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

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 17:33 — 2026-11-16 17:33(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:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 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。

23,827 已收录论文19,941 AI 相关6,921 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 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.13306

Train High, Ship Low: Efficient LoRA Synchronization for Distributed On-Policy Post-Training

Shenghui Li, Li Ju, Thiemo Voigt

原文摘要

Transmitting LoRA adapters to rollout workers can bottleneck distributed on-policy post-training over bandwidth-constrained networks. Lowering the training rank may limit the capacity a workload needs, while adaptive optimizer updates are difficult to compress. Rollout workers can instead reconstruct updates from gradients by maintaining replicated optimizer states. We introduce HiLo, a compressor-agnostic framework that replaces parameter transmission with compressed gradient dissemination and local optimizer replay. By applying the same decoded gradients, the learner and workers maintain consistent policy states at the same version under reproducible execution. We further develop Spar, a budget-aware gradient compressor that combines spectral truncation, adaptive rank allocation and error feedback to decouple training rank from communication cost. Experiments across on-policy distillation and reward-guided post-training show that HiLo with Spar maintains learning quality close to full synchronization while transmitting as little as 1.6% of the adapter bytes, and accelerates end-to-end updates by up to $2.2\times$ under bandwidth constraints.

cs.LG · cs.AI

版本更新 · v2arXiv:2610.28856

Depth-guided Geometric Adaptation for Few-shot Image Classification

Zhiqi Miao, Estefanía Talavera, Weichuan Zhang, Jiapan Guo

原文摘要

Few-shot image classification (FSIC) frequently suffers from visual ambiguity, where background clutter and RGB appearance similarities hinder discriminative feature matching in data-scarce settings. To mitigate this, we propose DAFIC, a geometry-guided framework that incorporates monocular depth into representation learning, episodic adaptation, and dense support-query matching. DAFIC first learns geometry-aware token representations through RGB-D self-supervised pre-training. Subsequently, the Depth-guided Geometric Adaptation (DGA) module uses depth-derived geometry to refine patch representations with geometry-enriched class context while suppressing background interference. Spatial Bidirectional Patch Matching (SBiM) then performs bidirectional dense matching on the refined features, reducing sensitivity to spurious correspondences and background clutter. Extensive experiments on four benchmarks show that DAFIC achieves strong performance against existing methods, with ablation and robustness analyses supporting the effectiveness of coupling geometry-conditioned episodic adaptation with bidirectional matching for few-shot visual recognition.

cs.CV

版本更新 · v3arXiv:2602.08874

Do Reasoning LLMs Refuse What They Infer in Long Contexts?

Yu Fu, Haz Sameen Shahgir, Huanli Gong, Zhipeng Wei, N. Benjamin Erichson, Yue Dong

原文摘要

Long-context LLMs can infer objectives that are not explicitly stated. This capability is useful for reasoning over documents, code, and tool traces, but it also introduces a safety risk. Harmful intent can be distributed across a context and become apparent only after the model combines the relevant information. Existing safety evaluations largely focus on explicitly stated harmful requests and therefore do not fully capture this failure mode. We introduce compositional reasoning attacks, a long-context attack setting in which harmful requests are decomposed into semantically incomplete fragments and embedded in long contexts. The final query is neutral, and the model must retrieve and combine the fragments to infer the implied harmful objective. Empirically, we show that models generally refuse harmful requests when they are explicitly stated. However, refusal rates drop when the same objectives must be reconstructed from fragments, and these failures often become more pronounced in longer contexts. Our analyses suggest that this gap cannot be explained by retrieval difficulties alone. Models can often reconstruct the harmful objective but do not reliably refuse it. Increasing inference-time reasoning effort improves refusal, but at a higher computational cost, with unsafe responses still occurring. Our results reveal a long-context safety gap: Models are better at refusing harmful requests they see than harmful objectives they infer.

cs.CL · cs.CR

版本更新 · v2arXiv:2610.28480Berkeley BAIR

SuperMimic: Scaling Humanoid Whole-Body Control with One Differentiable World Model

Qiayuan Liao, Yiyang Shao, Junfeng Long, Kevin Zakka, Roberto Horowitz, Pieter Abbeel, Koushil Sreenath

原文摘要

Tracking large human-motion datasets has become the dominant route to general, expressive humanoid whole-body control, but scaling across many motions is expensive. Current pipelines use model-free reinforcement learning, either merging per-motion specialists through lossy distillation, or brute-forcing a single policy with cluster-scale compute. SuperMimic amortizes learning across all motions with one differentiable world model of their shared dynamics, fit from logged transitions of a standard rigid-body simulator. The world model and the tracking policy train together in one loop, and backpropagation-through-time over short imagined rollouts gives the policy analytic gradients. Fast imagined rollouts and analytic gradients make policy learning efficient. In 3 hours on a single GPU, SuperMimic surpasses the return of a state-of-the-art motion tracker baseline trained for 7 days on 128 GPUs. It reduces GPU-hours by more than $1000\times$ and fails on only 25 of 129,514 benchmark motions, versus 179 failures for the baseline. After 9.8 hours on two GPUs, SuperMimic achieves zero failures. From 1 to 264 hours of motion, the world model's prediction error stays stable, and GPU-hours to a target return grow slowly. Our policy transfers to a physical Unitree G1 across diverse and acrobatic motions. SuperMimic removes compute as the bottleneck to scaling humanoid whole-body control, making it practical to measure motion-tracking scaling laws.

cs.RO

新论文 · v1arXiv:2611.13304

DUO: Dual Readouts of Diffusion Models for OOD Detection

Alireza Javid, Shirin Shoushtari, Nuria González Prelcic

原文摘要

Diffusion models are powerful generative methods for learning and sampling from complex data distributions. Safely deploying these models requires detecting inputs that fall outside their training distribution. Because diffusion models recover clean samples from noisy inputs, reconstruction error is often used for out-of-distribution (OOD) detection. This approach assumes that in-distribution (ID) inputs are reconstructed more accurately than OOD inputs. However, OOD inputs may be reconstructed equally well or even better, making this score unreliable. We therefore propose the leading sensitivity spectrum of intermediate denoising features as a complementary OOD signal and demonstrate that it remains informative when reconstruction error is misleading. We introduce DUal-readout of diffusion models for OOD detection (DUO), a fully unsupervised, training-free OOD detector that combines reconstruction error and feature sensitivity. DUO improves average AUROC by approximately 6% points over the strongest baselines while substantially reducing inference cost, and achieves SOTA on near-OOD and high-resolution benchmarks.

cs.CV · cs.LG

版本更新 · v2arXiv:2611.00546

Low-Margin Branch Points in Deterministic LLM Deliberation

Hajime Shimao, Warut Khern-am-nuai

原文摘要

Deterministic multi-agent LLM deliberation can exactly re- play a fixed transcript, yet exact replay alone does not test local resistance to controlled internal interventions. Because each response becomes context for later agents, a changed greedy token can redirect a transcript-mediated execution. We present a white-box audit of this local failure mode in a five-agent committee under greedy decoding. We prospectively select low- and high-margin token positions, require exact no-op re- play, inject norm-relative residual displacements, and measure first transcript divergence within ten generated tokens. Low- margin positions are more branch-sensitive than high-margin controls, while matched margin-reducing gradient directions branch substantially more often than margin-increasing con- trols. We then continue selected realized branches through the committee to distinguish textual persistence from preference and final-decision changes. The contribution is a controlled audit for local branch susceptibility in this specified protocol, not an estimate of deployment frequency, decision correct- ness, or a phenomenon unique to multi-agent systems.

cs.AI

版本更新 · v2arXiv:2611.00301

The Rise of Low Precision Floating Point

Guy Lemieux, Michael L. Overton

原文摘要

Floating point computing has dominated scientific computations since the 1950s because of its versatile ability to approximate real numbers with both sufficiently high precision and sufficiently great range. Since 1985, two specific formats have become standard across the industry, one with 32 bits which is adequate for many purposes and one with 64 bits which allows numbers with both much higher precision and much greater range for applications where these are needed. However, during the past decade, deep learning has come to dominate computation, and narrower floating point formats with lower precision and reduced range have steadily become more common. In this article we discuss this phenomenon, why it is happening, how various 16-bit, 8-bit and even 4-bit floating point formats have been developed, and efforts to standardize these formats.

cs.MS · cs.AR · cs.LG · math.NA

版本更新 · v4arXiv:2610.29929

Privacy Preference Controls for Agentic Systems

Shreya Kochar, Peeranat Sugsavanvit, Vidur Gupta, Joseph A. Calandrino, Deepak Kumar, Brett Frischmann, Sebastian Zimmeck

原文摘要

In response to vast and widespread online tracking, regulators and technologists alike have worked to develop laws and tools that allow people to express their privacy preferences. These measures seek to offer users greater control over the sale and sharing of personal information, putting agency in their hands to protect their privacy. However, the web is undergoing a seismic shift, away from strictly user-driven behavior towards agentic behavior, where AI agents take autonomous actions on behalf of users. In this study, we ask: What should privacy preference controls look like in the agentic web and agentic systems more generally? To answer this question, we develop a taxonomy of enforceable privacy preferences for agentic systems. Our taxonomy is informed both by laws and empirical studies of existing privacy tools as well as an audit of 30 leading AI assistants and agent platforms. To explore how our taxonomy can be implemented, we design and develop eight open-source prototypes that mirror real-world agentic applications and demonstrate how major aspects of our taxonomy can be structurally integrated in agentic protocols, such as the Model Context Protocol and Agent2Agent protocol. Ultimately, our study seeks to provide the groundwork for ensuring end-user privacy and autonomy is not lost in the newly arriving agentic world.

cs.CY · cs.HC

版本更新 · v2arXiv:2608.10342

Shape optimisation of nonlinear Naghdi shells on discrete geometries

Ado Farsi, Alberto Paganini

原文摘要

We present an automated framework for the shape optimisation of a geometrically nonlinear, five-parameter Naghdi model on faceted triangulations. By recovering directors numerically, we remove the requirement for an analytic or spline parameterisation of the mid-surface, whereas partial selective reduced integration alleviates locking. The residual and tangent of symbolic energies are generated in an automated fashion building on Firedrake's and UFL's symbolic differentiation capabilities. Additionally, UFL's and pyadjoint's algorithmic differentiation enables automated first and second shape derivative evaluations that are verifiably correct via Taylor tests. The forward model agrees with the Sze/Abaqus semi-cylinder reference. A three-model mesh-refinement study indicates that geometry recovery and surface faceting have small effects on the predicted deflection. Numerical experiments show that 100 trust-region iterations suffice to reduce the squared-displacement functional of a semi-cylinder by 98.4% and the elastic strain energy of a bracket by 94.6%. The latter result is validated against a COMSOL benchmark. Non-uniqueness of optimal shapes is demonstrated by optimising initial designs subject to small perturbations. Comparisons with linearised designs distinguish optimisation performance from the accuracy of the predicted nonlinear response.

math.NA · cs.CE

版本更新 · v2arXiv:2509.26282

Benchmarking Stochastic Interpolants for Modeling Physical Systems

Anthony Zhou, Alexander Wikner, Amaury Lancelin, Pedram Hassanzadeh, Amir Barati Farimani

原文摘要

Generative models have recently emerged as powerful surrogates for physical systems, demonstrating increased accuracy, stability, and/or statistical fidelity. However, most approaches rely on iteratively denoising a Gaussian, a choice that may not be the most effective for autoregressive prediction tasks, where the current and future states are often closely related. We therefore benchmark generative models based on stochastic interpolants, which can learn maps between arbitrary densities, against standard Gaussian-denoising frameworks across a range of fluid and climate systems. Following prior work, we consider a transport map for dynamical systems that learns an interpolant between a point mass at the current state and a conditional distribution of future states. We find that stochastic interpolants can match or outperform Gaussian-denoising baselines in pointwise accuracy, spectral fidelity, and probabilistic skill. Furthermore, we identify a tradeoff where deterministic sampling can improve pointwise accuracy but smooth predictions, whereas stochastic sampling recovers spectral content and calibration but requires more function evaluations, as well as ensemble averaging to recover pointwise accuracy. As a whole, these results establish stochastic interpolants as a competitive baseline for generative physical emulation, and also indicate that the training loss, sampler, and transport map should be chosen with the physical system and target metric in mind.

cs.LG

新论文 · v1arXiv:2611.13298

Neural Network-Assisted CLEAN for Efficient Multipath Parameter Estimation in MIMO Systems

Chaofan Deng, Linyu Sun, Jaeho Lee, Zishen Wan, Arijit Raychowdhury

原文摘要

High-resolution multipath estimation in wideband multiple-input multiple-output (MIMO) channels requires repeated searches over angle of arrival, angle of departure, and propagation distance. This paper presents neural network-assisted CLEAN (NN-CLEAN), which replaces the multidimensional search at each extraction step with a multi-head classifier while retaining least-squares (LS) estimation of the complex path gain, parametric reconstruction, and residual cancellation. The same classifier is applied to successive residuals, allowing the extraction depth to vary without changing its output structure. With the number of iterations prescribed by the reference multipath-component (MPC) count, off-grid synthetic tests show that NN-CLEAN slightly exceeds grid-search CLEAN (GS-CLEAN) in path accuracy for one and two MPCs, although its accuracy declines more rapidly at larger path counts. For complete three-MPC extraction at a batch size of eight, NN-CLEAN achieves an approximately $27\times$ speedup and a $52$-fold reduction in peak GPU memory relative to GS-CLEAN. Applied without retraining to two-MPC line-of-sight (LOS) and non-line-of-sight (NLOS) Sionna ray-tracing channels within a coded MIMO link, NN-CLEAN substantially reduces channel-reconstruction mean-squared error (MSE) and bit error rate (BER) relative to interpolated LS channel estimation. GS-CLEAN retains an accuracy advantage on these channels, indicating the estimation cost associated with the computational savings.

cs.LG

新论文 · v1arXiv:2611.13297

Domain adaptation of a video Foundation model for Heart Failure Diagnosis from Echocardiography

Mahyar Bolhassani, Tijana Geroski, Narayana S. Singam, Amir Amini

原文摘要

The rapid advancement of foundation models has transformed computer vision, yet their adaptation to medical imaging, particularly purpose built foundation models for spatio temporal echocardiography videos, remains limited. In this work, we explore the feasibility of fine tuning a pretrained foundation model for video (TimeSformer) for automated diagnosis of reduced ejection fraction heart failure (HFrEF) from apical four chamber videos. The model is finetuned on the publicly available RVENet A4C dataset with a phase aware clip generation strategy that captures complementary systolic and diastolic dynamics. We employ divided space time attention, layer wise learning rate decay, and multi clip inference to enhance robustness under limited data. Experimental results show that full fine tuning of the proposed model outperforms classifier only tuning and a 3D CNN baseline. These findings highlight the potential of leveraging foundation video models for echocardiography based heart failure diagnosis and motivates further domain adaptation studies in medical imaging.

cs.CV

新论文 · v1arXiv:2611.13296

A Unified Interactive Framework for Real-Time Three-Dimensional Cellular Automata Simulation in XR

Ashkan Rezaei, Azam Bastanfard, Mohammad Erfan Safabakhsh

原文摘要

Integrating three-dimensional cellular automata (3D CA) into extended reality (XR) requires coordinated simulation, volumetric data management, rendering, and interaction under variable hardware constraints. This paper presents a hybrid study combining a critical review of existing approaches with a unified architecture for real-time 3D CA in XR. The proposed five-layer architecture integrates voxel and rule management, parallel computation, interoperability middleware, visualization, and XR interaction. Its key principles include hardware-aware execution, asynchronous simulation-rendering, adaptive fidelity, and cross-engine interoperability. An analytical evaluation framework is defined to assess performance, latency, scalability, memory efficiency, simulation correctness, and interaction quality. The proposed framework provides a foundation for developing portable and interactive 3D CA systems across desktop and mobile XR platforms.

cs.GR

新论文 · v1arXiv:2611.13295

Time Series Change Point Detection with Gaussian Processes

Olga Isupova, Danil Kuzin, Fredrik Gustafsson, Lyudmila Mihaylova

原文摘要

This paper proposes a novel general Gaussian process framework for change point detection in time series. A change is defined as an alteration of the hyperparameters of the Gaussian process prior. We formulate the problem in the context of statistical hypothesis testing and demonstrate its performance over both offline and online multiple change points detection. The approach provides theoretical guaranties of its performance. An important advantage of the developed framework is that it does not need a detailed specification of the time series function before and after a change. The hyperparameter values are learned from the data. Comprehensive evaluation of the proposed framework is provided both on synthetic and real data and its efficiency is demonstrated.

stat.ML · cs.LG · math.ST · stat.ME

新论文 · v1arXiv:2611.13294

Function Inversion Reporting

Itai Dinur, Alexander Golovnev, Chao Yan, Yiding Zhu

原文摘要

In the Function Inversion problem, the goal is to invert a function $f:[N] \to [N]$ in two phases. In the preprocessing phase, the offline algorithm computes an advice string of length $S$ bits. In the online phase, the online algorithm receives the advice and a challenge $y \in [N]$, and the goal is to find a preimage $x \in [N]$ such that $f(x) = y$ in time $T$. The problem was initially studied in cryptography, but in recent years it has found various applications to data structure problems. Yet, several of the applications require a variant of Function Inversion, known as Function Inversion Reporting, where the goal is to output all preimages of the challenge $y$. In this paper, we study the Function Inversion Reporting problem in a systematic way by unifying and improving existing algorithms. As a result, we obtain improved data structures for several problems including 3SUM-Indexing Reporting, Range Reporting, Approximate Nearest Neighbor, Jumbled Indexing Reporting, and Gapped String Indexing Reporting.

cs.DS

新论文 · v1arXiv:2611.13293

Decode Token Parallelism: Memory-Efficient Distributed Attention Parallelism for Scalable LLM Decoding

Susav Shrestha, Brad Settlemyer, Narasimha Reddy

原文摘要

Serving large language models at high concurrency with long contexts requires KV-cache capacity and attention bandwidth that grow with the decode pool. Existing parallelization strategies trade one against the other: data parallelism replicates model weights, limiting KV capacity; tensor parallelism stops scaling attention at the model's KV-head count and pushes dense collectives across nodes; and decode context parallelism (DCP) recovers capacity by sharding the sequence but adds cross-node aggregation of partial attention results. We observe that during decode, dense layers and attention scale differently: dense layers amortize weight reads across the batch and run efficiently within a single NVLink domain, whereas attention cost grows with every active request's KV cache. We present Decode Token Parallelism (TKNP), a decode-pool architecture that decouples weight placement from attention ownership. TKNP distributes a single model copy across nodes in balanced layer blocks. The active node holding a block executes its projections and MLP for the full batch using intra-node tensor parallelism, while every node computes attention for its own requests against locally resident KV cache. This extends request-local attention across nodes without replicating weights: only current-token activations cross the network, dense all-reduces remain within NVLink, and attention requires no cross-node merging of partial results. Implemented in vLLM and evaluated on Llama 3.1 405B and Nemotron-4 340B on up to 64 H100 GPUs, TKNP improves completion throughput for long-context, high-concurrency workloads by up to 1.7$\times$ over DCP and by up to 2.06$\times$ over data parallelism at matched GPU count.

cs.DC · cs.CL · cs.LG

新论文 · v1arXiv:2611.13292

Large Language Model Explainability for Planning Lunar Rover Trajectories under Uncertainty

Michelle Ho, Maximilian Adang, Zachary Booth, David E. Astle, Margaret Hansen, Edward Balaban, Mykel J. Kochenderfer

原文摘要

Planning planetary rover trajectories under probabilistic uncertainty is a multi-objective optimization problem that science teams currently iteratively solve and verify by hand. This process becomes impractical when timelines and constraints frequently shift throughout the mission planning phase. Sampling-based planners such as Monte Carlo tree search can speed up this process, but their outputs do not preserve traceability to the science objectives that justify each plan, which the science team needs to verify. We propose an interactive assistant based on a large language model (LLM) that can explain planner trajectories using domain vocabulary and re-run the planner under user-specified conditions to compare alternatives. Previous work has used LLMs inside planner decision-making loops, but we explore using them for post-planning explanation, where they are more likely to be trusted since they do not directly influence planner decisions. Our framework pairs a simulator inspired by the NASA Volatiles Investigating Polar Exploration Rover (VIPER) mission with a ReAct queryable interface that calls curated action tools and retrieval functions. We evaluate the assistant on a query bank consisting of plan comparisons, feasibility, and lookup queries. Experiments show that 90.9% of the assistant's responses are faithful to the planner's outputs, a nearly 65% improvement over zero-shot prompting of the same LLM without tool access, demonstrating the potential for trustworthy explainability of uncertainty-aware traverses with an LLM-based system.

cs.RO

新论文 · v1arXiv:2611.14573

Beyond the First Hit: Towards Tight Guarantees for $k$-means++

Aravind Reddy

原文摘要

Let $R_k$ be the worst-case ratio between the expected cost of the $k$ seeds chosen by $k$-means++ and the optimal $k$-means cost. In their seminal paper introducing $k$-means++, Arthur and Vassilvitskii (SODA 2007) showed that $2\ln k\le R_k\le8(\ln k+2)$, and Makarychev, Reddy and Shan (NeurIPS 2020) improved the upper bound to $5(\ln k+2)$. We prove $R_k\le\frac{1163}{233}+2.108\,H_{k-2}$ for every $k\ge3$ by a computer-assisted argument, and $R_k\le5+2.3139\,H_{k-2}$ for every $k\ge2$ by a short analytic argument; here $H_j$ is the $j$th harmonic number. Since $H_{k-2}\le1+\ln k$, this lowers the leading coefficient of $\ln k$ from $5$ to $2.108$. We also determine $R_2=5$ and $R_3=185/32$ exactly; both are suprema that are approached but not attained. On the lower side we prove $R_k\ge2(1+H_{k-1})$ for every $k$, and give a second family of lower bounds that is larger than this for $2\le k\le18$. Previous analyses bound the expected cost of a cluster just after it is first sampled by a constant times its optimal cost, and then charge that cost for the rest of the run. We instead track how a cluster's cost evolves after its first hit: a cluster left with a large residual cost is likely to be sampled again before it accumulates much of the logarithmic charge, and each repeat repairs it.

cs.DS · cs.LG

新论文 · v1arXiv:2611.13289

MRFoundry: Knowledge-guided agent loops for end-to-end MRI research

Ke Wang, Atakan Topcu, Hossein Momeni, Molin Zhang

原文摘要

AI agents can write code, use scientific software, and revise computational workflows, opening new possibilities for MRI research. Effective assistance requires connecting acquisition physics, data conventions, specialized tools, and scientific validation. We present MRFoundry, an open-source, extensible package that connects MRI knowledge to agent actions and output checks. Project-local memory preserves decisions and evidence, while reviewed contributions allow researchers to improve shared guidance. Researcher-supervised examples demonstrate skill-guided sequence auditing and acquired-data reconstruction, connecting tool use, output checks, and documented decisions. Alongside MRFoundry, we introduce MRI Agent Bench to compare agents with and without the package across models and MRI task domains. Across 240 paired Core evaluations spanning 24 task types and ten models, all-checks-passed completion increased from 67.5% without MRFoundry to 78.3% with it. Across 134 Hard pairs, completion increased from 36.6% to 44.8%. MRFoundry makes MRI workflow expertise available as reusable guidance that researchers can inspect, adapt, and extend within existing agent and scientific software environments. MRFoundry is openly available at https://github.com/KeWang0622/MRFoundry.

eess.IV · cs.AI

版本更新 · v2arXiv:2611.09505

BEiTScore++: Reference-free Image Captioning Evaluation with BEiT-3 and Conformalized Quantile Regression

Gonçalo Gomes, Bruno Martins, Chrysoula Zerva

原文摘要

Reliable uncertainty estimation is important for deploying evaluation metrics in real-world settings, where both input ambiguity and domain shifts are common. In this work, we propose an uncertainty-aware extension of the BEiTScore image captioning metric, producing conformally calibrated confidence intervals alongside alignment scores. Our approach models predictive distributions over human judgments, enabling both accurate scoring and principled uncertainty quantification in a single forward pass. We evaluate our BEiTScore++ metric across multiple benchmarks with human-annotated ratings, showing that it preserves the ranking correlation of BEiTScore, while producing intervals whose width tracks the prediction error more closely than Monte Carlo dropout on most benchmarks. The estimated uncertainty also grows under image degradation and on out-of-domain artwork images, making BEiTScore++ a practical tool for uncertainty-aware evaluation of image-caption alignment.

cs.CV · cs.AI · cs.CL · cs.LG

版本更新 · v3arXiv:2605.20436

Lighting-aware Unified Model for Instance Segmentation

Qisai Liu, Alloy Das, Zhanhong Jiang, Joshua R. Waite, Aditya Balu, Adarsh Krishnamurthy, Soumik Sarkar

原文摘要

Foundation models like the Segment Anything Model (SAM) demonstrate impressive zero-shot generalization but frequently degrade under diverse real-world illumination, particularly for instance segmentation. In this work, we address this limitation by developing Lighting Convolutional-Attention (LCA), an adapter module that enhances segmentation robustness without fine-tuning the heavy backbone. LCA employs a dual-branch architecture to process RGB features alongside contrast maps, enabling physically motivated sensitivity to structural changes rather than illumination artifacts. We optimize LCA through a pairwise training strategy, introducing a targeted loss term that explicitly penalizes discrepancies between clean images and their corresponding illumination variants. To evaluate and support this architecture, we conduct a comprehensive empirical study across multiple existing benchmarks and present a novel Unity-based synthetic dataset specifically designed to accurately replicate complex real-world lighting conditions. Extensive experimental results demonstrate that our approach successfully bridges the domain gap, delivering superior lighting-robust segmentation.

cs.CV

新论文 · v1arXiv:2611.13282

Network-Co-Designed Dynamic Sparsification for Dependable Distributed Robot Learning over 3GPP Networks

Géza Szabó, Boldizsár Bunda

原文摘要

Robot fleets performing distributed learning often face volatile uplink conditions like bandwidth variation, packet loss, and latency spikes that delay or destabilize training. We propose a network-co-designed dynamic sparsification loop that couples model-update compression to network-facing byte budgets and time constraints. We describe two realizations: (i) a standards-aligned SA6/5GC mapping that leverages CAPIF with NEF/PCF/NWDAF, enriched with AI-specific semantics; and (ii) a VASEAL-style role-reversed loop where the learning system exposes learning-state feedback and receives bounded, time-limited control intents. We implement the mechanism in an asynchronous federated reinforcement learning framework with heterogeneous simulated quadruped robots and reproducible uplink impairments via emulated network links. Results indicate that substantial communication reduction is achievable under dynamic constraints without materially degrading learning progress in the studied setting.

cs.NI

新论文 · v1arXiv:2611.13281

Constant query LCCs over the reals

Zeev Dvir

原文摘要

This note describes a new construction, found by ChatGPT Astra, of constant query Locally Correctable Codes (LCCs) over the real numbers. Prior constructions of constant query LCCs were exclusive to fields of positive characteristic and were conjectured not to exist over the reals. The construction uses low degree polynomial evaluations over an integer grid, together with a novel sampling procedure which outputs, for a given grid point $P$, a random quadratic curve through $P$ which intersects the grid in many other points (the decoding queries). The sampler is `smooth' in the sense that no grid point is queried with high probability. These codes have the additional property that the queried locations (the curve/grid intersections) are all nearby grid points.

cs.CC · math.CO

版本更新 · v3arXiv:2610.35658

A Hybrid Framework for Explainable Aviation Risk: Causal Chain Extraction from Safety Reports with Physics-Based Failure Quantification and Interventional Analysis

Yutian Pang, Yifang Tian, Xinyu Zhao, Jueming Hu, John-Paul Clarke, Hans-Arno Jacobsen

原文摘要

Aviation authorities hold decades of accident reports whose narratives record how investigators reconstructed each accident. Computational work on these archives has mostly sorted reports into fixed taxonomies. In this work, we propose a hybrid framework in which a text-based corpus identifies the leading factors of a failure mode. Physics-based models then quantify how likely that failure is at a stated operating point. Ordered causal chains extracted from 56,202 American accident reports with a local large language model aggregate into a causation knowledge graph. On an evaluation sample of 2,000 reports, the chains recover 90.8% of investigator-flagged causes. Each physical factor whose drivers the record carries receives an occurrence model calibrated to the accident population. A leaky noisy-OR fitted to the corpus combines the factors into a failure mode probability that supports intervention. For engine power loss, the carburetor icing model separates 1,205 icing accidents from other accidents using temperature and dewpoint alone, reaching 0.61 in area under the receiver operating characteristic curve against a density ratio ceiling of 0.64. Routine weather hours give no valid control, because flying concentrates in fair weather. On later years the physics adds 0.03 to that area for occurrence and nothing for severity, so its value lies in interpretability. On four named accidents, abduction gives a probability of necessity of 0.29 to 0.50 for the heat omission, under monotonicity. The Fast Causal Inference algorithm does not license the largest backdoor adjustment on the learned networks.

cs.LG · eess.SY · stat.AP

新论文 · v1arXiv:2611.13280

RetinexGS: Retinex-Inspired Gaussian Splatting for Low-Light RAW Reconstruction

Yulang Fei, Huaiyuan Weng, Chul Min Yeum

原文摘要

Standard 3D Gaussian Splatting (3DGS) pipelines struggle with severely underexposed images, producing unstable colors, floating artifacts, and incomplete reconstructions in dark regions. To better account for noise in these low-light observations, RAW images offer a natural basis for noise-aware reconstruction by preserving linear sensor measurements and providing access to noise metadata. We present RetinexGS, a RAW-domain 3DGS framework that combines Retinex-inspired appearance modeling with sensor-informed optimization for low-light novel-view synthesis. We factorize each Gaussian's color into a view-independent base color and a shared, position- and view-dependent modulation field, regularizing the two components separately to constrain appearance learning from noisy observations. We use DNG noise metadata to weight the reconstruction loss for signal-dependent noise, while distortion-aware rendering avoids spatially resampling RAW targets. To address sparse geometry in dark regions, we introduce depth-guided initialization. We evaluate RetinexGS on three public RawNeRF scenes and two custom-captured low-light RAW scenes. With all methods trained on the same RAW inputs for each scene, RetinexGS outperforms LE3D and RawNeRF in mean sRGB PSNR by 2.18 dB and 2.71 dB respectively, across the five scenes, while supporting real-time novel-view rendering.

cs.CV

新论文 · v1arXiv:2611.13276

An Analytical Model of Compute-limited Multistage Training Pipelines

Nishil Patel, Jin Hwa Lee, Basile Confavreux, Andrew Saxe

原文摘要

Modern foundation models are trained through multiple stages, yet how these stages interact and how compute should be allocated across them remain poorly understood. We introduce an analytically tractable high-dimensional model combining unsupervised pretraining with a linear autoencoder, supervised fine-tuning (SFT) with noisy stepwise labels, and reinforcement learning (RL) with sparse episodic rewards. Using random matrix theory and an operator-projection closure, we derive approximate low-dimensional learning dynamics that closely match simulations. We show that finite pretraining data imposes a representation-dependent performance limit, with Bayes classification error scaling as the inverse square root of the pretraining sample ratio, and observe the same exponent in asymptotic SFT and RL errors. Better pretraining also reduces sensitivity to noisy supervision. SFT initialization shortens the initial RL plateau induced by sparse rewards, an effect we also observe in OLMo-2 1B on GSM8K. Longer SFT warm starts additionally improve asymptotic RL performance. Optimizing compute across all three stages reveals that the optimal allocation depends on supervision quality and total budget, with a non-monotonic dependence of the RL compute share on budget. Finally, a complementary compositional model shows how RL selectively strengthens task-relevant pretrained skills while largely preserving unused skills. Together, these results identify mechanisms linking representation quality, feedback structure, and compute allocation in multistage training.

cs.LG

新论文 · v1arXiv:2611.13275

Off-policy Learning with Excursion Policies

Jiamin He, Mark Rowland, Zhaohan Daniel Guo, Hado van Hasselt, Diana Borsa

原文摘要

Off-policy reinforcement learning (RL) tries to learn the value of a target policy while data comes from a different behavior policy. This often requires trading off bias for variance or stability. One way to trade these off is to linearly interpolate between the behavior and target policies, but this represents only one point in a broader space of interpolation mechanisms. We introduce excursion policies--a structured alternative where the agent follows the target policy for a multi-step "excursion" before reverting to the behavior policy. We derive dynamic programming results for these policies, establishing the theoretical basis for their use in RL. We further develop provably sound off-policy temporal-difference (TD) algorithms for excursion value estimation. We find that excursion policies provide an efficiency-stability trade-off comparable to mixture policies in continuous control benchmarks, and our analysis illustrates conceptual differences in their behavior.

cs.LG · cs.AI

版本更新 · v3arXiv:2610.04542

Decide, Ask, or Defer: Clinical LLMs under Incomplete Evidence

Mingzhan Yang, Weili Wu

原文摘要

Clinical LLMs must decide not only what diagnosis to produce, but also whether the available evidence is sufficient for autonomous decision making. Binary DECIDE/ABSTAIN formulations merge distinct non decision states and do not explicitly evaluate information acquisition. We introduce a DECIDE/ASK/DEFER formulation together with a blinded protocol that prevents models from using evidence completeness metadata. We evaluate Qwen, Gemini, and GPT on 200 matched clinical evidence states constructed from DDXPlus. The models show substantial differences in action selection under identical evidence, with disagreement in 137 of 200 states. For Qwen, a matched targeted versus random analysis shows that selected information changes the likelihood of a subsequent autonomous decision more clearly than diagnostic correctness. Its matched DECIDE/ABSTAIN baseline further reveals a safety autonomy tradeoff: the three action policy rescues some erroneous autonomous decisions but also removes some correct autonomous deci sions. These results show that separating information acquisition from clinician deferral exposes behavior that binary abstention hides, without yielding a uniformly improved decision policy.

cs.AI

版本更新 · v4arXiv:2605.30608

Semantic Motion Anchors: Bridging Motion and Meaning in Co-Speech Gestures

Varsha Suresh, Mohammad Mahdi Abootorabi, Mohamed Salman, M. Hamza Mughal, Christian Theobalt, Ashwin Ram, Jürgen Steimle, Vera Demberg

原文摘要

Learning a shared representation between spoken text and gesture is central to co-speech gesture retrieval, synthesis, and understanding, but remains challenging for semantically meaningful gestures whose communicative intent is not captured by motion alone. Direct contrastive alignment between transcripts and continuous motion embeddings often overemphasizes low-level kinematics and misses the symbolic content of semantic gestures. We propose semantic motion anchors, natural-language abstractions of gesture motion capturing physical form and communicative intent. Our method discretizes 3D gestures into body-hand motion primitives, verbalizes them into structured descriptions, and grounds them in the transcript to provide auxiliary contrastive supervision. On BEAT2, our method improves text-to-gesture R@1 by 8.2% over a direct text-motion baseline and outperforms prior retrieval approaches on text to gesture and gesture to text retrieval directions. Beyond aggregate retrieval metrics, semantic motion anchor supervision helps retrieve gestures that are semantically meaningful for the spoken query, rather than defaulting to generic motion patterns. A downstream retrieval-augmented gesture generation study showed that users significantly preferred gestures retrieved by our approach over a retrieval-augmented generation baseline, demonstrating that semantically grounded retrieval translates to gestures that better convey communicative intent in downstream generation.

cs.CL

新论文 · v1arXiv:2611.13271

RaMOD: Moving-Object Detection from Raw mmWave Radar Cubes under Ego Motion

Yuan Fang, Long Zhuang, Lingzi Xing, Xijia Wei, Jingqi Jiang, Fangzhan Shi, Simon Julier, Kevin Chetty

原文摘要

Millimeter-wave (mmWave) radar provides weather-robust sensing and direct Doppler measurements, yet automotive perception pipelines often reduce its output to sparse point clouds or two-dimensional projections, leaving raw range-azimuth-Doppler (RAD) cubes underutilized. Ego motion induces Doppler responses from world-static structures, while Doppler wrapping aliases radial velocities, complicating moving-object detection and velocity estimation. We present RaMOD (Radar-based Moving-Object Detection), a real-time framework for moving-object detection and velocity estimation from raw RAD cubes acquired by a vehicle-mounted single-chip radar. RaMOD explicitly estimates frame-wise ego motion and uses the estimated radar translational velocity to predict the Doppler region of world-static structures and suppress returns within it. It temporally encodes the suppressed cubes into multi-scale features to predict RAD-space boxes with class labels. For each detected object, it predicts radial and forward velocities under raw-Doppler and Doppler-unwrapped hypotheses, together with Doppler-wrapping probabilities. On our BRIDGE-Liv dataset, RaMOD outperforms all compared raw-radar methods across RAD-cube, RA, and RD detection settings, achieving 80.8% cube mAP at IoU 0.30, 15.7 percentage points above the strongest RAD-cube baseline. Velocity MAE is 1.128 m/s, with 99.87% Doppler-wrapping accuracy.

cs.RO · cs.CV