box data synthesis pipeline that queries a strong teacher under a forced think-then-code contract and filters trajectories by task success; (2) an SFT pipeline that distills the explanation-and-program targets into an open-weight 9B VLM with both vision and language encoders trainable; and (3) an online RL pipeline that optimizes student-generated episodes via group-relative advantage with a runtime-error-penalized outcome reward. All three pipelines share one primitive-free Python execution tool exposing only raw visual observation and seven-dimensional end-effector control, with no action decoder and no interface shift across stages. Under a strictly separated evaluation protocol on ten LIBERO Spatial tasks (disjoint state splits, greedy test-time decoding, training-only safeguards), held-out success on 100 test states rises from 0/100 (base 9B VLM) to 14/100 (after SFT) and 84/100 (after RL), while training rollout success climbs from 8.4% to 87.7% and median model calls per episode drop from 36 to 11. We further identify a self-reinforcing runtime-error mode induced by outcome-based RL on executable code, and establish a failure-category monitoring and sampling-side curation protocol that stabilizes training.

cs.RO

版本更新 · v2arXiv:2611.24157

GenRF: Generative Registration-free Image Fusion

Linfeng Tang, Zhijun Fan, Yang Chen, Zizhuo Li, Hao Zhang, Jiayi Ma

原文摘要

Multi-modal image fusion combines complementary observations to improve scene visibility and perception. However, in real-world acquisition, differences in sensing principles and configurations introduce geometric discrepancies, while degradations further compromise source quality. Existing methods typically rely on explicit registration, yet large parallax complicates correspondence estimation, while mismatched fields of view leave some regions without cross-modal counterparts. Meanwhile, independent restoration underuses cross-modal information, whereas restoration-fusion methods assuming alignment remain vulnerable to misregistration. This study revisits misaligned and degraded image fusion in the era of generative foundation models, in which cross-attention enables position-agnostic complementary information aggregation, while generative priors support degradation recovery and inference in missing regions. Building on this perspective, we propose GenRF, which adapts pretrained FLUX through LoRA to jointly enhance degraded observations, infer missing cross-modal context, and fuse complementary information without explicitly estimating deformation fields. Extensive experiments on real-world infrared and visible captures show that GenRF delivers high-quality fusion directly from unregistered, degraded images without preprocessing, while improving downstream task performance under misalignment. Additional experiments demonstrate that GenRF can generalize to misaligned multi-exposure and multi-focus image fusion without task-specific fine-tuning.

cs.CV

版本更新 · v2arXiv:2610.37358

When Is Additional Retrieval Worthwhile? A Cost-Aware Study of Evidence Gain and Answer Reliability in RAG

Zhouting Zhao

原文摘要

Retrieval-augmented generation (RAG) can benefit from more sophisticated retrieval, but extra retrieval may be unnecessary for many questions and gains in evidence retrieval may not translate into faithful or correct answers. We study a cost-aware, two-action retrieval policy that chooses between a dense-retrieval-plus-reranking baseline and a hybrid lexical--dense retriever. Rather than classifying baseline retrieval as simply successful or unsuccessful, we estimate the question-specific incremental evidence-retrieval benefit of hybrid retrieval using features available before the routing decision. A regularized linear model and decision threshold are selected using document-grouped cross-validation and frozen prior to held-out evaluation. On 60 previously unseen QASPER training-split articles (188 questions, 169 evidence-evaluable), the policy triggers hybrid retrieval on 46 questions (24.5\%) and obtains the same evidence Hit@10 as always-hybrid retrieval (78.70\%, versus 76.92\% for always-keep). Paired, paper-cluster bootstrap intervals do not establish a reliable utility advantage. We further compare generated answers from a 4-bit Qwen3-4B model under the three retrieval policies. Provisional answer-level assessments show no clear correctness or faithfulness improvement after partial review, despite the evidence-retrieval result. The generation assessments remain model-assisted and lack independent human validation. These results expose an important distinction between retrieving relevant evidence efficiently and improving the reliability of the generated answer. The work is presented as a reproducible empirical study, not a claim of statistically established answer-quality superiority.

cs.IR

版本更新 · v2arXiv:2611.23531

RESCUE Jumper: A Centimeter-Scale Rolling and Jumping Robot for Search and Rescue

Kiran Marques, Shashwat Singh, Ben D'Ambrosia, Zeynep Temel, Melisa Orta Martinez

原文摘要

Centimeter-scale robots are promising for urban search and rescue because they can enter confined spaces that are inaccessible or unsafe for humans. However, their small size limits obstacle traversal after deployment. This paper presents the RESCUE Jumper, a 125 g mobile robot with a 6.2 cm width and 6.2 cm diameter wheels that combines ground rolling with jumping to traverse steps and gaps that exceeds its rolling capability. The RESCUE Jumper uses its two actuators for both rolling mode and jumping by reversing the direction of wheel motion. Forward wheel motion enables rolling, while reverse wheel motion winds a spring steel tail to store elastic potential energy and release it for jumping. The RESCUE Jumper varies tail winding speed to control jump direction, transitioning from backward to forward jumps as winding speed increases from 0.75 rad/s to 8.73 rad/s. The launch angle of the jumps ranges from 45 degree to -11 degree with respect to the vertical axis, reaching a maximum height of 9.2 cm and a maximum lateral displacement of 11.2 cm. We model the winding speed-dependent jumping behavior in three phases: tail release to determine the contact point and robot orientation, tail straightening until liftoff, and ballistic flight to predict jump height and lateral displacement. Finally, qualitative tests highlight the robot's locomotion in cluttered, real-world environments. The model and experiments presented in this work can inform future designs of space-constrained jump mechanisms in centimeter-scale robots for search and rescue and inspection in unstructured environments.

cs.RO

新论文 · v1arXiv:2611.26188

Approximation Algorithms for Asymmetric Multi-Path TSP

Manuel Christalla, Vera Traub

原文摘要

Asymmetric Multi-Path TSP is the generalization of the Asymmetric Traveling Salesperson Problem where we are looking for $k$ walks, each with prescribed start $s_i$ and prescribed end $t_i$, such that every vertex is visited by at least one of the walks. The objective is to minimize the total length of all walks. In general, it is NP-hard to find any approximation for this problem in polynomial time (even if the approximation factor is allowed to depend on the number of vertices). We show that one can obtain an $O(k)$-approximation in time $n^{O(k)}$, answering an open question by Friggstad [2013]. For the special case where all tour start vertices $s_i$ are identical and all end vertices $t_i$ are identical, we obtain an $O(k)$-approximation in polynomial time, as well as an $(O(\frac{1}ε), 1+ε)$-bicriteria approximation. For the multi-depot setting, where $s_i =t_i$ for all $i$, we obtain a constant-factor approximation in polynomial time. Finally, our results imply improved constant-factor approximation algorithms for Asymmetric Regret-Bounded Vehicle Routing and unit-weight Path ATSP.

cs.DS

新论文 · v1arXiv:2611.26187

Invertible Transport Between Sample-Only Distributions via Projected Characteristic Functions

Juan Gutiérrez, Victor Gutiérrez-García, José Luis Blanco-Murillo

原文摘要

Many useful latent distributions can be sampled but do not have a tractable density. Such distributions may be represented by empirical collections of real-world observations or generated by scientific simulators and black-box generative models. These sample-only priors cannot be used directly in likelihood-based normalizing flows, which require evaluating the prior density. We propose Projected Characteristic-Function matching (PCF), a density-free framework for learning an invertible map between a data distribution and a prior specified only through samples. Our method aligns distributions using projected empirical characteristic functions, eliminating the need for density estimation, adversarial training, or paired observations. To address the non-uniqueness of the transport map, we introduce an optional transport regularizer that selects lower-displacement transformations while preserving endpoint alignment. We benchmark PCF on controlled transports, sample-efficiency studies, and high-dimensional alignment tasks. PCF matches the accuracy of kernel MMD on the controlled benchmark and on raw-pixel MNIST--USPS at a cost linear in the batch size, and it is more sample-efficient, achieving lower endpoint error than MMD in 13 of 15 paired runs across library sizes. By avoiding pairwise kernel evaluation, it reduces discrepancy memory by 29.8% and trains at batch sizes where kernel MMD exceeds GPU memory. These results show that PCF provides accurate and efficient invertible transport, particularly in sample- and memory-limited settings.

cs.LG · cs.CV

版本更新 · v2arXiv:2605.30727

MosaicLeaks: Privacy Risks in Querying-in-the-Open for Deep Research Agents

Alexander Gurung, Spandana Gella, Alexandre Drouin, Issam H. Laradji, Perouz Taslakian, Rafael Pardinas

原文摘要

Deep research agents increasingly combine private local documents with external tools like web retrieval, creating a privacy risk: an agent's external queries may leak sensitive information from its local context. This risk is amplified by the mosaic effect, where individual queries may appear harmless but become revealing in aggregate. We introduce MosaicLeaks, a benchmark of 1,001 multi-hop deep research tasks that chain private enterprise documents and a public web corpus, forcing agents to make external queries that depend on local information. We evaluate leakage with an adversary LLM that observes only the agent's external queries and attempts to infer private information at three levels: the agent's research intent, answers to specific private questions and verifiable claims about the enterprise documents. We find that models across families and sizes frequently leak at all three levels, that zero-shot privacy prompting has inconsistent effects across models and that reinforcement learning for task performance alone worsens leakage. To address this, we propose Privacy-Aware Deep Research (PA-DR), an RL framework that combines situational rewards for task success with a learned privacy classifier to provide dense credit assignment over both per-query and mosaic-level leakage. Training Qwen3-4B-Instruct with PA-DR improves accuracy from 48.7% to 58.1% and reduces Privacy Leakage from 34.0% to 6.5%.

cs.CL