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 20:25 — 2026-11-16 20:25(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)
版本更新 · v2arXiv:2605.24311

Terrain-Adaptive Grouser Wheel for Optimal Planetary Exploration: Design and Experimental Investigation

Vincent Griffo, Yashwanth Kumar Nakka

原文摘要

Planetary rovers operating in extraterrestrial environments often encounter significant mobility challenges due to varying terrain features such as gradients and granularity. While recent works in multimodal wheel design have explored adjustments in stiffness, compliance, and diameter as a means to improve terrain adaptability, full wheel grouser-adjustable designs remain largely unexplored. Grousers are a compelling feature to actuate, as granular terrains tend to require increased grouser height for improved wheel performance. As a result, we introduce GROVER, a multimodal wheel capable of continuously adjusting its grouser height for terrain adaptation. Fixed-height performance was characterized on vinyl, coarse rock, pea gravel, and sand under two packing states. Across 950 trials, the best configuration varied with terrain, reducing slip by 34.6\%--58.0\% in granular terrains and improving travel time and energy consumption by up to 77.4\%. No single grouser height minimized slip across all terrains, motivating mid-traversal reconfiguration toward lower-slip operation. Two experiments demonstrated this. First, an instructed terrain transition changed grouser height toward a known low-slip configuration during motion, with slip decreasing by $44.0\pm4.7\%$ from the transient peak across 20 trials. Second, an online adaptation routine used closed-loop slip feedback alone to search the grouser-height range for a lower-slip configuration on four terrains with previously uncharacterized granularities: three field terrains and one laboratory regolith terrain. The controller selected different heights, with settled slip 25.4\%--37.2\% lower than the pre-settled mean. Together, these results demonstrate GROVER's ability to improve mobility by varying wheel morphology during traversal toward lower-slip operating states.

cs.RO

版本更新 · v2arXiv:2603.26993

On the Reliability Limits of LLM-Based Multi-Agent Planning

Ruicheng Ao, Siyang Gao, David Simchi-Levi

原文摘要

LLM-based multi-agent planning delegates operational decisions to specialists that communicate through finite reports. In this research, we study its reliability limits when a coordinator can revisit source records before completing a resource-constrained plan. A useful report can support an immediate decision or direct later reading, so its value depends on how these stages communicate. We derive exact communication and access tradeoffs and prove that two report forms suffice for a broad class of allocation requirements, one favoring immediate resource identification and the other distinguishing absence from unnamed availability. For shared capacity, this reduction permits joint optimization of reporting roles and adaptive reads for a fixed number of source types with unequal workloads and reading costs. Identical specialists can optimally report different facts, and maximizing immediate completion can impose an unbounded recovery cost penalty even with full-record access. We also conduct numerical experiments to quantify the benefits of the proposed joint optimization and show how source access improves language-agent decisions that already use their reports optimally. In particular, an exhaustive evaluation of 207,632 report designs on small allocation instances recovers the predicted joint optima. Our analysis suggests that reliable agent communication should be evaluated by the complete decisions it supports and the cost of finishing its unresolved cases, instead of solely by report length, local prediction accuracy, or immediate task completion, as is often the case in current practice.

cs.MA · cs.LG · math.OC · stat.ML

版本更新 · v4arXiv:2605.08571

BEACON: Cross-Domain Co-Training of Generative Robot Policies via Best-Effort Adaptation

Antong Zhang, Han Qi, Heng Yang

原文摘要

We introduce BEACON--Best-Effort Adaptation for Cross-Domain Co-Training--a theory-guided framework for training generative robot policies with abundant source demonstrations and limited target demonstrations. BEACON casts cross-domain co-training as a discrepancy-aware importance-reweighting problem, jointly learning a diffusion-based visuomotor policy and per-sample source weights through an objective inspired by the Best-Effort Adaptation (BEA) bound. To make this approach practical for high-dimensional sequence policies, we develop scalable instance-level discrepancy proxies, stochastic alternating updates for policy and weights, and a multi-source extension that balances heterogeneous source domains. Across sim-to-sim, sim-to-real, and multi-source manipulation settings, BEACON improves robustness and data efficiency over target-only, fixed-ratio co-training, and feature-alignment baselines. Without an explicit alignment objective, BEACON also brings source and target representations closer together as an implicit result of discrepancy-aware co-training.

cs.RO

新论文 · v1arXiv:2611.01302

A Decomposition Theorem and a Simple Algorithm for Contraction Fixed Points

Xi Chen, Yuhao Li, Mihalis Yannakakis

原文摘要

We prove a decomposition theorem for the problem of computing an approximate fixed point of a contraction map $f\colon [0,1]^k \to [0,1]^k$ under the $\ell_{\infty}$-norm. After a preliminary version of the decomposition theorem appeared on arXiv [CLY26], Feodorov and Haslebacher [FH26] gave a striking application of the theorem, showing that it can be used to convert any $\operatorname{poly}(k,\log(1/\varepsilon))$-query algorithm with running time $(k\log(1/\varepsilon))^{O(k)}$ into an algorithm with running time $(k\log(1/\varepsilon))^{O(\sqrt{k})}$. They instantiated this framework with an $O(k^2\log(1/\varepsilon))$-query algorithm with the desired running time, thereby obtaining the first subexponential-time algorithm for contraction fixed points under the $\ell_{\infty}$-norm and, via well-known reductions, the first deterministic subexponential-time algorithm for simple stochastic games and mean-payoff games. In addition to the decomposition theorem, as our second main result in this paper, we show that the $O(k\log(1/\varepsilon))$-query algorithm of [CLY25] can be implemented in time $(k\log(1/\varepsilon))^{O(k)}$; our algorithm may be viewed as conceptually simpler compared to the algorithm of [FH26]. A key observation here is that the function constructed in [CLY25], whose fixed points are used as the next query points, turns out to be nonexpansive under the $\ell_{\infty}$-norm, so the brute-force procedure can be replaced by known algorithms for contraction fixed points.

cs.CC · cs.DS

版本更新 · v2arXiv:2511.00532

AQBuc: Air Pollution Forecasting in Bucharest

Dragoş-Andrei Şerban, Răzvan-Alexandru Smădu, Dumitru-Clementin Cercel

原文摘要

In recent years, air pollution, especially the particulate matter $2.5\,μ\text{m}$ (PM2.5), has become a growing concern mainly in urban areas. Exposure to air pollution is linked to the development of numerous health conditions, such as the aggravation of respiratory diseases, cardiovascular disorders, impaired lung function, and even cancer or early death. Forecasting future levels of PM2.5 has become increasingly important, as it can provide early warnings and help prevent diseases. We propose AQBuc, a dataset for predicting PM2.5 pollution in Bucharest, Romania, introducing an understudied location, as most work in this field has focused on Asian cities. Our dataset allows us to benchmark models for predicting future levels of PM2.5 across various time horizons. We evaluate a broad range of methods, including machine learning models, such as linear regression and ensemble-based methods, deep learning models based on recurrent networks and transformers, and large language models (LLMs). Specialized time-series models handle temporal data better, especially on longer horizons, while tree ensembles are more cost-effective for short horizons. Meanwhile, LLMs struggle to capture continuous sensor dynamics without specialized architectural changes.

cs.LG · cs.AI · cs.CY · stat.AP

版本更新 · v2arXiv:2505.23565

DRO: A Python Library for Distributionally Robust Optimization in Machine Learning

Tianyu Wang, Jiashuo Liu, Henry Lam, Hongseok Namkoong, Jose Blanchet

原文摘要

We introduce dro, an open-source Python library for distributionally robust optimization (DRO) for regression and classification problems. The library implements 15 DRO formulations and 9 backbone models, enabling 85 distinct DRO methods. Furthermore, dro is compatible with both scikit-learn and PyTorch through a unified interface, and uses approximation techniques to reduce runtime for some computationally demanding formulations. Comprehensive documentation is available at https://python-dro.org.

cs.LG · cs.MS · math.NA

新论文 · v1arXiv:2611.01300

Accelerating posterior sampling in Bayesian inverse problems with diffusion models: an online-offline perspective

Duc-Lam Duong

原文摘要

Bayesian inverse problems require both informative prior models and computationally feasible posterior inference. Score-based diffusion models provide expressive learned priors, but their use for inversion introduces a conditioning problem: the score of a noised posterior is generally unavailable from a prior score alone. This selective survey reviews the principal approaches to that problem, including likelihood guidance, spectral and projection methods, sequential Monte Carlo corrections, and amortized conditional training. We organize methods by how they split cost between offline preparation and online inference, and compare their assumptions, advantages and limitations, with emphasis on computational speedups. Some ongoing directions and open questions are gathered at the end.

cs.LG · math.NA · math.ST · stat.ML

新论文 · v1arXiv:2611.01299

Best-of-Both-Worlds FTRL for Linear Bandits: The Interplay of Information Acquisition, Corruption, and Geometry

Canzhe Zhao, Vincent Y. F. Tan

原文摘要

We study \textit{best-of-both-worlds} (BOBW) algorithms for linear bandits, which aim to simultaneously guarantee $\gO(\sqrt T)$ regret in the adversarial regime and $\gO(\log T)$ regret in the stochastic regime over $T$ rounds. For finite action sets, we introduce \emph{information-acquisition follow-the-regularized-leader} (\IAFTRL{}), the first BOBW algorithm based purely on the follow-the-regularized-leader (FTRL) framework that attains an $\gO(\cstar\log T)$-type regret in the stochastic regime, where $\cstar$ is the information-acquisition complexity that characterizes instance-dependent optimality in linear bandits, while retaining the $\gO(\sqrt{T})$ regret guarantee in the adversarial regime. This resolves the open problem posed in~\cite{LeeEtAl2021,KongZ023,ItoT23,ZhaoItoLi2025}.

cs.LG

新论文 · v1arXiv:2611.01297

Reading between the levels: new tools for the Thorup-Zwick hierarchy and their applications

Shiri Chechik, Gur Lifshitz, Avi Kadria, Liam Roditty

原文摘要

In this paper, we develop three new analytical tools for the Thorup-Zwick hierarchy: the Mixed-Level Growth, Two-Level Growth, and Long-Short Growth lemmas. Using these tools, we obtain improved approximate distance oracles (ADOs), and algorithms for $n$-pairs shortest paths ($n$-PSP), multiple-source shortest paths (MSSP), and $ST$-shortest paths, as well as new hopsets. One of our main results is a $(\frac 65 k+O(1))$-stretch ADO with $\tilde O(mn^{1/k})$ preprocessing time and space (where $\tilde O$ hides polylogarithmic factors), and $\tilde O(n^{1/k})$ query time, breaking, for sparse graphs, the $(2k-O(1))$-stretch barrier for ADOs with $\tilde O(n^{1+1/k})$ space and $\tilde O(n^{1/k})$ query time. In unweighted graphs, we also obtain a $(\frac 65 k+O(1),O(k))$-approximate ADO with $\tilde O(n^{1+1/k})$ space and $\tilde O(n^{1/k})$ query time. This also yields a $(\frac 65 k+O(1))$-approximation algorithm for $m$-pairs shortest paths ($m$-PSP) in $\tilde O(mn^{1/k})$ time, answering the question of Chechik, Hoch, and Lifshitz [SODA'25] of whether the $2k-O(1)$ barrier for $n$-PSP in $\tilde O(mn^{1/k})$ time can be broken. For unweighted graphs, we give a new analysis of the existing $\tilde O(mn^{1/k}+n^{1+2/k})$-time $n$-PSP algorithm of [Chechik et al., SODA'25], and show that, without any modification, it is a $(k,k-1)$-approximation, i.e., $d(u,v)\le\hat d(u,v)\le k\cdot d(u,v)+k-1$ for every queried pair. This improves its multiplicative factor from $\frac 43 k+O(1)$ to $k$, and the leading coefficient $k$ is tight for this algorithm. Moreover, for graphs with $m=Ω(n^{1+1/k})$, this answers the question of Dalirrooyfard et al. [FOCS'22] up to the additive $k-1$.

cs.DS

新论文 · v1arXiv:2611.01295

[Re] Pure Noise to the Rescue of Insufficient Data

Seungjae Ryan Lee, Seungmin Brian Lee

原文摘要

We examine the main claims of Zada, Benou, and Irani (2021), which states that in an image classification task with imbalanced training data, (i) using pure noise to augment minority-class images encourages generalization by improving minority-class accuracy. This method is paired with (ii) a new batch normalization layer that normalizes noise images using affine parameters learned from natural images, which improves the model's performance. Moreover, (iii) this improvement is robust to varying levels of data augmentation. Finally, the authors propose that (iv) adding pure noise images can improve classification even on balanced training data. We implemented the training pipeline from the description of the paper using PyTorch and integrated authors' code snippets for sampling pure noise images and batch normalizing noise and natural images separately. We reproduced the main claims that (i) oversampling with pure noise improves generalization by improving the minority-class accuracy, (ii) the proposed batch normalization (BN) method outperforms baselines, (iii) and this improvement is robust across data augmentations. Our results also support that (iv) adding pure noise images can improve classification on balanced training data. However, additional experiments suggest that the performance improvement from OPeN may be more orthogonal to the improvement caused by a bigger network or more complex data augmentation.

cs.CV · cs.LG

新论文 · v1arXiv:2611.01292

Causality-Based Fault Localization

Melane Navaratnarajah, Aidan Dakhama, Tom Yaacov, David A. Kelly, Karine Even-Mendoza, Hana Chockler

原文摘要

We introduce Causality-Based Fault Localization (CBFL), a novel approach to fault localization grounded in the theory of actual causality. We use the notion of causal responsibility to formalize and define the contribution of a given location in the source code under the context of a failing test. We also utilize a distance metric to prioritize minimal fixes and penalize broken tests, leading to more interpretable and fixable fault localization. We implemented CBFL in a tool, SoftReX, and our evaluation results demonstrate that SoftReX outperforms state-of-the-art Mutation-Based Fault Localization (MBFL) tools based on Mean Reciprocal Rank (MRR) and Top-1 by 16% on both metrics, when using the same set of mutants. We also propose a sophisticated mutation generation strategy based on the structure and representation of the program to improve the accuracy of our ranked list, which outperforms state-of-the-art methods by 2.6x in terms of required mutants evaluated while remaining competitive in performance.

cs.SE

新论文 · v1arXiv:2611.01287

Dynamic Click Destinations: Personalizing Post Ad-Click Landing Experiences

Apurva Pathak, Yuya Shiraki, Iman Jenabzadeh, Nikhil Bhale, Yuwen Tan, Shashank Rangarajan, Amirmehdi Sharifzad

原文摘要

Apps that monetize outbound (offsite) ad clicks have multiple post ad-click levers that influence user and business outcomes, including the landing page shown on the advertiser's site, whether the click resolves to a webpage or an app on the user's device, and whether it resolves to a native in-product surface or an external website. We refer to personalization over these levers as post ad-click destination automation. The optimal destination is heterogeneous across users, advertisers, placements, devices, and inferred intent, making static, one-size-fits-all destination policies suboptimal. We present Dynamic Click Destinations (DCD), a production personalization framework that selects a destination for each eligible offsite ad click to maximize Advertiser Value (AV), a value-weighted conversion outcome. DCD applies to any post-click destination decision where the system can choose among destination options at click time and downstream conversion feedback is available. We describe an evolution of learning objectives from post-conversion destination inference, to two-task destination-conditioned conversion prediction, to a single-task policy model that directly predicts which of two destinations is better for a given click, trained with Advantage Actor Critic (A2C)-inspired soft labels derived from a higher-capacity destination-conditioned "critic" model. In a web-vs-app case study, online A/B experiments at scale on a major advertising platform show that per-click personalization with DCD outperforms both static routing policies, with the single-task objective delivering the largest gains. These results highlight post ad-click destination as an important and under-explored lever in conversion optimization and demonstrate that personalized destination automation can outperform one-size-fits-all destination policies.

cs.IR

版本更新 · v2arXiv:2607.06699

RoboSnap: One-Shot Real-to-Sim Scene Generation for Generalizable Robot Learning and Evaluation

Shujie Zhang, Jingkun Yi, Weipeng Zhong, Zirui Zhou, Yangkun Zhu, Hanqing Wang, Xudong Xu, Weinan Zhang 等 9 位作者

原文摘要

Recovering real-world scenes as interactive simulation environments can enable generalizable robot learning and reproducible policy evaluation. However, constructing scenes that are both physically stable and visually faithful remains slow and expensive. In this work, we present RoboSnap, a real-to-sim framework that turns a single RGB image into a simulation-ready scene. The key idea is a layered design that separates the physics-critical interaction area from the surrounding visual context: collision-aware foreground assets are refined for stable robot interaction, while a 3D Gaussian splatting visual layer preserves faithful background appearance under novel views. Experiments on DROID scenes and real-robot tasks show that RoboSnap achieves reliable trajectory replay in the recovered scenes, supports task-specific synthetic data generation for policy training, and yields meaningful sim-real correlation for policy evaluation. To further support real-to-sim research, we introduce DROID-Sim, a real-to-sim companion dataset constructed from 564 real-world scenes in DROID. Extensive experiments suggest that the value of real-to-sim methods lies not only in high-fidelity visual reconstruction, but in turning real environments into reusable infrastructure for robot learning and evaluation.

cs.RO

新论文 · v1arXiv:2611.01284

Character-Name Concentration in LLM Fiction: Measuring Displacement and Mitigating Repetition

Alejandro Mozo Quesada, Sergio Gálvez Rojas, Francisco López Valverde

原文摘要

Character names in large language model (LLM) fiction concentrate on a handful of recurrent names such as 'Elara' and 'Elias', a measurable face of AI slop. Existing fixes either require logit access or retraining, or operate per request and cannot control concentration across a corpus. How much prompt-level strategies reduce concentration, and at what cost to name naturalness, has not been systematically measured. We present an empirical study of name-concentration control across eight strategies and introduce speculative naming, a fine-tuning-free method that adapts the draft-verify-reject paradigm of speculative decoding from tokens to names. The method requests candidate name-sets through verbalized sampling, scores them against a SlopTracker that combines a per-model fingerprint with a runtime counter, and selects through a temperature-controlled rule or its strict variant (HARD). We use 20 LLMs to generate 44,782 stories in four languages from text and visual stimuli (88,919 named characters), and measure concentration with a list-free collision metric (Slop Ratio, SR) decomposed into known and emergent components. List-based strategies do not remove slop: static banlists displace concentration to emergent names and more than halve the share of attested real names. Speculative naming removes it: the sampling scaffold alone cuts SR by 89% on average, the dynamic tracker brings the total reduction to 95%, mean collision probability falls from 7.3% to 0.4%, and known-name collisions hold at zero while naturalness stays close to baseline (42-69% attested by language) and within-story collisions drop from 4.3% to 0.2%. The strategy ranking is stable across languages, model families, and name-counting conventions. Name concentration is thus controllable at the corpus level without logit access or retraining; broader creative diversity beyond naming remains open.

cs.CL · cs.AI

新论文 · v1arXiv:2611.01283

DriftingPlanner: Drifting Generative Models for One-Step Trajectory Planning in End-to-End Autonomous Driving

Ziming Liu, Yizhan Qu, Leichen Wang, Hao Sun

原文摘要

End-to-end planners decode the ego trajectory either by coordinate regression, which is fast but blends plausible maneuvers into one trajectory that may follow none of them, or by diffusion and flow matching, which model the trajectory distribution but need several inference steps. Drifting models move this iteration into training: a one-step generator learns to follow an attraction--repulsion field between generated and ground-truth samples. Drifting was developed for class-conditional image generation, where every class supplies many positive samples. In planning, every scene is its own condition. Pooling scenes would attract the generated trajectories of one scene to the ground truth of unrelated scenes, whereas computing the field per scene leaves a single positive, the expert trajectory. Mutual repulsion then holds the generated trajectories on a shell around it, so any single generated trajectory deviates from the ground truth. We present DriftingPlanner, a trajectory planner trained with the drifting loss alone, without any coordinate regression term. It computes the field per scene and removes the shell at inference: it decodes every noise vector together with its negation in one batched pass, and averaging each antithetic pair cancels the linear part of the displacement from the shell center. On NAVSIM navtest, DriftingPlanner reaches a state-of-the-art 93.75 PDMS, and with single-step inference its drifting decoder comes within 0.13 PDMS of the best diffusion or flow matching setting, which needs ten inference steps.

cs.CV · cs.RO

新论文 · v1arXiv:2611.01281

Two-Dimensional Search for a Moving Target on Rectangular and Cylindrical Grids

Alexey Lebedev, Vladimir Lebedev, Christian Deppe

原文摘要

We study how precisely a moving target can be localized on finite rectangular grids and their cylindrical counterparts. Each query asks whether the target lies in a chosen subset of vertices and receives a noiseless answer. Queries may depend on previous answers. Between successive queries, the target may stay in place or move along one horizontal or vertical edge. Accuracy is measured by the number of positions still possible immediately after the final answer, with no subsequent movement. A strategy achieves accuracy $s$ if it always terminates with at most $s$ possible positions, whatever admissible trajectory the target follows. Thus $s=1$ means exact localization. We denote by $s^*(M,N)$ the smallest value of $s$ achievable by a finite adaptive strategy on a finite grid. Our main result shows that every finite rectangular grid admits a strategy that localizes the target to at most eight positions, regardless of the grid dimensions: $s^*(M,N)\leq8$. The construction uses nine local query patterns and their vertical reflections. Its termination follows from the progress these patterns force toward the finite grid boundaries. We also prove the dimension-dependent bound $s^*(M,N)\leq\min\{M+1,N+1\}$. For finite cylindrical grids $P_M\square C_N$, where the columns are periodic but the first and last rows remain boundaries, we introduce the corresponding accuracy parameter and state the proposed dimension-independent bound $s^*_{\mathrm{cyl}}(M,N)\leq9$.

cs.DM

新论文 · v1arXiv:2611.01280

Improving Ads Ranking Models with Auxiliary Supervision: Techniques and Insights

Nikhil Bhale, Apurva Pathak, SaiSujithKumarReddy MarapaReddy, Xiao Yin, Prateek Bhansali

原文摘要

Accurate prediction of post-click Conversion Rate (CVR) is essential for personalized ad delivery in the advertising industry. Traditional ads ranking models rely on conversion events (e.g., a user purchasing an item) as ground truth labels for training. However, these conversion events are often sparse or missing, which limits the effectiveness of model learning. The primary contributions of this paper are: (1) a case study on the use of auxiliary supervision from a diverse set of user events and metadata signals beyond traditional conversion events, and (2) advanced modeling techniques designed to maximize the value of these signals. We detail architectural innovations such as linearized labels for improved auxiliary signal precision, a split architecture to facilitate training task decomposition, and a novel Label Combination (LaCo) approach for robustly managing noisy auxiliary data. Empirical results demonstrate that these methods deliver measurable improvements in ranking models, underscoring their versatility and effectiveness across recommendation systems and related domains.

cs.IR

新论文 · v1arXiv:2611.01277

Programmable Droplets as Active Matter in a Reconfigurable Environment

Ivan Shmarov, Abhishek Sharma, Michael Jirasek, Kristine Laws, Leroy Cronin

原文摘要

Exploring systems that bridge the gap between non living and living matter requires a reconfigurable environment coupled to synthetic systems capable of autonomous motion, adaptive behaviour and persistent dynamics. Self propelled droplets provide a minimal platform for such life like behaviour, but quantitative measures capturing both persistence and adaptability to enable closed loop reconfiguration remain lacking. Here we introduce an autonomous closed loop robotic platform to characterise and dynamically program the autonomous behaviour of multicomponent oil in water droplets. We explored two chemical composition spaces, with and without external pH perturbations, analysing droplet behaviour in real time and iteratively selecting formulations. To quantify this behaviour, we introduce two descriptors, persistence and diversity. Persistence is quantified by mapping temporal dynamics in a speed shape complexity space, where we identify a persistence domain that distinguishes active from inactive droplets. Diversity captures spontaneous or environmentally induced variation in motion and the propensity of droplets to reorient or adapt under perturbation. We show that persistence and diversity are constrained by a behavioural trade off: high persistence limits diversity, whereas high diversity reduces persistent activity. Our results provide a quantitative framework for navigating and programming life like behaviours in active droplets and show how closed-loop experimentation can uncover organising principles in complex active matter.

cs.RO · cond-mat.mtrl-sci

新论文 · v1arXiv:2611.01276

OntoDoc: Automatically Generating Ontology Resource Descriptions

Juan Guajardo Gutierrez, Mike Tran, Nasim Shirvani Mahdavi, Chengkai Li

原文摘要

Knowledge graphs and ontologies form the backbone of structured, machine-readable knowledge representation, yet ontology terms often lack natural language descriptions, limiting their accessibility and reuse. Existing ontology verbalization approaches tend to rely on rule-based or template-driven techniques that operate on strict, formal schema axioms, resulting in rigid verbalizations that fail to convey richer contextual semantics. We present OntoDoc, a multi-agent framework for automatically generating natural language descriptions for any Internationalized Resource Identifier (IRI) within a SPARQL endpoint or RDF file. OntoDoc operates through a four-stage pipeline: (1) a Database Context agent that adaptively explores the knowledge graph via SPARQL to collect semantically informative triples about the target IRI; (2) a Web Context agent that retrieves and re-ranks encyclopedic background knowledge from Wikipedia and the open web; (3) an Assumption Generation agent that synthesizes both contexts into a structured, evidence-grounded list of intermediate assumptions; and (4) a Description Generation agent that produces the final natural language description from the grounded assumptions. We evaluate OntoDoc on three knowledge graphs spanning biomedical, agricultural, and cross-domain settings, using both automatic scoring via Large Language Models (LLMs) and human evaluation with 11 annotators. OntoDoc consistently matches or exceeds a naive LLM baseline and a template-based ontology verbalizer in accuracy. Furthermore, it vastly outperforms both baselines in the completeness of the generated descriptions, delivering an average 12% improvement in completeness over the naive baseline across all domains, and improving completeness scores by as much as 2.8 points on a 5-point scale relative to the ontology verbalizer.

cs.AI · cs.IR

版本更新 · v3arXiv:2605.09294

Understanding, Predicting, and Steering LLM Behavior via Representational Effective Theory

Muhammed Ustaomeroglu, Guannan Qu

原文摘要

Large language models (LLMs) assist with writing, teaching, programming and decision-making, yet the computations underlying their behaviour remain largely opaque. Full access to every weight and activation does not by itself yield understanding: a microscopic description need not reveal how computation is organized at the level that governs behaviour. Complex systems are often understood instead through a few macroscopic variables whose dynamics capture the behaviour of interest, as temperature and pressure do for molecular motion in thermodynamics. Here we show that such an effective description of LLM computation can be learned directly from data. We introduce Representational Effective Theory (RET), a framework that learns low-dimensional macrostates and their dynamics from a model's hidden-state trajectories. These macrostates exhibit approximately closed dynamics and trace interpretable trajectories through reasoning. They also predict sycophancy and alignment faking early in generation, while steering the model towards selected macrostates produces corresponding changes in its reasoning. Together, these results show that LLM computation admits useful macroscopic descriptions that support interpretation, prediction and control.

cs.LG · cs.AI

新论文 · v1arXiv:2611.01272

Geometry of Confabulation and Refusal in Small Language Models

Vladimir Kazei

原文摘要

Faced with an unanswerable question, small language models can either refuse or confabulate: confidently produce a wrong answer. Can the hidden state before the first generated token provide a clue? Can we flip confabulations into refusals? I introduce ConfabQA, a 784-item benchmark whose obscure-pre-cutoff category breaks the typical correctness/knowledge-cutoff confound and map the geometry of the hidden state with linear probes, a sparse autoencoder (SAE), and direct optimization of intervention directions. On Qwen3-1.7B and Gemma 2 2B the probe separates upcoming refusals from confabulations well beyond prompt features (+7.4/+16.3 pp); on Llama 3.2 3B the ConfabQA margin is within fold-to-fold spread, but a direct refusal probe on PopQA and TriviaQA recovers +18-25 pp. On Qwen I closely inspect three candidate directions for the refusal vector: probe-recovered, Qwen-Scope SAE feature, and directly optimized. Although the three directions are pairwise 50-81 degrees apart, a push at or below the state's own norm along any of them flips most confabulations into refusal openings dominated by the "As..." family. Forcing the opener without touching the hidden state yields the same one-in-three judged-refusal rate as any push. The opposite push collapses refusals mostly into confabulations, yet leaves originally correct answers intact, so the direction gates the opening speech act rather than the knowledge behind it. Confabulations do not resolve into a concentrated feature in a dictionary or a token signature on Qwen3-1.7B. Scoring every probe on the margin over the strongest of four prompt-feature baselines extracts the hidden state's own contribution. Correctness signal is model-dependent and portable only for Llama 3.2 3B: 81% of the probe's margin over test majority survives transfer between ConfabQA, PopQA, and TriviaQA. Benchmark, judge, and code are released.

cs.LG · cs.CL

版本更新 · v3arXiv:2603.08683

Benchmarking Language Modeling for Lossless Compression of Full-Fidelity Audio

Phillip Long, Zachary Novack, Chris Donahue

原文摘要

Autoregressive "language" models (LMs) trained on raw waveforms can be repurposed for lossless audio compression, but prior work is limited to 8-bit audio, leaving open whether such approaches work for practical settings (16/24-bit) and can compete with existing codecs. We benchmark LM-based compression on full-fidelity audio across diverse domains (music, speech, bioacoustics), sampling rates (16kHz-48kHz), and bit depths (8, 16, 24-bit). Standard sample-level tokenization becomes intractable at higher bit depths due to vocabulary size (65K for 16-bit; 16.7M for 24-bit). We propose Trilobyte, a byte-level tokenization schema for full resolution audio, improving vocabulary scaling from $O(2^{b})$ to $O(1)$ and enabling the first tractable 24-bit LM-based lossless compression. While LMs consistently outperform FLAC and yield state-of-the-art compression at 8-bit and 16-bit, we observe that compression gains become more modest as bit depth increases beyond 8-bit.

cs.SD · cs.AI · cs.LG · eess.AS

版本更新 · v2arXiv:2610.38691

Beyond fabrication: Misattributed numbers in papers written by AI research agents

Mosab Alfaqeeh, Omar Mohammed Horani, Mou'th Hourani, Hashem Alfaqeeh

原文摘要

Verifying numerical claims in research written by AI agents is an important but challenging problem. Recent benchmarks show that many agent-written papers fail integrity checks, but such verdicts, often produced by a single LLM judge, identify failure without explaining its nature, and existing checks either test a paper for internal consistency or test whether a reported value appears somewhere in an agent's output. We re-analyze all 540 released judgments from a recent public benchmark of AI research agents (nine agents, fifteen open research problems) and manually label 256 numerical claims from 18 submissions. Failures concentrate on alignment between the paper and the underlying work rather than overt cheating, and about four in five unsupported claims correspond to values in the agent's own files that come from the wrong experiment, metric, or run. We introduce a deterministic claim-to-evidence checker that scores whether the surrounding context identifies the claimed result and calibrates each claim against numerical decoys. With its rules fixed before labeling, it certifies claims with over 90% precision against blinded annotators (78 of 85; Cohen's kappa = 0.89), while verifying only a subset of claims; most claims it cannot verify are nevertheless traceable, so failure to verify is not evidence of falsehood. An LLM verifier given the same evidence recovers more traceable claims but accepts about three times as many misattributed ones, so the two are best used together. Applied to 99 submissions, the checker reveals large differences in traceability across agents, and on 30 submissions a second judge configuration, with a different model and harness, orders the agents' vendor groups as the official judge does while passing twice as many papers. These findings motivate provenance-first auditing of AI-produced research.

cs.AI · cs.CL · cs.DL

新论文 · v1arXiv:2611.01269

Learning momenta for Hamiltonian-based models

Ignacio Puiggros T., A. Srikantha Phani

原文摘要

There has been increasing interest in methodologies that incorporate physics priors into neural network architectures to enhance their modeling capabilities. Among these methodologies, Hamiltonian neural networks (HNNs) and their variants have gained considerable attention. These architectures explicitly encode Hamiltonian mechanics both in their structure and loss function, resulting in desirable properties and additional modeled information. A crucial limitation of HNNs is their reliance on data on the target system's generalized momenta. This severely hampers their applicability when the analytical form of the generalized momenta is unknown, which frequently is the case in real-world applications. The goal of the present work is to develop a general extension of Hamiltonian-based architectures that addresses this issue by simultaneously learning the system's generalized momenta, Hamiltonian structure, and dynamics from data. The proposed architecture learns the generalized momenta when their analytical form is unknown, and only (potentially non-sequential) data on the state and its derivatives is available. A dissipative mass-spring system, a double pendulum, and a rolling disk under nonholonomic constraints are considered as canonical examples to assess the performance of the proposed architecture.

cs.LG · eess.SY

新论文 · v1arXiv:2611.01268

EZ-Ar-VC: Robust Arabic Voice Anonymization with Generalization across Dialects and Code-Switching

Injy Hamed, Adarsh Arigala, Rufael Marew, Arjun Gangwar, Atharva Kulkarni, Hanan Aldarmaki, Srinivasan Umesh

原文摘要

Voice conversion (VC) models can be used to anonymize speech data while preserving naturalness. Existing models, however, are mainly optimized for English and other high-resource languages, and they fail to generalize well to Arabic due to its distinct phonology. In this work, we comprehensively evaluate existing zero-shot VC systems for Arabic speech, identifying limitations in pronunciation preservation. We then train an Arabic-centric model based on EZ-VC on diverse Arabic speech, and demonstrate strong performance in intelligibility, naturalness, and pronunciation preservation, while maintaining high speaker dissimilarity. Through subjective evaluation, we further demonstrate its robustness to code-switching and cross-dialectal conversion, as well as its generalization to Arabic dialects with limited representation in the training data. Our findings highlight the limitations of zero-shot VC and the importance of target-language adaptation for robust voice anonymization.

cs.CL

版本更新 · v3arXiv:2601.10083

Starfield: Demand-Aware Satellite Topology Design for Low-Earth Orbit Mega Constellations

Shayan Hamidi Dehshali, Tzu-Hsuan Liao, Shaileshh Bojja Venkatakrishnan

原文摘要

Low-Earth orbit (LEO) mega-constellations are emerging as high-capacity backbones for next-generation Internet. Deployment of laser terminals enables high-bandwidth, low-latency inter-satellite links (ISLs); however, their limited number, slow acquisition, and instability make forming a stable satellite topology difficult. Existing patterns like +Grid and Motif ignore regional traffic, ground station placement, and constellation geometry. Given sparse population distribution on Earth and the isolation of rural areas, traffic patterns are inherently non-uniform, providing an opportunity to orient inter-satellite links (ISLs) according to these traffic patterns. In this paper, we propose Starfield, a novel demand-aware satellite topology design heuristic algorithm supported by mathematical analysis. We first formulate a vector field on the constellation's shell according to traffic flows and define a corresponding Riemannian metric on the spherical manifold of the shell. The metric, combined with the spatial geometry, is used to assign a distance to each potential ISL, which we then aggregate over all demand flows to generate a score for each satellite's link selection. Inspired by +Grid, each satellite selects the link with the minimum Riemannian distance along with its corresponding angular links. To evaluate Starfield, we developed a custom, link-aware, and link-configurable packet-level simulator, comparing it against LAMP, +Grid, Motif, and Random topologies. For the Phase 1 Starlink, simulation results show up to a 30% reduction in hop count and a 15% improvement in stretch factor across multiple traffic distributions. Moreover, static Starfield, an inter-orbital link matching modification of Starfield, achieves a 15% improvement in stretch factor under realistic traffic patterns compared to +Grid. Experiments demonstrate Starfield's robustness under traffic demand perturbations.

cs.NI · cs.ET · math.DG

新论文 · v1arXiv:2611.01265

Toward Bounding Coding-Agent Autonomy in Software Maintenance: A Pilot Study of Boundary Contracts

Heeyong Eun, Seungyeon Chung, Hyejee Park, Youngeun Lee, Sukhyun Hong, Hyewon Jung

原文摘要

As coding agents gain greater autonomy to modify software repositories, relevant context alone does not define their operational authority. An artifact may be relevant to a maintenance task while being inappropriate to edit; conversely, another artifact may be required even when it is not explicitly mentioned in the request. We explore Boundary Contracts, a machine-readable abstraction that makes task-specific artifact roles (editable, inspect-only, required, and protected) explicit before repository modification begins. We conduct a pilot study on 40 maintenance tasks from a real enterprise repository, comparing the same Codex-based coding agent with and without Boundary Contract information. The boundary-informed condition improves macro edit-selection F1 from 0.440 to 0.682, required-behavior coverage from 0.429 to 0.673, and the number of strictly acceptable patches from 9 of 40 to 18 of 40. To probe whether these gains are explained only by improved file localization, we additionally analyze 21 tasks in which both conditions modify at least one identical file. Differences remain in edit selectivity and patch outcomes, providing initial evidence that explicit artifact roles may influence maintenance behavior beyond localization alone. This pilot does not establish the general effectiveness of Boundary Contracts. Rather, it provides initial evidence for a broader research question: how should the operational boundaries of coding agents be generated, validated, revised, and ultimately enforced as repository-level maintenance becomes increasingly autonomous?

cs.SE · cs.AI

新论文 · v1arXiv:2611.01263

StreamClarify: Proactive Clarification for Grounded Streaming Video Question Answering

Zhuchen Shao, Bo Chen, Klara Nahrstedt

原文摘要

Streaming video question answering (QA) requires real-time reasoning over continuous video streams under strict latency and active-context budgets. Current streaming vision-language models (VLMs) often give confident yet ungrounded answers when queries are ambiguous or have false premises, or when relevant visual evidence is no longer in the active context. Proactive clarification can help, but must satisfy the same latency and memory constraints. We present StreamClarify, a training-free framework for grounded streaming QA that combines a pre-answer uncertainty check with hierarchical memory. The check uses the entropy of a binary pre-answer judgment as a lightweight uncertainty score to decide whether to answer directly or request clarification. To support re-answering, a temporal-pyramid KV cache maintains a bounded active visual context, while a CPU-side semantic retrieval archive provides access to historical frames. We further construct StreamClarify-QA, a diagnostic benchmark of 1,837 QA pairs from StreamBench and OVO-Bench, spanning standard, referential ambiguity, and unanswerable scenarios. Across three VLM backbones, StreamClarify improves Macro accuracy by up to 8.2 points over backbone-matched baselines. At comparable trigger rates, entropy-based selection achieves more than 18 points higher precision than random selection in identifying initially incorrect answers. Under oracle user guidance, clarification improves Macro accuracy by up to 3.5 points. We also report a controlled, oracle-assisted Qwen3-VL simulation on Ambiguous QA with generated questions and referent-only user replies, where the entropy-gated condition improves accuracy by 8.3 points.

cs.CV

新论文 · v1arXiv:2611.01262

Does Random Search Discover Task Experts? Revisiting Neural Thickets

Julian Asilis, Guanzhe Hong, Vatsal Sharan

原文摘要

Pretrained models are typically viewed as generalists, requiring bespoke post-training to achieve task-specific expertise. Gan & Isola (2026) recently proposed a striking alternative: that pretrained models lie in a dense neural thicket of task specialists, which can be surfaced with simple Gaussian weight perturbations. We examine this neural thicket of task-specific experts and identify several key findings that question this perspective. First, we find that the apparent lift of the best-of-N selected perturbation decays quickly with selection-set size m, strongly suggesting overfitting to the selection questions. In fact, for 10 of the 12 model-task pairs we study, a simple null model of pure selection noise predicts more than 75 percent of the top expert's reward lift. Second, the top experts' advantage often vanishes on held-out questions or remains within the run-to-run variability of the unperturbed pretrained model. Third, we find that majority voting over the top-K selected perturbations, termed RandOpt(N, K) by Gan & Isola (2026), is often matched or outperformed by majority voting over K samples from the base model. Overall, our results suggest that random weight perturbations may be ineffective at uncovering task experts around pretrained models, and that task adaptation requires more sophistication than random search. Code and artifacts are available at github.com/asil012/RevisitingNeuralThickets.

cs.LG · cs.CL

新论文 · v1arXiv:2611.01261

MedAstra: ASR-less Speech Retrieval with Diagnostic Grounding for Medical QA

Elahe Khatibi, Ziyu Wang, Amir M. Rahmani

原文摘要

Spoken medical question answering can fail when automatic speech recognition (ASR) corrupts a clinically important term before retrieval. We present MedAstra, a framework that maps frozen WavLM speech representations through a lightweight adapter into a frozen E5 text embedding space. This enables a dense retrieval path that accepts a waveform without a query transcript. Retrieved passages and speech-linked textual metadata support answer generation with entity alternatives, diagnostic contrasts, relation heuristics, and bounded retrieval refinement. ASR-less refers to the initial speech retrieval interface; lexical retrieval, string-based entity correction, and the text generator require textual inputs. The deterministic speech embedding does not constitute a calibrated model of acoustic uncertainty. Reported retrieval results reach 87.6 Recall@10 for the speech-only retriever and 90.4 for the hybrid configuration, compared with 81.0 for transcript-first dense retrieval. Medical QA and ablations provide descriptive system comparisons, with input-provenance and evaluation limitations stated explicitly. We distinguish controlled synthetic acoustic tests from real clinical speech, qualify component attribution, and specify the remaining comparisons needed to assess speech-only QA and clinical generalization.

cs.CL