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 21:17 — 2026-11-16 21:17(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:2505.16409

Retrieval as Exploration: Retriever-Free Retrieval via Corpus-Traversing MCTS

Chaeeun Kim, Seungone Kim

原文摘要

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in multi-step reasoning and calling search tools at appropriate steps. However, existing retrieval-augmented reasoning approaches still rely on separate retrieval models, limiting LRMs to deciding when to retrieve and how to formulate queries rather than leveraging their pretrained knowledge and reasoning capabilities for retrieval itself. This structural separation introduces a representation bottleneck, as retrieval relies on separately learned representations that may obscure fine-grained distinctions needed for reasoning. Moreover, these approaches commonly employ fixed top-k retrieval, which can introduce superfluous documents and increase retrieval noise and context overhead. To address this, we reformulate retrieval from query-document relevance matching into the exploration of answer-containing paths within the corpus, and propose FREESON (Retriever-FREE Retrieval-Augmented ReaSONing), a framework that enables LRMs to directly navigate the original corpus text to locate information that satisfies their specific needs, serving as both the reasoner and the retriever. Specifically, we introduce CT-MCTS (Corpus-Traversing Monte Carlo Tree Search), a retrieval-specialized variant of Monte Carlo Tree Search (MCTS). CT-MCTS iteratively expands and evaluates exploration paths, starting from multiple promising entry points across the corpus. This allows LRMs to selectively reference specific segments identified during traversal, instead of fetching a fixed top-k set. Across nine benchmarks, FREESON improves average EM and F1 by 15 points over four retriever-based baselines on five general-domain QA tasks, matching the strongest baseline. It also gains 12 points on fact-checking and 13 points on medical QA under zero-shot transfer, performing on par with the much larger MedGemma-27B.

cs.AI

版本更新 · v2arXiv:2611.06487

Measuring the collaboration, not the agent

Xinxiao Li, Eisei Nakahara

原文摘要

Benchmarks for visualization agents score the agent alone; the human only supplies reference answers. For high-dimensional data this misses what matters: the knowledge of which variables count is held by on-site experts, not by the model, so the useful question is how well an analyst and an agent do together. We study one specific form of collaboration, the agent proposes a view, the analyst accepts, rejects, or modifies it, and those judgments are kept for later sessions, and propose five measures for it: complementarity, intervention efficiency, appropriate reliance, knowledge retention, and agency. The first four are computed from interaction logs alone. We test the measures, not people: in a testbed for parallel-coordinates design on public manufacturing data (UCI SECOM), with a simulated analyst whose behavior we control, all four are computable and respond to the controlled differences. Whether they reveal anything about real analysts is the next step; we release the testbed for it.

cs.HC

版本更新 · v2arXiv:2609.37022

Physics-Informed Multi-Agent Coordination for Hospital Patient Flow Optimization

Guoqing Zhang, Rafik Hadfi, Takayuki Ito

原文摘要

Efficient patient flow coordination across autonomous hospital departments is critical for mitigating overcrowding and balancing resource utilization. While classical queueing theory, specifically open Baskett--Chandy--Muntz--Palacios (BCMP) networks, provides an interpretable mathematical topology for healthcare operations, analytical models rely on stationary assumptions and fixed routing matrices that degrade under state-dependent real-world dynamics. Conversely, centralized reinforcement learning approaches struggle to accommodate the decentralized structure of hospital governance, where individual clinical departments function with localized observations, heterogeneous resources, and divergent operational objectives. In this paper, we present a Multi-Agent Systems (MAS) framework titled \emph{Physics-Informed Multi-Agent Coordination}, which embeds empirically calibrated BCMP queueing topologies as physical priors within a decentralized multi-agent reinforcement learning architecture. Formulated as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP) under coupled resource constraints, our method enables autonomous departmental agents to cooperatively negotiate patient routing and dynamic service scaling. To mitigate environmental non-stationarity without inducing excessive communication overhead, agents exchange localized action fingerprints along network edges and optimize a spatially decomposed reward structure. Empirical evaluations driven by real-world MIMIC-IV patient trajectories indicate that this cooperative multi-agent approach substantially reduces cumulative system delay compared to static Markovian approximations, heuristic dispatching, and independent multi-agent baselines, while maintaining clinical safety constraints.

cs.AI · cs.MA

新论文 · v1arXiv:2611.11966

On Non-Deterministic Representation of Boolean Functions

Sudharshan Rajagopalan, Nitin Saurabh

原文摘要

We study non-deterministic representation of Boolean functions by polynomials, introduced by (de Wolf, 2000). A polynomial $p(x)$ is said to be a non-deterministic polynomial for a Boolean function $f$ if for all $a\in\{0,1\}^n$, $p(a)\neq 0$ iff $f(a)=1$. The non-deterministic degree of $f$, denoted $\mathsf{ndeg}(f)$, is the minimal degree of a non-deterministic polynomial for $f$. In this work, we show the following main results: - Almost all Boolean functions on $n$ variables have non-deterministic degree at most $n/2 + O(\sqrt{n\log n})$. This confirms a conjecture of (Iyer et al., 2023). Together with the lower bound of (Iyer et al., 2023) it establishes a tight bound on the rational degree of a random Boolean function up to lower order terms. - We disprove a conjecture of (Kothari et al., 2026) about effective hypercube nullstellensatz for more than two polynomials. On the positive side, we also identify a constraint under which an effective hypercube nullstellensatz holds for many polynomials.

cs.CC

版本更新 · v2arXiv:2606.21954

Are Multilingual Models Actually Improving? Revisiting Cross-Lingual Transfer

Prasoon Bajpai, Eleftheria Briakou, Colin Cherry, Preethi Jyothi, Vihari Piratla

原文摘要

Cross-lingual transfer is a model's ability to generalize capabilities from well-represented source languages to under-represented target languages. Existing measures of a model's transfer strength conflate improvements in transfer with general improvements to accuracy in the source language. We advocate for an alternate metric that reliably captures transfer strength called Hardness Adjusted Transfer (HAT) Score, and use it to derive multiple insights on factors influencing transfer strength. Our analysis across twenty diverse language models and three popular mainstream multilingual benchmarks argues that 1) transfer in small models is not broken, 2) we are making slower than expected progress in cross-lingual transfer with model size, and 3) we have made clear progress over time.

cs.CL

新论文 · v1arXiv:2611.11965

ChainCheck: Near-Perfect Evidence-Sufficiency Scores Can Conceal Sensitivity to Construction Artifacts -- Paired Conditional Contrasts that Expose an Evaluation Confound

Hyojung Han, Ryangkyung Kang, Youngeun Kim, Seung-Hun Jeon

原文摘要

Evidence-sufficiency benchmarks ask whether a model can tell a complete passage set from one whose reasoning chain is broken. When broken sets are made by editing text, near-perfect sufficiency scores--and even positive crossed-control scores--need not demonstrate multi-hop reasoning. We present ChainCheck, an evaluation-validity audit that pairs validator-certified counterfactual cells with artifact-only baselines. In an exploratory crossed control on 2,214 HotpotQA pairs, a language-model scorer that never reads the chain reaches a nominal AUC of 0.997, and a one-string match reaches the maximum of the crossed chain-sensitivity statistic CS4 (0.500), while the 11 evaluated systems score from 0.308 to 0.484; the two statistics are different metrics. We therefore read positive CS4 as operational bridge-consistency sensitivity, not as semantic multi-hop reasoning. Every system is also sensitive to one extra edit, and the edits are detectable according to model-based naturalness ratings. On an independent HotpotQA set of 2,276 pairs, patterns pre-specified on MuSiQue and 2WikiMultiHopQA did not replicate: 5 of 6 trained readouts were edit-dominated, and the reference judge's selectivity interval [-0.007, +0.042] includes zero. Judge scores also depended on batch layout. The MuSiQue and 2Wiki records are public; the HotpotQA records and the fine-tuned checkpoints are not, so external reproduction is partial.

cs.AI

版本更新 · v2arXiv:2611.08477

EgoGeneralist: Unifying Egocentric Action-Video Tasks through Video-Native Modeling

Yanlin Jin, Bowen Yang, Cheng Zhang, Yifan Yang, Zhe Li, Jianfei Cai, Kai Zhu

原文摘要

Modern video models possess strong visual priors, yet do not natively represent human action in metric 3D space. We present EgoGeneralist, which adapts pretrained video generators to unify action-conditioned video generation, pose estimation, and joint action-video generation for egocentric manipulation. Our role-adaptive action renderer provides video-native representations for multidirectional action-video learning, making metric motion usable as both a spatial control signal and a recoverable generation target. Cross-stream action-video coupling establishes close correspondence between metric motion and visual dynamics through lightweight adaptation while preserving the pretrained visual prior. Together, these designs establish a generalist framework spanning six action-video tasks. With only narrow-domain data, EgoGeneralist generalizes to diverse unseen scenes and interactions with effective action control and visual quality, bridging pretrained visual knowledge and metric 3D human motion.

cs.CV

新论文 · v1arXiv:2611.11964

3R-Adapter: Retrieval, Rewiring, and Refinement for Efficient Adaptation of 3D Reconstruction Model

Zixiang Ai, Zhenyu Cui, Xu Zou, Jiahuan Zhou

原文摘要

Feed-forward 3D reconstruction models have demonstrated strong generalization under large-scale pre-training, yet they struggle in long-tail scenarios such as low-light reconstruction, joint human-scene reconstruction, and test-time adaptation. We observe relational attention structure collapse, manifested as the failure of cross-view correspondences, as a primary cause of these limitations. While adaptation offers a practical way to bridge this gap, existing parameter-efficient fine-tuning (PEFT) approaches mainly perform channel-wise feature adjustment and lack mechanisms to explicitly adapt relational structures, leaving correspondence failures unresolved. In this work, we formulate adaptation of 3D reconstruction models as a problem of correspondence recovery under domain shift and propose 3R-Adapter, a PEFT paradigm for long-tail 3D reconstruction scenarios. Our method consists of three components: Deformable Retrieval for task-adaptive relation candidate retrieval, Relational Rewiring for reconstructing cross-view relational structures, and Consistency Refinement for injecting the rewired relations into stable predictions. Extensive experiments on low-light reconstruction, joint human-scene reconstruction, and test-time adaptation demonstrate that our approach significantly improves robustness over existing PEFT methods while maintaining efficient lightweight adaptation. Our code is released at https://github.com/PKU-OV3-LAB/3R-Adapter.

cs.CV

新论文 · v1arXiv:2611.11962

Shaping Useful Noise: Energy Distributions Predict Visual Pretraining Quality

Ching Lam Choi, Antonio Torralba, Phillip Isola, Stefanie Jegelka

原文摘要

Synthetic data can scale visual pretraining, but current selection criteria only partially explain which datasets train strong representations. We propose using the energy profile of a dataset--the distribution of log-probability levels it occupies under a normalised real-image density model--as an audit and curation principle for synthetic data. To operationalise this view, we introduce Energy-Level Distribution Distance (ELD), which compares real and synthetic energy distributions. Real images span sparse high-likelihood scenes and dense low-likelihood textures, so useful synthetic data should cover this energy range rather than collapse to likely but low-variation samples. Across diverse synthetic datasets, ELD exposes mismatches missed by FID and predicts pretraining performance beyond FID, LPIPS variation, and feature-space recall, including across CNN and ViT self-supervised settings. We then use ELD to resample and mix synthetic sources, matching the real-image energy histogram while preserving diversity and improving downstream transfer.

cs.LG · cs.AI · cs.CV

版本更新 · v3arXiv:2609.22212

A Channel-Boosted Multi-Agent System with Iterative Consultation for Document Sensitivity Classification

Aleesha Zainab, Asifullah Khan, Muhammad Ahmed Khalid, Faheem Ullah Khan

原文摘要

Organizations in critical national infrastructure sectors must assess heterogeneous documents for sensitivity before routing or storage. Manual assessment is slow, inconsistent, and unscalable. Extending our prior leakage-controlled benchmark, BERT established the top single-encoder baseline (89.14% accuracy, 89.33% F1-score under 5-fold cross-validation on the Strategic 16K corpus). However, transformer baselines suffer from a structural limitation: fixed input length truncation discards evidence beyond the retained window-precisely where sensitive cables tend to be longest. We present Channel-Boosted MAS (CB-MAS) and instantiate it as IC-MAS (Iterative Consultation Multi-Agent System) to solve this without long-context computational costs. A Channel Critic Agent learns document-adaptive trust weights governing Gated Channel Boosting between two first-window encoders, while paired Consultation Agents iteratively exchange belief states to reconcile evidence from the beginning and end of long documents. IC-MAS holds computation constant regardless of document length by reconciling fixed windows in a compact representation space. Ablation studies show critic-controlled Channel Boosting provides the bulk of accuracy gains, while consultation recovers recall without precision collapse. Critic-Controlled Gated Channel Boosting with Max-Pool fusion and Blackboard Adaptive Consultation achieves 90.72% accuracy, 91.23% F1-score, 92.01% sensitive recall, and 90.46% sensitive precision, using about 54% less average computation than a fixed-round baseline. Gains over the single-encoder baseline are statistically significant (McNemar's test, p less than 0.000001; paired t-test). We include LIME/SHAP explainability, multi-agent evaluation, and an honest accounting of limitations.

cs.CL · cs.LG · cs.MA

新论文 · v1arXiv:2611.11960

Operation-aware Multimodal Clinical Decision Support System for ICU Discharge Risk Assessment

Guoqing Zhang, Rafik Hadfi, Takayuki Ito

原文摘要

Unplanned 30-day intensive care unit (ICU) readmission is a critical benchmark for evaluating healthcare quality. Most predictive models assume readmission risk depends solely on a patient's individual pathophysiological state, ignoring hospital operational context and resource capacity. In practice, discharge decisions are dynamic trade-offs between patient stability and bed turnover pressures. To address this gap, we develop an Operation-aware Multimodal Clinical Decision Support System (CDSS) for ICU discharge risk assessment. The system combines multi-agent collaborative extraction with self-evolving retrieval-augmented generation (RAG) to eliminate template noise from progress notes, while constructing departmental workload indicators alongside admission flow features, continuous vital signs, and sparse medical codes (ICD/DRG). Addressing severe class imbalance (about 10.5% readmissions) and alarm fatigue, we implement data normalization, class reweighting, and decision-threshold calibration. In 20 independent runs across 20,000 ICU stays from MIMIC-III, empirical findings demonstrate that: vital signs alone have limited predictive capacity under real-world class imbalance (PR-AUC of 0.1387 +/- 0.0086); directly concatenating raw text embeddings degrades decision tree performance (XGBoost and LightGBM PR-AUC drop to 0.3893 and 0.4030); whereas an end-to-end multimodal fine-tuning architecture (Transformer E2E FineTune) utilizing layer-wise parameter freezing and differential learning rates reverses text negative transfer, achieving the highest AUROC of 0.8288 +/- 0.0110, PR-AUC of 0.4373 +/- 0.0310, and F1-Score of 0.4757 +/- 0.0196. Operational indicators supply independent risk signals, laying an engineering foundation for high-utility clinical decision support tools.

cs.LG

新论文 · v1arXiv:2611.13020

ChipOmni: A General-Purpose AI Agent for Electronic Design Automation

Pengkun Wang, Rui Mao, Zhe Zhao, Dongting Xie, Haibin Wen, Song Xu, Di Wu, Xu Wang 等 12 位作者

原文摘要

Electronic design automation (EDA) workflows remain highly fragmented, requiring engineers to coordinate heterogeneous representations, specialised software tools, and iterative verification across multiple design stages. Although large language models have brought more general reasoning and code-generation capabilities to EDA, many existing approaches remain focused on isolated tasks and struggle to plan, verify, and repair designs autonomously within executable engineering environments. Here we introduce ChipOmni, a knowledge-enhanced, context-evolving AI agent framework for EDA. ChipOmni integrates multimodal understanding, dynamic planning, multi-agent collaboration, and verification-driven tool interaction into a unified autonomous system. By continually incorporating feedback from external engineering tools, the framework maintains an evolving task context, integrates domain knowledge, and iteratively refines intermediate designs. Across benchmarks for analog circuit, RTL, testbench, and formal-assertion generation, ChipOmni improves multiple task-specific measures over the evaluated baselines and solves all 30 AnalogCoder-Pro tasks. In a long-horizon case study, ChipOmni advances a natural-language RISC-V specification through three design levels to a micro-SoC GDSII layout that passes physical sign-off, without human intervention after initialization. Together, these results show that ChipOmni can coordinate verification-driven design across heterogeneous tasks and sustain long-horizon engineering workflows, advancing a shift from fragmented, tool-centred processes towards agent-centred, closed-loop systems.

cs.AI

版本更新 · v2arXiv:2606.20135

Frequency-Aware Flow Matching for Continuous and Consistent Robotic Action Generation

Jianing Guo, Fangzheng Chen, Zihao Mao, Wong Lik Hang Kenny, Zhenhong Wu, Yu Li, Yishuai Cai, Yuanpei Chen 等 15 位作者

原文摘要

Flow matching has emerged as a standard paradigm for robotic manipulation owing to its strong expressive power for modelling complex, multimodal action distributions, alongside similar approaches like diffusion policy. However, existing methods rely on discretized action chunks, making them brittle to demonstrations collected at heterogeneous control frequencies and prone to temporally inconsistent actions that degrade control stability. In this paper, we propose Frequency-Aware Flow Matching (FAFM), which outputs continuous, temporally consistent actions. To handle heterogeneous frequency input, we transform discrete action sequences into the frequency domain with the discrete cosine transform (DCT), perform flow matching over the resulting coefficients, and reconstruct continuous actions via cosine basis expansion. To generate temporally consistent actions, we regularize the first-order temporal derivative to promote smooth actions. This corresponds to a Sobolev-type constraint that suppresses high-frequency errors and discourages abrupt action changes. Our FAFM is simple, introduces no additional network parameters and applies to standalone flow-matching policies and vision-language action models. Across synthetic toy benchmark, obstacle avoidance, LapGym, and LIBERO, FAFM improves success rates, multimodal expressivity, motion smoothness, convergence speed, robustness to mechanical bias and mixed-frequency input. These gains are consistent when deployed on a real-world Franka robot. Code available at https://github.com/gakakulicc/FAFM.

cs.RO · cs.AI

版本更新 · v3arXiv:2605.18309

Alignment Dynamics in LLM Fine-Tuning

Yuhan Huang, Huanran Chen, Yinpeng Dong

原文摘要

Although Large Language Models (LLMs) achieve strong alignment through supervised fine-tuning and reinforcement learning from human feedback, the alignment is often fragile under subsequent fine-tuning. Existing explanations either attribute alignment fragility to gradient geometry or characterize it as a distributional shift in model outputs, yet few provide a unified account that bridges parameter-space learning dynamics with function-space alignment behavior during fine-tuning. In this work, we introduce a tractable alignment score and derive its closed-form update during fine-tuning, yielding a unified framework for alignment dynamics. Our analysis decomposes alignment updates into two competing components: a Rebound Force, governed jointly by the current alignment state and the narrowness of model distribution, and a Driving Force, determined by how the training distribution aligns with outcome-conditioned posteriors over aligned and non-aligned completions. This decomposition explains why prior alignment can be reversed by later fine-tuning and why narrower posterior structure strengthens such reversal. Moreover, our framework predicts a Rehearsal Priming Effect: prior alignment leaves a latent posterior imprint that amplifies the effective Driving Force upon re-exposure, leading to faster re-alignment. We validate these predictions across safety alignment, emergent misalignment, and sentiment settings, demonstrating consistent alignment reversal and accelerated re-alignment under re-exposure. In addition, controlled experiments in safety alignment confirm the predicted dependence of rebound strength on posterior narrowness. Together, these results provide a unified dynamical perspective on how alignment is disrupted and reactivated during LLM fine-tuning.

cs.LG · cs.AI

新论文 · v1arXiv:2611.13019

Two-Tier Task Offloading for Satellite-Assisted Marine Networks: A Hybrid Stackelberg-Bargaining Game Approach

Zhen Wang, Bin Lin, Qiang, Ye, Haixia Peng

原文摘要

The proliferation of maritime activities has spurred the emergence of numerous computation-intensive and delay-sensitive marine applications and services. Given the inherent rationality, selfish nature, and limited computational abilities of marine devices, devising effective strategies to incentivize their participation in task processing become a critical challenge. In this paper, we investigate the satellite-assisted marine multi-access edge computing (MEC) and propose a two-tier task offloading scheme through a hybrid Stackelberg-Bargaining game approach to enhance offloading efficiency and maximize the utility of marine devices. Specifically, for the underwater acoustic communication, we consider the scenario where multiple autonomous underwater vehicles (AUVs), managed by maritime autonomous surface ships (MASSs), upload their collected data using non-orthogonal multiple access(NOMA) to optimize channel utilization. For the data transmission above the sea surface, we consider the scenario where a low earth orbit satellite (LEOS) functions as a space edge server to provide computing services, and MASS offloads workloads to LEOS through frequency division multiple access(FDMA) to prevent co-channel interference. we define the utility of AUVs, MASSs and LEOSs, and model the offloading process between AUVs and MASSs as a Stackelberg game, while representing the offloading interaction between MASSs and LEOSs as a Bargaining game. Additionally, we propose efficient algorithms to optimize AUV offloading strategies and MASS pricing strategies, while refining the bidding strategies for both MASSs and LEOSs. Simulation results demonstrate that the proposed algorithms significantly outperform benchmark schemes in achieving optimal solutions.

cs.DC

版本更新 · v3arXiv:2603.14527

DNA-MGC+: A versatile codec for reliable and resource-efficient data storage on synthetic DNA

Ramy Khabbaz, Jérémy Mateos, Marc Antonini, Serge Kas Hanna

原文摘要

The biochemical processes underlying DNA data storage, including synthesis, amplification, and sequencing, are inherently noisy, leading to insertion, deletion, and substitution errors as well as sequence dropouts that challenge reliable data retrieval. Here we introduce DNA-MGC+, a DNA storage codec designed for reliable and resource-efficient retrieval under diverse operating conditions. We evaluate DNA-MGC+ across various in silico and in vitro settings. In comparison with selected representative codecs, the results show that DNA-MGC+ consistently improves key performance metrics under explicit reliability constraints, including required sequencing depth, read cost, decoding time, storage density, and error-correction capability. In silico experiments show that DNA-MGC+ supports reliable decoding at error rates up to 24% for a 15-KB file, while separate scalability experiments demonstrate reliable decoding of files up to 200 MB at a 5% error rate. In vitro experiments involving a 24-KB file and electrochemical synthesis show that different DNA-MGC+ configurations achieve minimum sequencing depths below 3x and read costs below 3.5 nts/bit under both Illumina and Nanopore sequencing.

cs.IT · cs.ET

版本更新 · v2arXiv:2611.08136

How Far Can Untrained Neural Networks Go in Anomaly Detection? From Tables to Pixels

Hyojun Yi, Geunyoung Kim, Hogeon Seo, Seunghyoung Ryu

原文摘要

Anomaly detection (AD) is often framed as a representation-learning problem, where strong performance is expected to require learned features or AD-specific optimization. However, this view can overlook the intrinsic separability of anomalies from normal references, even in the absence of learned representations. We therefore investigate how far untrained neural networks can go in anomaly detection. To this end, we propose PRISM, a framework combining fixed random nonlinear features with normal-reference Mahalanobis scoring for tabular detection and dense visual localization. Across 47 tabular datasets in ADBench, PRISM-T achieves the highest mean AUROC (86.4%) and the second-highest mean AUPRC (65.9%) among the compared methods. On MVTec AD and VisA, covering 27 visual categories, PRISM-V achieves mean image-level and pixel-level AUROCs of 90.4% and 96.4%, respectively. Notably, both models achieve these results without neural weight optimization or pretrained representations. A theoretical analysis further characterizes how nonlinear transformations affect the mean and covariance contributions to the Mahalanobis score gap, while empirical analyses examine the resulting score separability. These findings establish PRISM as both a competitive anomaly detector and a prior-to-learning baseline for assessing the added value of learned representations in anomaly detection.

cs.LG · cs.CV

新论文 · v1arXiv:2611.11955

CHO-Bench: How Do Context Hints Affect Ad Rankings in LLM Advertising?

Shiqi Zhang, Yang Fei, Xiaokui Xiao

原文摘要

LLM advertising selects advertisements based on user conversations, where user needs may extend beyond explicit product searches. ChatGPT Ads allows advertisers to provide natural-language context hints describing what they offer, who may find it useful, and when it may be useful, as additional information for ranking advertisements across diverse user conversations. However, how to effectively construct these hints remains unclear. We formulate Context Hint Optimization (CHO) as the problem of constructing context hints to improve an advertisement's ranking under a given budget. Drawing on established marketing frameworks, we develop seven context hint generation strategies covering What, Who, and When, along with a Unified strategy that combines all seven dimensions. We introduce CHO-Bench and conduct over 1.19 million paired evaluations across five datasets using embedding-based and LLM-based rankers. Our results show that context hints improve advertisement rankings under the evaluated offline rankers. While individual strategies achieve similar average gains and Unified offers no consistent advantage, strategy differences become more pronounced under specific generation-ranking configurations, with embedding-based and LLM-based rankers favoring different information dimensions. Increasing the hint budget further improves rankings with diminishing marginal gains. These findings establish an offline benchmark for studying ad-side ranking optimization in LLM advertising and highlight opportunities for model-specific hint selection and budget-aware generation and aggregation.

cs.IR · cs.CL

版本更新 · v3arXiv:2606.16138

Closing the Approximation Gap in Simulation-free Latent SDEs

Henry D. Smith, Brian L. Trippe, Scott W. Linderman

原文摘要

Recovering dynamical systems from noisy observations is a recurring challenge across scientific domains, including neuroscience and physics. Latent stochastic differential equations (SDEs) address this by modeling the system as an unobserved state that evolves according to a learnable SDE and generates the observations. Variational inference (VI) provides a tractable objective for fitting latent SDEs. Traditional VI algorithms evaluate this objective by numerical simulation over a time discretization, trading fidelity for computational cost. A recent class of algorithms, simulation-free VI, sidesteps this tradeoff by parameterizing the posterior through its instantaneous marginals rather than its drift. In this work, we show that the efficiency of existing simulation-free VI algorithms comes at a price: their parameterizations restrict the approximate posterior to a subset of the SDEs available to simulation-based methods, degrading posterior inference and parameter learning. We propose Helmholtz-SDE, a simulation-free VI algorithm that closes this gap by optimizing over path laws compatible with a prescribed collection of marginals. Helmholtz-SDE recovers dynamics more faithfully than prior simulation-free methods, with the largest gains under high posterior uncertainty. It further matches the performance of simulation-based VI at a fraction of the runtime. Code is available at https://github.com/lindermanlab/helmholtz-sde .

stat.ML · cs.LG

新论文 · v1arXiv:2611.11952

BharatSynthQA: A Context-Grounded Question Answering Dataset on Indian Temples and Religious Heritage

Riya Naik, Shivam Sharma, Swati Agarwal

原文摘要

India's temples and other places of worship are among its richest repositories of cultural heritage, bringing together religious tradition, history, architecture, and art. Due to the widespread curiosity, people increasingly turn to Artificial Intelligence (AI) assistants for information about them. Current models are rarely trained or evaluated on this domain. We present BharatSynthQA, a passage grounded question answering (QA) dataset focused on Indian temples, which also covers other religious sites connected to them. Our pipeline crawls Wikipedia from topics seeded by authentic heritage sources, filters articles for topical relevance, and locations in India. Further it generates Boolean, factoid, and explanatory QA pairs with a fewshot prompted LLM. An LLM judge filters the pairs on answer correctness, retaining 98,677 of 131,494 generated pairs. Additionally, 300 human-annotated pairs are released separately as a reference set. Human evaluation of the subsample of this dataset showed 89.83% of the questions were formed correctly. Benchmarking five current LLMs shows that factoid token F1 is only 0.18-0.30 without the source passage but 0.73-0.77 with it, indicating that this domain is poorly captured in model knowledge. The dataset is available at https://huggingface.co/datasets/theshivam7/bharatsynth-qa to support research on culturally grounded QA and retrieval-augmented generation for Indian heritage.

cs.CL · cs.AI

新论文 · v1arXiv:2611.11951

UltraVoxelGS: Voxel-First Feed-Forward Gaussian Splatting for 3D Ultrasound Reconstruction

Yue Wang, Haoxin Chen, Xiaoqing Guo

原文摘要

We present UltraVoxelGS, a 3D ultrasound reconstruction method that achieves both fast reconstruction and physically faithful rendering for the first time, bringing live spatial feedback during 2D ultrasound scanning within reach. This is made possible by a feed-forward design that predicts a complete Gaussian scene representation from posed ultrasound images directly, entirely bypassing the per-scene optimization bottleneck that has confined prior methods to offline use. Realising such feed-forward prediction in this setting is non-trivial: unlike natural images, ultrasound slices share at most one-dimensional intersections and exhibit view-dependent appearance due to acoustic propagation and attenuation, violating the dense overlap and photometric consistency assumed by existing feed-forward Gaussian methods. Hence, to achieve fast reconstruction, we introduce a feed-forward voxel-to-Gaussian pass that decouples representation size from input count by lifting all posed slices into a fixed-size voxel support and predicting Gaussian parameters directly. For faithful rendering, we propose ultrasound-aware appearance rendering strategy factorize reflection from cumulative attenuation during training and exploit appearance continuity among spatially adjacent slices for efficient Render-time Appearance Adaptation. On both real-world and simulated datasets, UltraVoxelGS achieves best PSNR/SSIM compared with per-scene optimization baselines while reducing inference from 10-20 minutes to approximately 10 seconds (over 35 times faster) and scales to sequences exceeding 1,000 frames. Code is available at https://github.com/YuebyYue/UltraVoxelGS-camera-ready.

cs.CV · eess.SP

新论文 · v1arXiv:2611.11949

Watching Itself Watch: Self-Auditing Visual Reliance for Video Reasoning

Rohan Dugad, Mi Luo, Kristen Grauman

原文摘要

Video reasoning hinges on a small number of visually decisive tokens embedded in otherwise largely language-driven chains of thought. Yet prevailing post-training methods such as GRPO overlook this structure, assigning coarse trajectory-level rewards while requiring multiple rollouts and often costly external judges. We introduce Visually-Aware On-Policy Self-Distillation (VIOS), a post-training framework that identifies where a model under-utilizes visual evidence and concentrates learning at those positions. Our key insight is that a model can audit its own visual reliance: the divergence between its next-token distributions with and without the video reveals how strongly each prediction depends on the visual input. Measuring this reliance for both a student and an answer-privileged teacher exposes a per-token reliance gap, identifying positions where the teacher exploits visual evidence that the student overlooks. VIOS translates this signal into dense, targeted supervision through three complementary components: an exponential moving average (EMA) teacher that co-evolves with the student, a contrastive objective that encourages predictions to depend on the video, and a reliance-gap gate that focuses learning on visually under-utilized tokens. Crucially, VIOS requires only a single on-policy rollout from a single model, without external rewards, judges, or larger teachers. Across 12 benchmarks spanning general, temporal, spatial, knowledge-intensive, and long-video understanding, VIOS consistently improves three model backbones and outperforms contemporary video-reasoning systems, while training in over 9x fewer steps, 60x fewer FLOPs, and 111x fewer generated tokens. Project page: https://vision.cs.utexas.edu/projects/VIOS/

cs.CV · cs.LG

新论文 · v1arXiv:2611.11947

The Relative Value of Demonstration Data: Execution Time Limits and Operator Mixtures in Behavior Cloning

Jiaxuan Guo, Xingyu Ren, Youran Sun, Jingxin Yang, Kejia Zhang, Haizhao Yang

原文摘要

Robot demonstration datasets combine demonstrations from teleoperators of uneven experience, so collection teams need to know how many demonstrations from one group match those from another. We measure this with a data multiple: the ratio of the numbers of demonstrations two groups need for their policies to reach the same success rate. On robomimic's simulated Square and Can tasks, we train behavior-cloning policies on demonstrations from the two teleoperators robomimic labels Better and the two it labels Worse, varying dataset size and the share of Worse demonstrations. On Square, within robomimic's 25-second time limit, an all-Worse training set needs 1.55 times as many demonstrations as an all-Better set. Most of this difference is late completion: policies trained on Worse demonstrations finish later, as the Worse teleoperators do, and with a 100-second limit the multiple falls to 1.11. On Can, most of the difference remains at 100 seconds. If each Worse demonstration were worth 1/1.55 of a Better one, as in an all-Worse set, a half-Better, half-Worse set on Square would need 1.22 times as many demonstrations as an all-Better set. In fact, it needs 13% more than that, and this excess persists at every time limit from 20 to 200 seconds. The excess remains when training draws demonstrations uniformly instead of in proportion to their length. On Square, within the 25-second limit, switching to these Worse teleoperators is cheaper at equal success only if they earn less than a third of the Better teleoperators' hourly pay, because Worse demonstrations also take longer to record.

cs.RO · cs.LG

新论文 · v1arXiv:2611.11946

Decision Aware Origin-Destination Demand Estimation with Structurally Constrained Data

Xianzhe Wang, Yueyue Fan, Johannes Royset

原文摘要

Origin-destination (OD) demand plays an important role in transportation system design and management applications. Conventional OD estimation methods typically judge estimation quality based on how estimated demand aligns with observed traffic data and historical demand patterns. We argue that data alignment alone is insufficient; how errors in OD estimates influence downstream decision quality should also be considered. This paper develops a decision aware OD demand estimation framework that leverages structurally constrained traffic data to characterize an admissible demand region, within which we identify OD estimates that would lead to least regret in the downstream decision. Therefore, our OD estimates are both data-consistent and decision-relevant. Methodologically, we approximate the admissible demand region induced by physical network constraints through a geometric representation, which regularizes the search over feasible OD estimates. Within this regularized region, we use a convex surrogate of downstream regret to obtain a tractable decision aware optimization problem. Numerical experiments show that the proposed framework consistently reduces decision regret relative to conventional estimation benchmarks, demonstrating the value of aligning OD demand estimation with downstream decision quality.

cs.LG

新论文 · v1arXiv:2611.11941

Flip Anything with Agentic Robotics Self-Learning

Shuangyu Xie, Kaiyuan Chen, Ken Goldberg

原文摘要

Flipping is a fundamental robotic manipulation skill that requires reorienting a target object in a stable pose on a planar support surface by rotating it 180$^\circ$ about an axis parallel to the support surface -- think of flipping a coin from heads to tails. Although flipping is a common objective in industrial tasks such as parts inspection, mechanical assembly, and tool use, coding a bimanual robot with grippers to flip diverse objects is a significant challenge. In this paper, we show that a coding agent can autonomously develop and refine object-flipping strategies through iterative learning in physics simulations across diverse object geometries. Progressive skill acquisition, from basic handover to toppling and pushing, robust grasping and sensing, and thin-object manipulation with recovery, improves task success from 24.7% to 95.0%. The resulting graph-based code integrates high-level strategy selection with reactive control, enabling multi-stage flipping on physical robots.

cs.RO

版本更新 · v2arXiv:2611.00580

Scaling Science: Toward a Chain Reaction of Discovery

Yuheng Ding

原文摘要

Scientific discovery advances when evidence from different investigations is brought into contact. Yet paper-centric communication leaves experimental results fragmented, delayed, or unreported, creating a "scientific memory wall" between growing computational capabilities and the evidence accessible to AI systems. Breaking this wall requires a paradigm shift in AI for Science: moving from passively mining questions out of existing datasets to actively generating and recombining experimental data around unresolved scientific questions. In a network of intelligent laboratories, a failed or overlooked experiment in one domain could trigger a hypothesis in another, whose testing generates fresh evidence that stimulates further investigations. To enable these evidence-driven chain reactions, we propose Evolving Scientific Intelligence (ESI), an architectural blueprint that connects shared scientific memory with distributed experimental loops. ESI preserves experimental records -- including negative and anomalous results -- in computable representations, allowing models to recombine evidence across domains into testable hypotheses. Rather than following fixed screening pipelines, the system jointly selects candidates and evaluation methods according to scientific value, reliability, and cost, directing distributed laboratories to produce the exact evidence needed next. Their physical feedback revises both hypotheses and evaluators, while slower meta-control reassesses research objectives and decision criteria to guard against self-reinforcing errors and misguided optimization. We call for an Information Manhattan Project to build this infrastructure for scaling science through experimentally grounded chains of discovery.

cs.AI · cs.LG

新论文 · v1arXiv:2611.11940

Reliability-Adaptive Multimodal Relative Pose Tracking for Underwater Leader-Follower Robots

Mingyang Yang, Zeyu Sha, Xiaorui Wang, Jun Wang, David Chen Wang, Feitian Zhang

原文摘要

Underwater leader-follower formation control requires continuous relative-pose estimation despite degraded sensing conditions and limited onboard computation. This paper presents a reliability-adaptive multimodal perception framework for six-degree-of-freedom relative-pose tracking between two moving underwater robots. The framework integrates complementary visual, acoustic-ranging, and hydrodynamic measurements while accounting for their distinct physical characteristics and time-varying reliability. It adaptively weights modality contributions and models temporal dependencies with linear computational complexity, enabling efficient pose estimation on embedded hardware. Extensive experiments were conducted using a custom-built AUV platform, with 648 pool trials spanning two leader vehicle types, three illumination conditions, and nine trajectory patterns. Evaluation yields an average translational error of 3.8 cm and an average orientation error of 2.4°. On an onboard NVIDIA Jetson AGX Orin, the fusion network achieves an inference latency of 17.62 ms, providing a 2.69-fold speedup over the evaluated Transformer-based fusion baseline. Closed-loop experiments further demonstrate stable formation maintenance with a moving leader under onboard computational constraints. A multimodal dataset containing measurements from all 648 trials will be made publicly available.

cs.RO

新论文 · v1arXiv:2611.11937

Attention Is Only as Good as Its Witnesses: When Higher-Order Layers Help, and When They Do Not

Mostafa 'Neo' Mohsenvand

原文摘要

Transformers stop learning graph search as graphs grow, and learn the card game SET only after many distinct questions, although attention can represent both. We read these failures, and the uneven record of higher-order attention, from what a layer sums over: each layer we study computes the partition function of a family of witnesses and reads it at a temperature. Two laws follow. The depth law is a known result of logic, which we state for these layers: L layers over two-step walks reach exactly 2^L - 1 steps, just as a logical statement with L nested clauses of the form "there is a vertex such that" sees exactly that far. We build a construction that reaches this far, checked in Lean, and, when vertices carry no names, no such network reaches further. The size law is the cost of reading at a temperature, which logic does not have: existence is read correctly at every size, in the worst case, if and only if inverse temperature times margin is at least the logarithm of the number of candidates. Layers built on these laws, and on two principles that we test, learn where Transformers fail. One propagator layer trained on 49-vertex graphs answers every question at every search depth on 250-vertex graphs. Given the modulus 3, exponential Newton computes the softmax of 2-simplicial attention over pairs exactly in 3^d n operations for d clocks; with six clocks it learns SET from as few deals as 2-simplicial attention and transfers from 8- to 20-card tables. On CLRS-30 without hints, a 186,000-parameter block of OR-join and power-mean channels matches (within half a point) or beats a model of at least 73 million parameters on 9 of 12 graph tasks of the official test set, and on 8 of 12 with freshly drawn test graphs. The same account explains where pair layers did not help and where parallel layers must loop.

cs.LG · cs.AI · cs.NE

新论文 · v1arXiv:2611.11936

Constrained Variational Policy Optimization for Hybrid Action Spaces

Shuchang Yan

原文摘要

Constrained reinforcement learning in hybrid action spaces must coordinate discrete modes and mode-conditioned continuous controls under long-horizon cost constraints. Existing constrained hybrid-action methods typically optimize factorized policies directly in parameter space, whereas Constrained Variational Policy Optimization (CVPO) separates nonparametric improvement from parametric projection in its original continuous-action formulation. We introduce Hybrid Constrained Variational Policy Optimization (H-CVPO), extending this variational framework to hybrid action spaces. Under boundedness and strict feasibility, its constrained E-step has zero duality gap and, when the dual optimum is attained at positive temperature, yields a closed-form joint target distribution over hybrid actions through exponential reward-cost reweighting. Using the exact hybrid KL decomposition, we formulate a factorized M-step that fits both policy components to this target under separate discrete and conditional-continuous trust regions. For exact E/M updates, we prove fixed-reference surrogate improvement and conditional reward-cost bounds with a sufficient feasibility-margin condition. For approximate updates, we establish the existence of a dual minimizer under continuity on a compact domain and use residual-based admissibility to determine whether to project the target. Ablations identify cost-aware reweighting as an important contributor to constraint control. Extensive experiments in simulated hybrid-control environments show that H-CVPO achieves favorable reward-cost trade-offs compared with hybrid-action baselines.

cs.LG

版本更新 · v4arXiv:2610.41132

When Disclosure Is Compulsory: Evaluating Ride-Hailing Rebalancing Policies with Self-Interested LLM Driver Agents

Xinyu Wang, Andres Fielbaum

原文摘要

The EU Platform Work Directive, to be transposed by December 2026, requires ride-hailing platforms to state in plain language the main parameters of their automated decisions and how a worker's behaviour affects them. Such rules are exactly what a large language model (LLM) can read, so drivers will be able to let one decide for them. We compare two main families of rebalancing policy once their rules are public: a reactive policy (R) that sends idle drivers to cover requests just lost, and an anticipatory policy (A) that plans moves on a demand forecast. Each driver is an LLM agent maximizing its own net income, given no rules (N) or the rules at the directive's level of detail (L). We test two LLMs, Claude Haiku 5.5 and Jev, which understand the rules equally well, in a three-zone model and in Manhattan. With the rules disclosed, drivers follow the platform more closely: in Manhattan, the share of relocation offers they decline falls from about four in five to one in four under both policies. Yet the effects differ by policy. For the platform, disclosure costs R 3.7% of its profit in Manhattan, as R now pays for moves drivers used to make for free, while A's profit is unchanged; the two policies, which tie on profit under full compliance, end 6.1% apart. For drivers, disclosure raises income in the small model under both policies and LLMs; for users, it raises the service rate there by 10 to 18 percentage points. In Manhattan, self-interested drivers also make A a win-win-win against full compliance, raising driver income, platform profit and service rate by 10 to 12% each. Rebalancing policies that perform equally well under full compliance can thus show opposite results under mandatory disclosure. The study offers a framework to evaluate such policies under the new requirement and is, to our knowledge, the first to do so with LLM agents.

cs.MA · cs.AI