ArXiv Domain 2026-10-28

数据来源：ArXiv Domain

LLM Domain Papers

1. ReCoPII: A Relation-Grounded Framework for Building Contextual PII Masking Datasets

Abstract:Training contextual masking systems for personally identifiable information (PII) requires examples distinguishing maskable from preservable mentions of one entity type, but privacy restrictions limit access to real data. Author-based augmentation (SPY) labels mentions unrelated to the author as non-PII, presuming a single data subject and overlooking others. We propose ReCoPII (Relation-grounded Contextual PII masking), a framework that builds such data without this premise: it plans ontology-constrained entity relations, writes insertion sentences with placeholders, reconstructs annotations with code, checks the result with a separate LLM, and derives MASK/KEEP labels from entity relations. On Korean documents from six domains, it yields ReCoPII-Ko, a corpus with relation, privacy, and MASK/KEEP annotations, which we validate. Across 300 pairs, four annotators agree with 88.42% of its sampled KEEP labels, against 26.27% for SPY-style augmentation of the same sources. Classifiers trained on it over-mask less than under that reference on a matched test. Contextual masking fine-tuned jointly with a PII detector removes most over-masking of detection alone within a fixed leakage budget; on human-verified entity records, the four detectors meeting it over-mask at most 5.04% with at most 4.18% leakage. The detector is comparable to XLM-R-large on KDPII with about a quarter of its parameters.

中文摘要

摘要：训练用于个人可识别信息（PII）的上下文掩码系统需要区分同一实体类型中可掩码与可保留的实例，但隐私限制限制了对真实数据的访问。基于作者的增强方法（SPY）将与作者无关的提及标记为非PII，假设只有单一数据主体并忽略其他人。我们提出了ReCoPII（基于关系的上下文PII掩码），这是一个在没有这一前提下构建此类数据的框架：它规划受本体约束的实体关系，用占位符撰写插入句子，通过代码重建标注，用独立的LLM检查结果，并从实体关系中推导MASK/KEEP标签。在来自六个领域的韩文文档上，它生成了ReCoPII-Ko语料库，带有关系、隐私和MASK/KEEP标注，我们对其进行了验证。在300个配对中，四位标注员对其抽样的KEEP标签达成88.42%的一致，而同来源的SPY风格增强仅为26.27%。在匹配测试上，基于它训练的分类器比参考方法掩码过度更少。与PII检测器联合微调的上下文掩码在固定泄露预算内去除了大部分单独检测的过度掩码；在人工验证的实体记录上，四个满足条件的检测器的过度掩码最多为5.04%，泄露最多为4.18%。该检测器在KDPII上的性能可与XLM-R-large相媲美，但参数约为其四分之一。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.35925

Authors: Taehwan Lee

Categories: cs.CL

PDF URL: https://arxiv.org/pdf/2610.35925.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.35925

Published: 2026-10-28T02:34:33.007Z

2. MedJev: Evaluating Zero-Shot System-One Decision Making in Medicine

Abstract:System One decision models such as Jev answer structured questions in a single forward pass without generating text, offering fast and computationally efficient clinical decision support. We evaluate MedJev, an open System One model that runs locally on a laptop, across ten medical benchmarks spanning medical knowledge, diagnosis, and patient level prediction using MIMIC IV and MIMIC IV ED. We compare MedJev against zero shot LLM baselines, published GPT results, and supervised models. MedJev achieves accuracies of 72.5 percent on MedQA, 75.4 percent on USMLE, and 80.1 percent on NEJM, approaching published GPT 4 performance while maintaining well calibrated confidence estimates (ECE 0.028 to 0.063). On patient level tasks, MedJev achieves an AUROC of 0.926 for In Hospital Mortality, exceeding XGBoost (0.902), but underperforms supervised models on operational outcomes such as ED Triage Admission (0.745 vs. 0.809). Patient level predictions also exhibit substantial miscalibration (In Hospital Mortality ECE 0.286). We introduce a lightweight, two parameter recalibration method that adapts predictions to local patient populations using 50 to 200 labeled examples, reducing ECE to 0.007. Our findings establish open System One models as a promising zero shot baseline for medical AI, combining competitive predictive performance with low computational cost and efficient local calibration. We release our code and evaluation harness to support future research.

中文摘要

摘要：系统一决策模型，例如 Jev，可以在一次正向推理中回答结构化问题，而无需生成文本，从而提供快速且计算高效的临床决策支持。我们在十个涵盖医学知识、诊断和基于 MIMIC IV 及 MIMIC IV ED 的患者级预测的医学基准上评估了 MedJev，这是一款可在笔记本本地运行的开源系统一模型。我们将 MedJev 与零样本大型语言模型（LLM）基线、已发布的 GPT 结果以及监督模型进行比较。MedJev 在 MedQA 上的准确率达到 72.5%，在 USMLE 上为 75.4%，在 NEJM 上为 80.1%，接近已发布的 GPT-4 性能，同时保持良好校准的置信度估计（ECE 0.028 到 0.063）。在患者级任务中，MedJev 在院内死亡率预测中实现 AUROC 为 0.926，高于 XGBoost（0.902），但在急诊分诊入院等操作性结果上表现不如监督模型（0.745 对 0.809）。患者级预测还表现出显著的校准不足（院内死亡率 ECE 0.286）。我们提出了一种轻量级、仅含两个参数的重新校准方法，能够使用 50 到 200 个带标签示例将预测适应于本地患者群体，将 ECE 降低至 0.007。我们的研究结果表明，开源系统一模型是医疗人工智能领域有前景的零样本基线，兼具具有竞争力的预测性能、低计算成本和高效的本地校准。我们发布了代码和评估工具，以支持未来的研究。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36006

Authors: Simon A. Lee, Jiahang Sha, Moonseong Jeong, Yunbei Pan, Jeffrey N. Chiang

Categories: cs.CL

PDF URL: https://arxiv.org/pdf/2610.36006.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36006

Published: 2026-10-28T02:34:33.007Z

3. OmniBrain-0: A Unified Agentic Model for Embodied Intelligence

Abstract:General-purpose embodied intelligence requires robots to coordinate diverse skills over long horizons, track task progress, and recover from failures. Specialist policies alone do not ensure task-level reliability, while powerful multimodal agents rely on costly reasoning and external experience that compact models struggle to reproduce. We introduce OmniBrain-0, a lightweight unified embodied agent that coordinates manipulation and navigation through a shared high-level decision model, integrating task understanding, planning, progress tracking, and feedback-driven recovery. Our progressive training framework combines embodied pretraining, domain-specialized agent distillation, and multi-teacher on-policy distillation (MOPD). It distills powerful teachers’ interaction experience into manipulation and navigation experts, then consolidates their decision capabilities into OmniBrain-0. Unification therefore occurs within the learned decision model rather than only at the tool interface. We further introduce Rubric-Guided Recursive Self-Improvement (RSI), a data flywheel in which a Meta-Agent turns execution evidence into refined rubrics, step-level reminders, and verified trajectories for domain-expert updates before their reconsolidation into OmniBrain-0 through MOPD. We evaluate OmniBrain-0 on LIBERO-Pro, LIBERO-Plus, RoboCasa365, RoboTwin 2.0, and R2R-CE Val-Unseen, as well as multiple real-world manipulation tasks. OmniBrain-0 combines strong cross-domain task performance with substantially lower inference and execution overhead than its closed-source teacher, demonstrating efficient transfer and consolidation of embodied capabilities into a compact unified agent.

中文摘要

摘要：通用型具身智能要求机器人在长时间范围内协调多种技能、跟踪任务进度并从失败中恢复。仅靠专业策略无法保证任务级别的可靠性，而强大的多模态代理依赖于昂贵的推理和外部经验，这是紧凑模型难以复制的。我们介绍了 OmniBrain-0，这是一款轻量级的统一具身代理，通过共享的高层决策模型协调操作和导航，集成了任务理解、规划、进度跟踪以及基于反馈的恢复。我们的渐进式训练框架结合了具身预训练、领域专用代理蒸馏以及多教师在策略蒸馏（MOPD）。它将强大教师的交互经验蒸馏到操作和导航专家中，然后将它们的决策能力整合到 OmniBrain-0 中。因此，统一体现在学习到的决策模型中，而不仅仅在工具接口上。我们进一步引入了评分标准引导的递归自我改进（RSI），这是一个数据飞轮，其中元代理将执行证据转化为精炼的评分标准、步骤级提醒和经验证的轨迹，以便在通过 MOPD 再整合到 OmniBrain-0 之前用于领域专家的更新。我们在 LIBERO-Pro、LIBERO-Plus、RoboCasa365、RoboTwin 2.0 和 R2R-CE Val-Unseen 以及多个真实操作任务上评估了 OmniBrain-0。OmniBrain-0 结合了强大的跨领域任务表现，同时其推理和执行开销远低于封闭源代码的教师模型，展示了将具身能力高效转移并整合到紧凑统一代理的能力。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36013

Authors: Xiaomi Embodied Intelligence Team, Yuechen Luo, Chong He, Fang Li, Shaoqing Xu, Jingkai Wang, Menglun Su, Jiaxin Liu, Shengyin Jiang, Zhiyi Lai, Long Chen, Longlong Wang, Liang Hu, Haochen Liu, Yuncheng Jiang, Hongwei Xie, Jieming Cui, Hanbing Li, Junjie Huang, Zhixiang Duan, Hexin Zhang, Weixiang Liang, Ying Gong, Yuhan Wang, Yong Pan, Pengna Li, Kangyi Wu, Ken Deng, Kun Ma, Fuxi Wen, Zhi-xin Yang, Hangjun Ye

Categories: cs.CL

PDF URL: https://arxiv.org/pdf/2610.36013.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36013

Published: 2026-10-28T02:34:33.007Z

4. FinLLM-KG: Knowledge Graph-Enhanced LLMs for Financial Sentiment Analysis in Algorithmic Trading

Abstract:Recent advances in Generative AI have substantially improved financial sentiment analysis through post-trained financial large language models (LLMs). However, existing approaches remain confined to predicting the sentiment of each article in isolation and operate as black boxes, which limits contextual understanding and hinders deployment in high-stakes financial decision-making. To this end, we introduce FinLLM-KG, a model-agnostic framework that combines causal LLMs with a financial knowledge graph, in order to inject temporally grounded, company-level knowledge from SEC 10-K filings at inference time, without updating model weights. Within FinLLM-KG, context is supplied either as a natural-language company profile or as a small set of relevance-ranked factual triples. This enables sentiment predictions to account for broader firm-level information rather than the article alone, at almost zero computational cost and for any causal LLM. In addition, attributing each article-level sentiment score to individual sentences and to the retrieved knowledge-graph facts makes the evidence behind the prediction inspectable, thereby enhancing explainability and supporting human-in-the-loop review. Simulations demonstrate that FinLLM-KG consistently improves portfolio performance over the state-of-the-art baseline.

中文摘要

摘要：生成式人工智能的最新进展通过后训练的金融大语言模型（LLMs）显著提升了金融情感分析。然而，现有方法仍局限于孤立地预测每篇文章的情感，并以黑箱方式运行，这限制了上下文理解，并阻碍了在高风险金融决策中的部署。为此，我们提出了FinLLM-KG，这是一个模型无关的框架，将因果大语言模型与金融知识图结合起来，以便在推理时注入来自SEC 10-K 文件的时间性、公司级知识，而无需更新模型权重。在FinLLM-KG中，上下文可以通过自然语言的公司简介或一小组相关性排序的事实三元组提供。这使得情感预测能够考虑更广泛的公司级信息，而不仅仅是文章本身，几乎无需额外计算成本，并适用于任何因果大语言模型。此外，将每篇文章的情感得分归因于各个句子和检索到的知识图事实，使预测背后的证据可以被审查，从而增强可解释性并支持人工参与的审查。模拟结果表明，FinLLM-KG在投资组合表现上持续优于最先进的基线方法。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36083

Authors: Giorgos Iacovides, Oliver Hannibal, Wuyang Zhou, Danilo Mandic

Categories: cs.CL

PDF URL: https://arxiv.org/pdf/2610.36083.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36083

Published: 2026-10-28T02:34:33.007Z

5. 3, 7, 14, 17, 42: Instruction Tuning Installs and Sharpens Number-Choice Heuristics in Language Models

Abstract:We measure, without sampling error, the probability a language model assigns to each integer from 1 to N when asked for a random number. For a fixed prompt the model defines one probability vector, which we compute by summing over each integer’s scored spellings rather than estimate by sampling, removing the noise that limits earlier studies [1, 4]. We evaluate 18 open-weight model lines at five ranges up to N = 100, under 29 decoding configurations, on two inference stacks; 15 of them have matched base and instruction-tuned checkpoints that both give usable answers. Instruction tuning makes the distribution less uniform in all 15 pairs. It installs one heuristic, round-number avoidance, and sharpens another, endpoint avoidance. Base checkpoints do not avoid round numbers once the endpoints are removed from those sets; tuned checkpoints avoid them, multiples of 10 almost completely. Base checkpoints return the endpoints 1 and N at 0.30 to 0.60 of the interior rate; tuned checkpoints almost never return them. A preference for odd numbers is consistent across tuned checkpoints only at N = 100, where base checkpoints also show it weakly. Endpoint avoidance and the odd preference fit the account Kubovy and Psotka [6] proposed for human number choice; round-number avoidance is not part of that account, and the midpoint avoidance it predicts is essentially absent, with one slight exception at N = 100. Tuning does not install a new favourite integer shared across models: above N = 10 no modal integer is shared by more than 42 percent of tuned conditions, and P (17) rises in 10 of 15 pairs and falls in 5. The concentration is present in the model’s own distribution: at temperature 1.0, nucleus truncation at top-p 0.95 adds a median of 0.035 to the total variation distance.

中文摘要

摘要：我们在没有抽样误差的情况下，测量了当要求语言模型给出一个随机数字时，该模型对从 1 到 N 的每个整数分配的概率。对于固定提示，模型定义了一个概率向量，我们通过对每个整数的评分拼写求和来计算它，而不是通过抽样估计，从而消除了限制早期研究的噪声[1, 4]。我们评估了 18 条开源权重模型系列，在 N = 100 的五个范围内，在 29 种解码配置下，使用两个推理堆栈；其中 15 个既有匹配的基础检查点，也有指令调优检查点，两者都能给出可用答案。指令调优使所有 15 对中分布变得不那么均匀。它安装了一个启发式规则——避免整数字，并强化了另一个——避免端点。一旦从这些集合中移除了端点，基础检查点不会避免整数字；调优检查点会避免它们，几乎完全避免 10 的倍数。基础检查点以 0.30 到 0.60 的内部分布率返回端点 1 和 N；调优检查点几乎从不返回它们。对奇数的偏好仅在 N = 100 时在调优检查点中一致，而基础检查点在该情况下也表现出微弱偏好。端点回避和奇数偏好符合 Kubovy 和 Psotka [6] 对人类数字选择提出的解释；整数字回避不在该解释中，且它预测的中点回避基本不存在，仅在 N = 100 时有一个轻微例外。调优并未在模型间安装一个共享的新最爱整数：当 N > 10 时，没有一个众数整数被超过 42% 的调优条件共享，并且 P(17) 在 15 对中有 10 对上升，5 对下降。这种集中性存在于模型自身的分布中：在温度为 1.0 时，最高概率截断为 top-p 0.95 会使总体变化距离的中值增加 0.035。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36178

Authors: Samar Ansari

Categories: cs.CL

PDF URL: https://arxiv.org/pdf/2610.36178.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36178

Published: 2026-10-28T02:34:33.007Z

6. Lipi-Ghor: A Large-Scale, Diarized, Multi-Domain Bengali Speech Corpus and a Scalable Pipeline for Building It

Abstract:Bengali, spoken by over 230 million people, remains severely under-resourced in spoken language research. Existing open Bengali ASR corpora are confined to short, read or crowd-sourced speech and lack speaker diarization and long-form audio. We present Lipi-Ghor, a large-scale weakly-supervised Bengali speech corpus comprising 885 hours of audio sourced from 998 YouTube videos across 596 unique channels, spanning 17 diverse domains including audiobooks, drama, religious sermons, news, and regional dialects. Each recording is annotated in SSTT format (Speaker, Speech, Transcription, Timestamp), which combines automated diarization with Bengali YouTube caption tracks. To our knowledge, Lipi-Ghor is the first Bengali speech corpus to pair large-scale coverage with speaker-diarized, long-form audio annotations, both of which are absent from existing open Bengali resources. We also present the construction methodology as a replicable pipeline for any language with a sufficient captioned YouTube presence. Targeted channel curation across a handful of rich domains yields corpus scales that were previously out of reach for low-resource languages. We benchmark four widely-used ASR models under zero-shot and fine-tuned conditions. All four degrade consistently on emotive, dialectal, and long-form content. Because caption targets are noisy, we also release a human-annotated gold evaluation split, verified by 17 volunteer annotators over 30 hours of human-in-the-loop correction and stratified across all 17 domains. We release our original contributions (video-ID lists, diarization output, pipeline code, and the gold annotations) under CC-BY-4.0, and distribute caption-derived transcripts for research use only; no raw audio is redistributed.

中文摘要

摘要：孟加拉语由超过2.3亿人使用，但在口语语言研究中仍然严重缺乏资源。现有的开源孟加拉语自动语音识别（ASR）语料库仅限于短句、朗读或众包语音，缺乏说话人分离和长时音频。我们提出了Lipi-Ghor，这是一个大规模弱监督孟加拉语语音语料库，包含885小时音频，来源于998个YouTube视频，涵盖596个独特频道，横跨17个多样化领域，包括有声书、戏剧、宗教讲道、新闻和地方方言。每个录音均以SSTT格式（说话人、语音、转录、时间戳）进行注解，该格式结合了自动分离技术和孟加拉语YouTube字幕轨道。据我们所知，Lipi-Ghor是首个结合大规模覆盖与说话人分离长时音频注解的孟加拉语语料库，而这些特性在现有开源孟加拉语资源中均不存在。我们还介绍了构建方法论，作为任何拥有足够字幕化YouTube内容语言的可复制管道。通过针对少数丰富领域的频道策选，语料库规模达到了低资源语言此前无法实现的水平。我们在零样本和微调条件下对四个广泛使用的ASR模型进行了基准评测。四个模型在情感化、方言化和长段内容上均表现出一致下降。由于字幕目标存在噪声，我们还发布了一份经过人工注解的黄金评估集，由17名志愿者注解者在30小时的人工纠错过程中验证，并在所有17个领域中进行分层。我们将原创贡献（视频ID列表、分离输出、管道代码和黄金注解）以CC-BY-4.0许可发布，并仅分发由字幕派生的转录文本用于研究；原始音频不作公开分发。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36184

Authors: Sanjid Hasan, A H M Fuad, Risalat Labib, Bayazid Hasan Simon

Categories: cs.CL

PDF URL: https://arxiv.org/pdf/2610.36184.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36184

Published: 2026-10-28T02:34:33.007Z

7. Frankly Speaking: The Company Election Integrity Keeps in Congressional Communication

Abstract:Election integrity is a shared commitment in American politics, but Democrats and Republicans in Congress increasingly mean different things by it. Analyzing 10,420 congressional e-newsletters sent from 2010 to 2025, we examine how the two parties invoke election terms such as integrity,''security,’’ and fraud.'' Using diachronic word embeddings, which track semantic change through how words are used in context, we measure how differently each party uses each term, how much each party shifts, and whether they share nearest semantic neighbors. We show that members of Congress do not need different words to tell different stories about elections. They need only place those same words in different company. Across nearly every term and year, the two parties surround election-integrity vocabulary with entirely different words. That divergence is easy to miss, because most election vocabulary is no more divergent than other words used at roughly the same frequency, and neither party's usage shifted more than the other's. Only a subset of terms grew more divergent, most notablycertification,’’ while rigged'' andstolen’’ entered election discourse after 2020 and polarized there. By 2024, Democrats surround voter,''election,’’ and integrity'' with the language of access and administration. Republicans surround the same terms withcitizenship verification,’’ noncitizen voting,'' andborder security.’’ For one party, integrity means protecting eligible voters’ ability to cast a ballot. For the other, it means protecting the electoral process from illegitimate ballots. Election officials, who must administer a single system under both definitions, inherit this tension.

中文摘要

摘要：选举诚信是美国政治中的共同承诺，但国会中的民主党人和共和党人对其含义越来越不同。通过分析2010年至2025年间发送的10,420份国会电子通讯，我们研究了两党如何使用诸如“诚信”、“安全”和“舞弊”等选举相关术语。利用历时词嵌入——通过单词在语境中的使用追踪语义变化的方法——我们衡量了每个党派对每个术语的使用差异、各党派的语义转变程度，以及是否共享最近的语义邻居。我们显示，国会议员不必使用不同的词语来讲述不同的选举故事。他们只需将相同的词置于不同的语境中即可。在几乎每一个术语和年份，两个党派在描述选举诚信的词汇周围使用的词是完全不同的。这种差异容易被忽视，因为大多数选举词汇的分歧程度并不高于频率相近的其他词汇，而且两个党派的使用变化幅度也相差无几。只有部分术语的分歧增加，尤其是“认证”，而“操纵”和“被盗”是在2020年后进入选举话语并在那里产生极化的。到2024年，民主党人用有关包容性和选举管理的语言围绕“选民”、“选举”和“诚信”；共和党人则将同样的术语与“公民身份验证”“非法居民投票”和“边境安全”联系在一起。对于一个党派来说，诚信意味着保护符合条件的选民投票的能力；对于另一个党派来说，它意味着保护选举过程免受非法选票的干扰。选举官员必须在两种定义下管理同一系统，因此承接了这种紧张关系。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36187

Authors: Michael A. Robinette, Christina Barsky, Amanda D. Clark, Helen Flannery, Juniper Lovato

Categories: cs.CL

PDF URL: https://arxiv.org/pdf/2610.36187.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36187

Published: 2026-10-28T02:34:33.007Z

8. LLM Hallucination Detection via Low-rank Multilinear Decomposition

Abstract:Large language models (LLMs) frequently generate fluent yet factually incorrect responses, raising concerns about their reliability. Recent hallucination detectors increasingly exploit internal representations, but extracting informative signals from high-dimensional hidden states remains challenging. Existing approaches often rely on selected activations or pooling-based compression, potentially overlooking discriminative information distributed across Transformer layers, feature modes, and tokens. We propose LOTUS (Low-rank Order-statistic TUcker-based Subspace learning), a multilinear low-rank decomposition framework for hallucination detection that extracts compact representations from LLM hidden states while reducing dependence on labeled data. Our approach first summarizes variable-length token representations using complementary statistical descriptors that capture peak activations, activation distributions, and cross-layer changes. We then leverage low-rank multilinear decomposition to extract compact representations that capture the underlying structure of LLM hidden states, which are subsequently used to train a lightweight hallucination classifier. Experiments across multiple LLMs and question-answering benchmarks demonstrate improved hallucination detection performance over recent state-of-the-art baselines.

中文摘要

摘要：大型语言模型（LLMs）经常生成流畅但事实错误的回答，这引发了对其可靠性的担忧。近期的幻觉检测器日益利用内部表示，但从高维隐藏状态中提取信息信号仍然具有挑战性。现有方法通常依赖于选定的激活或基于池化的压缩，可能会忽略分布在Transformer层、特征模式和标记上的判别信息。我们提出了LOTUS（低秩阶统计Tucker子空间学习），一种用于幻觉检测的多线性低秩分解框架，该框架从LLM隐藏状态中提取紧凑表示，并减少对标注数据的依赖。我们的方法首先使用互补的统计描述符对可变长度的标记表示进行总结，这些描述符捕捉峰值激活、激活分布及跨层变化。然后，我们利用低秩多线性分解提取紧凑表示，这些表示捕捉LLM隐藏状态的潜在结构，随后用于训练轻量级幻觉分类器。在多个LLM和问答基准上的实验表明，相较于近期最先进的基线方法，我们的方法在幻觉检测性能上有所提升。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36191

Authors: Devansh Sharma, Faizul Rakib Sayem, Shahana Ibrahim

Categories: cs.CL

PDF URL: https://arxiv.org/pdf/2610.36191.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36191

Published: 2026-10-28T02:34:33.007Z

9. Beyond IceBERT: Open-Data ModernBERT Encoders for Icelandic from 12M to 1B Parameters

Abstract:IceBERT, the reference encoder for Icelandic, found that a cleaned web crawl is enough to train a strong model and that starting from a multilingual model can help on some tasks. We revisit both findings with the ModernBERT architecture. We train Icelandic encoders from 12M to 1B parameters on 9B tokens of open data, and rerun IceBERT’s benchmarks and five newer tasks for 30 encoders under one protocol with confidence intervals. Our 1B model trained from scratch, to our knowledge the first monolingual Icelandic encoder of that size, is significantly better than IceBERT on all eleven tasks; warm-started from the English Ettin encoder of the same shape, it has the best score of all encoders on every task we rank. Because our model shapes match the English Ettin encoders and the multilingual mmBERT, we can also test the warm start under controlled conditions, at six model sizes and four token budgets. With our vocabulary transplanted, a warm start was never significantly worse than scratch training on the same Icelandic text, and from base size up it was not significantly worse on four tasks than scratch training on 4 times the text (8 times at base and 1B). As models grow, most of the transfer comes from the source model’s transformer layers, so even an English source helps. Keeping the source vocabulary instead cost 5 F1 on question answering and nearly three times the compute.

中文摘要

摘要：IceBERT，冰岛语的参考编码器，发现清理后的网页抓取数据足以训练出强大的模型，并且从多语言模型开始可以在某些任务上有所帮助。我们使用 ModernBERT 架构重新考察了这两个发现。我们在 90 亿个开放数据 token 上训练了参数从 1200 万到 10 亿的冰岛语编码器，并在一个统一的协议下对 30 个编码器重复进行了 IceBERT 的基准测试和五个更新任务，同时提供置信区间。我们从零开始训练的 10 亿参数模型，据我们所知，是首个此规模的单语冰岛语编码器，在所有十一项任务中显著优于 IceBERT；如果从同样结构的英语 Ettin 编码器进行预热启动，其在我们排名的每个任务中都取得了所有编码器中的最好得分。由于我们的模型结构与英语 Ettin 编码器和多语言 mmBERT 匹配，我们也可以在受控条件下测试预热启动，涵盖六种模型尺寸和四种 token 预算。在迁移词汇表时，预热启动在相同冰岛语文本上的表现从未显著低于从零开始训练，并且从基础模型大小起，在四个任务上也没有显著低于使用四倍文本（基础模型和 10 亿参数时为八倍文本）进行从零训练。随着模型规模增长，大部分迁移来自源模型的 Transformer 层，因此即使是英语源模型也有所帮助。保持源词汇表的情况下，在问答任务上 F1 降低了 5 分，计算量几乎增加了三倍。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36230

Authors: Hafsteinn Einarsson

Categories: cs.CL

PDF URL: https://arxiv.org/pdf/2610.36230.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36230

Published: 2026-10-28T02:34:33.007Z

10. Detect Before You Disambiguate: Perturbation-Based Input Ambiguity Detection in LLMs

Abstract:Large language models (LLMs) often answer ambiguous inputs as if they had a single intended meaning. This is problematic because input ambiguity is an upstream source of uncertainty: when a prompt admits multiple valid interpretations, the key question is whether the model should answer directly at all. Existing input uncertainty methods often rely on LLM-generated statements or clarifications, but such transformations may already disambiguate the input before the ambiguity is measured. We propose a label-preserving perturbation framework for input ambiguity detection in which perturbations remain close to the original input while preserving its label. We instantiate this principle with two detectors: a black-box rule-based perturbation library and a white-box importance-guided method using model-internal signals. Experiments across four datasets in open-domain, conversational, and visual QA show that our methods outperform output-side uncertainty baselines and LLM-paraphrase-based perturbation baselines. Our results highlight the importance of detecting ambiguity before attempting to disambiguate it. Our code is available \href{this https URL}{\textcolor{purple}{here}}.

中文摘要

摘要：大型语言模型（LLMs）常常将含糊输入当作单一意义来回答。这存在问题，因为输入含糊性是不确定性的上游来源：当提示符允许多种有效解释时，关键问题是模型是否应直接回答。现有输入不确定性方法通常依赖LLM生成的陈述或澄清，但此类转换可能在测量歧义前就已消除歧义。我们提出了一种保持标签的扰动框架用于输入歧义检测，扰动保持接近原始输入但保持其标签。我们通过两种检测器实现这一原则：基于规则的黑盒扰动库和基于模型内部信号的白盒重要性引导方法。在开放域、对话式和可视化质检中，跨越四个数据集的实验显示，我们的方法优于输出端不确定性基线和基于LLM的变句扰动基线。我们的结果强调了在尝试消歧之前检测歧义的重要性。我们的代码可用 \href{this https URL}{\textcolor{purple}{here}}。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36353

Authors: Tiejin Chen, Xiaoou Liu, Michael Clifford, Ahmadreza Moradipari, Yitao Chen, Kyungtae Han, Nejib Ammar, Hua Wei

Categories: cs.CL

PDF URL: https://arxiv.org/pdf/2610.36353.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36353

Published: 2026-10-28T02:34:33.007Z

Agent Domain Papers

1. Counting the Bandages: On measuring the time that AI saves

Abstract:I consider what it means for AI assistance to save time. I contrast a stopwatch view, on which time saved is whatever the clock records, with a ledger view, on which it is a counterfactual that has to be read next to the errors the work lets through, and I argue for the latter. The argument has four parts. I define a model-free pair of quantities, time saved and excess escaped defects, and one decision number built from them: the break-even defect cost. I give a baseline model of checking in which, until the model is good enough not to check, a calibrated worker’s escaped-defect rate does not depend on how good the model is; checking time grows with the logarithm of the model’s error rate; and over-trust buys minutes on the clock at a larger cost in total minutes. I show what randomized studies can and cannot identify, and I replicate METR’s developer study from its public data: the same 246 issues support a slowdown of 19% or 24% depending on the estimand (34% without adjusting for a chance imbalance), and AI helped on somewhere between 3% and 82% of them. Finally, I restate the published record, with stated bounds in place of imported point assumptions. In GDPval’s own review-every-output workflow, review time alone caps GPT-5’s speedup at 3.6x; the consultants outside the frontier were faster, and more often wrong. Last, I test two of the model’s predictions in a small pre-specified experiment on AI reviewers checking AI drafts of the same kind of brief, built from SEC filings made after the models’ training data were collected. Told the drafter’s true error rate, the reviewer checked more as it rose, but all-or-nothing, switching near where its prompt’s costs break even. Told that the drafter erred ten times less often than it did, it checked 7 fewer of 9 figures and let a wrong figure through in 22.5% of briefs instead of none: faster and worse, entirely through reduced effort.

中文摘要

摘要：我思考了人工智能辅助节省时间意味着什么。我对比了一种计时器视角，在这种视角下，节省的时间就是时钟记录的时间，与一种账本视角，在这种视角下，它是一种反事实，必须与工作留下的错误一起阅读，并且我支持后者。论证分为四部分。我定义了一对无模型的量——节省时间和多余的未发现缺陷，以及从它们构建的一个决策数：盈亏平衡缺陷成本。我给出了一个检查的基准模型，在该模型中，除非模型足够好以至于不需要检查，否则经过校准的工作人员的未发现缺陷率不取决于模型好坏；检查时间随模型错误率的对数增长；过度信任以更大的总时间成本换取时钟上的分钟。我展示了随机研究能识别和不能识别的内容，并从公开数据中复制了METR的开发者研究：相同的246个问题根据估计量支持19%或24%的减速（未调整偶然不平衡时为34%），AI在其中的某些问题上提供了3%到82%的帮助。最后，我重述了已发表的记录，以明确界限代替导入的点假设。在GDPval自己每个输出都要审查的工作流程中，仅审查时间就将GPT-5的加速上限限制在3.6倍；前沿之外的顾问更快，但更容易出错。最后，我在一个小型预先规定的实验中测试了模型的两个预测，该实验针对AI审阅者检查与模型训练数据收集后生成的SEC文件构建的同类简报的AI草稿。当告知审稿人的真实错误率时，审稿人随着错误率上升而检查更多，但采取全有或全无的方式，在其提示的成本盈亏平衡处切换。当告知撰稿人的错误率比实际低十倍时，它检查了9个图表中的7个更少，并在22.5%的简报中放过了一个错误图表，而不是没有错误：更快且更差，完全是因为减少了努力。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.35942

Authors: Solomon Shalom Lijo

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.35942.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.35942

Published: 2026-10-28T02:34:59.553Z

2. Enhancing Deep Learning Model Performance through Data Generation Strategies: Classification of Olive Tree Diseases

Abstract:Deep learning models are highly effective in a wide range of domains, particu larly in plant disease diagnosis. However, their performance is often limited by challenges such as insufficient data and class imbalance. In our work, we propose a comprehensive data generation strategy to overcome these limitations. First, we apply various data generation techniques, including traditional augmentation methods, CutMix, MixUp, and synthetic image generation using Deep Convolu tional Generative Adversarial Networks (DCGANs), to create new data samples. Second, we exploit this generated data in three scenarios: (S1) balancing class distribution in the original dataset, (S2) increasing the number of samples per class, and (S3) expanding the dataset while maintaining balanced classes. Third, we evaluate the impact of these data distributions (S1, S2, S3) on model perfor mance using the EfficientNetV2B0 architecture with pre-trained and fine-tuned weights. The experimental results show a substantial improvement in classifica tion accuracy, emphasizing the critical role of data diversity and class balance. These findings highlight the effectiveness and adaptability of the proposed strat egy of data generation and distribution for enhancing dataset quality, offering promising applications in plant disease detection and precision agriculture.

中文摘要

摘要：深度学习模型在广泛的领域中表现出极高的效能，尤其是在植物病害诊断方面。然而，它们的性能通常受到数据不足和类别不平衡等挑战的限制。在我们的工作中，我们提出了一种全面的数据生成策略以克服这些限制。首先，我们应用各种数据生成技术，包括传统的数据增强方法、CutMix、MixUp，以及使用深度卷积生成对抗网络（DCGANs）生成的合成图像，来创建新的数据样本。其次，我们在三个场景中利用这些生成的数据：（S1）平衡原始数据集中的类别分布，（S2）增加每个类别的样本数量，以及（S3）在保持类别平衡的同时扩展数据集。第三，我们使用具有预训练和微调权重的EfficientNetV2B0架构评估这些数据分布（S1、S2、S3）对模型性能的影响。实验结果显示分类准确率显著提高，强调了数据多样性和类别平衡的重要作用。这些发现突显了所提出的数据生成与分布策略在提升数据集质量方面的有效性和可适应性，为植物病害检测和精准农业提供了有前景的应用。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.35984

Authors: Hicham El Akhal, Abderrahim Waga, Aissa Ben Yahya, Abdelbaki El Belrhiti El Alaoui

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.35984.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.35984

Published: 2026-10-28T02:34:59.553Z

3. The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents

Abstract:Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing heterogeneous, verifiable environments is costly, and manual Harness iteration cannot keep pace with growing task diversity and complexity. A key insight is that tasks with different modalities and surface forms can share the same underlying capability requirements. We therefore introduce The Trinity, a recursive self-improvement framework coupling world generation with Harness evolution through three roles: Creator, Explorer, and Evolver. Drawing on verified execution trajectories, Evolver shifts the basis of task organization from surface categories to shared requirements, reorganizing the original task tree into a hierarchical capability tree. We introduce Capability-Driven Real2Sim2Real: for heterogeneous tasks at the same node, Creator abstracts their common requirements into simplified, verifiable simulated worlds for capability learning, while evaluation on original tasks measures transfer. Along this capability tree, Explorer progressively evolves reusable capability modules through selective inheritance, forming a Harness tree whose validated updates accumulate across iterations within a fixed topology. The resulting Harnesses specialize in different capabilities, motivating a Capability-Aware Harness Router that uses public task information to select compatible module configurations from the tree. Our evolved Harnesses improve mean performance by 34 points across 28 training benchmarks and 26 points across 18 unseen benchmarks, including two real-world embodied tasks.

中文摘要

摘要：多模态智能可以被视为通过交互实现的世界与智能体之间的人类引导共进化。然而，这一过程的扩展面临两个瓶颈：构建异质且可验证的环境成本高昂，以及手动开发的迭代无法跟上任务多样性和复杂度的增长。一个关键见解是，不同模态和表面形式的任务可以共享相同的底层能力需求。因此，我们引入了“三位一体”（The Trinity），这是一个递归自我改进框架，通过三种角色——创造者（Creator）、探索者（Explorer）和进化者（Evolver）——将世界生成与Harness演化相耦合。在经过验证的执行轨迹的基础上，Evolver 将任务组织的基础从表面类别转移到共享要求，将原始任务树重组为层次化能力树。我们引入基于能力驱动的 Real2Sim2Real：对于同一节点的异质任务，Creator 将它们的共性需求抽象为简化、可验证的模拟世界进行能力学习，同时在原始任务上的评估衡量迁移效果。沿着这棵能力树，Explorer 通过选择性继承逐步演化可复用的能力模块，形成一个 Harness 树，其验证后的更新在固定拓扑内跨迭代累积。由此产生的 Harnesses 在不同能力上实现了专门化，从而激发了能力感知的 Harness 路由器（Capability-Aware Harness Router），它使用公共任务信息从树中选择兼容的模块配置。我们演化的 Harnesses 在28个训练基准上平均性能提高34点，在18个未见基准上提高26点，包括两个现实世界的具身任务。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36077

Authors: Weidong Tang, Ruiheng Wang, Jingxuan Zhang, Hexin Wang, Haoyuan Chen, Zhengfeiyang Zhang, Yixing Ma, Zichen Jiang, Ziyu Guo, Haodong Li, Zhengbo Jiao, Zhiqing Cui, Xinxiang Yin, Shuo Liang, Zhenglin Wan, Hongzhan Lin, Wangbo Zhao Kaipeng Zhang, Pengfei Zhou, Odin Zhang, Yang You

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.36077.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36077

Published: 2026-10-28T02:34:59.553Z

4. CohortFlow: A Steerable Clinical Cohort Curation Agent with Localized Semantic Correction

Abstract:Language model agents for clinical cohort curation should accommodate evolving eligibility criteria without repeatedly processing unchanged requirements. We introduce CohortFlow, a steerable agent that represents natural language corrections as localized updates to a structured cohort specification and reconciles them with a persistent execution graph. Explicitly recorded semantic dependencies enable affected computations to be selectively invalidated while preserving valid prior results. On 100 scenarios derived from clinical-trial eligibility criteria, comprising 126 correction turns, localized steering achieves 77.0% requirement micro-F1 versus 76.4% for full regeneration using the same 8B model, a small numerical advantage that is not statistically significant ($p=0.493$). It reduces mean correction latency by 64.8% after completion and 44.3% during execution, with 38.1% fewer model calls. In a separate proof-of-concept evaluation over MIMIC, all 13 cohort states execute successfully, while correction trajectories demonstrate selective preservation of unaffected computations and recomputation of changed or dependent nodes. Together, these results show that localized semantic steering can substantially reduce correction latency and model calls while maintaining strong requirement-level accuracy.

中文摘要

摘要：用于临床队列策展的语言模型代理应能适应不断变化的资格标准，而无需反复处理未更改的要求。我们引入了CohortFlow，一种可引导的代理，它将自然语言修正表示为对结构化队列规范的局部更新，并将其与持久的执行图进行协调。明确记录的语义依赖关系使受影响的计算能够被选择性地作废，同时保留有效的先前结果。在基于临床试验资格标准的100个场景（共包含126次修正回合）中，局部引导实现了77.0%的要求微F1，相比使用相同的8B模型进行完整再生成的76.4%，这一小幅数值优势在统计上并不显著（$p=0.493$）。它在完成后将平均修正延迟减少了64.8%，执行过程中减少了44.3%，模型调用次数减少了38.1%。在另一个基于MIMIC的概念验证评估中，所有13个队列状态均成功执行，同时修正轨迹展示了对未受影响计算的选择性保留以及对已更改或依赖节点的重新计算。综合来看，这些结果表明，局部语义引导可以在保持高要求级准确性的同时，大幅降低修正延迟和模型调用次数。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36100

Authors: Neil Chen, Adrian Serapio, Hanxue Gu, Evan Lee, Kang Wang, Yang Yang

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.36100.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36100

Published: 2026-10-28T02:34:59.553Z

5. Why and How to Do Science When AI Is Better at It: A Framework Grounded in Human Understanding and Direction

Abstract:As AI begins to match or exceed human researchers at core scientific tasks, two questions become pressing: \emph{why} should humans keep doing science, and \emph{how} should they use AI when they do? This paper argues that the second can be answered only by answering the first. It holds that one indispensable aim of science is \emph{durable, collective human understanding of the world, pursued in service of human ends and values}. From this principle it derives a two-part test for when a research task can be delegated to AI. The first part, \emph{human understanding}, requires that the scientific community remain able to explain, defend and contest the resulting claims, and retain the skills to do so. The second, \emph{human direction}, requires that judgments about which questions matter and what findings mean stay with accountable humans. Applying the test to each phase of research in the Contributor Roles Taxonomy (CRediT) yields recommendations that fields can tailor to their questions and methods. The framework differs from existing guidance in three ways. It rests on an account of what science is for rather than on integrity norms. It holds even if AI outperforms human researchers, rather than depending on AI’s current limitations. And it judges each use of AI by its effects on human understanding and direction rather than by the type of tool, across every phase of research, including peer review and the training of new researchers. It closes with the reforms needed to keep science aimed at human understanding and direction.

中文摘要

摘要：随着人工智能在核心科学任务上开始与人类研究者匹敌甚至超越，两个紧迫问题变得迫切：为什么人类应该继续做科学，以及他们在做科学时该如何使用人工智能？本文认为，只有回答第一个问题才能回答第二个问题。它认为科学的一个不可或缺目标是实现持久的、集体的人类理解，服务于人类的目标和价值观。基于这一原则，它提出了一个两部分的测试，判断何时可以将研究任务委托给人工智能。第一部分，\emph{人类理解}，要求科学界能够解释、辩护和反驳所得主张，并保持相关技能。第二部分，\emph{人类指导}，要求对哪些问题重要性和发现意义的判断必须由负责任的人类掌握。将该测试应用于贡献者角色分类法（CRediT）中的每个研究阶段，可以提出各领域根据自身问题和方法量身定制的建议。该框架与现有指导意见有三点不同。它基于科学的目的，而非诚信规范。即使人工智能表现优于人类研究者，而非依赖人工智能当前的局限性，它依然适用。它在包括同行评审和新研究者培训在内的每个研究阶段，均以人工智能对人类理解和方向的影响而非工具类型来评判每一次人工智能的使用。最后，它提出了必要的改革，以确保科学以人类理解和方向为目标。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36116

Authors: Hoda Heidari, Aydin Mohseni

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.36116.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36116

Published: 2026-10-28T02:34:59.553Z

6. From Structural Feedback to Prompt Policies: Learning Faithful Text-to-Image Prompt Editors

Abstract:Prompt optimization should improve the image a user receives without changing the scene the user requested. Yet stylistic rewriting can weaken object attributes and relations even when global text—image similarity remains high. We propose StruPO, a structure-aware prompt editor that uses a calibrated scene graph as a shared representation for policy conditioning and image-grounded supervision. The graph exposes what should be preserved, while deletion, reordering, and insertion provide a token-aligned way to modify the prompt. This turns structural feedback from an external critique into a training signal for a reusable editing policy. Learning from that signal requires handling both uncertain grounding and stochastic image generation. StruPO retains grounding confidence through smooth reward shaping and averages multiple images for each edit before computing group-relative advantages. Experiments span three disjoint 2K-prompt test sets and four frozen generation backbones, with comparisons to learned prompt optimizers, iterative structural feedback, diffusion-model fine-tuning, and inference-time attention control. StruPO improves the faithfulness—aesthetics trade-off, with consistent gains in relational fidelity. Independent automatic evaluators and a 15-annotator study provide complementary evidence, and human preference margins increase with relation complexity. Controlled ablations connect these gains to graph conditioning, local editing, and image-grounded learning. The resulting policy produces reusable optimized text in one pass after graph calibration, without an iterative critique—rewrite loop.

中文摘要

摘要：提示优化应在不改变用户所请求场景的情况下改善用户收到的图像。然而，即使整体文本与图像的相似度保持较高，风格化重写也可能削弱对象属性和关系。我们提出了 StruPO，一种结构感知的提示编辑器，它使用校准后的场景图作为策略条件和基于图像监督的共享表示。该图揭示了应保留的内容，而删除、重排和插入提供了一种与令牌对齐的方式来修改提示。这将来自外部批评的结构化反馈转化为可重复使用的编辑策略的训练信号。从该信号学习需要处理不确定的落地和随机图像生成。StruPO 通过平滑的奖励塑形保持落地信心，并在计算组相对优势前对每次编辑生成的多张图像进行平均。实验涵盖了三个不相交的 2000 条提示测试集和四个冻结的生成主干网络，并与学习型提示优化器、迭代结构反馈、扩散模型微调以及推理时注意力控制进行了对比。StruPO 改善了忠实性与美学的权衡，并在关系保真度上实现了持续提升。独立自动评估器和 15 位标注者的研究提供了互补证据，人类偏好差距随关系复杂度增加而增大。受控消融实验将这些提升与图条件、本地编辑和基于图像的学习联系起来。由此产生的策略在图校准后即可一次性生成可重用的优化文本，无需迭代的批评-重写循环。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36146

Authors: Wentao Ye, Yali Ye, Zhiqing Xiao, Ru Peng, Xinpeng Ti, Liyao Li, Zhanming Shen, Peng Lu, Jie Zhang, Haobo Wang

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.36146.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36146

Published: 2026-10-28T02:34:59.553Z

7. Don’t Pick a Winner: Knowledge Conflicts Need a Prior, Not a Rule

Abstract:A retrieval-augmented language model answers from two sources, the retrieved context and its own knowledge, and the two disagree whenever the context is incomplete or wrong. Existing methods settle the disagreement with a rule fixed at design time: follow the context, amplify it in proportion to how far it moves the model, or trust the model’s memory. Each rule is confidently wrong in some deployment. In a decision-theoretic model of two sources, the score of any fixed rule is linear in the share of reliable contexts while the best attainable score is convex, so every fixed rule is beaten wherever it is not exactly optimal; and a symmetric divergence between the two sources, the signal adaptive decoding uses, carries no information about which one is right. Resolving a conflict therefore needs two inputs that no existing method keeps: evidence about each source separately, and a prior on how often the context is right. We test these claims on GRACE, a benchmark that intervenes on the knowledge-graph context of a fixed question, so that what the model knows, what the context says and what is true are measured separately. There, every baseline from four families is strong on right contexts or on wrong ones, never on both. We then build the two inputs: the model states its knowledge as notes, a small policy voices each note with a calibrated confidence, a reader answers in two voices, and a selector commits or abstains under a prior $\pi$ applied as an exact prior shift. With $\pi$ set to the true share of right contexts, the system is above the best baseline at every mixture of GRACE contexts, by up to 26 points. Its overall score is 45.3 and 35.0 (Qwen3.5-35B-A3B, Llama-3.1-8B), against 29.4 and 27.5 for the best baseline. On preregistered ClashEval it beats same-backbone CK-PLUG and TCR by 12 and 26 points. Where the model lacks the knowledge, the gains vanish, as the theory predicts.

中文摘要

摘要：检索增强语言模型从两个来源回答：检索的上下文和自身知识，当上下文不完整或错误时，两者会存在分歧。现有方法解决设计时固定规则的分歧：遵循上下文，按移动模型的程度放大，或信任模型记忆。每种规则在某些部署中都是明确错误的。在两个来源的决策理论模型中，任何固定规则的得分在可靠上下文中是线性的，而最佳可达分数是凸的，因此每个固定规则在不完全最优的地方都会被击败;信号自适应解码所用的两个来源之间的对称背离，不包含哪一条正确的信息。因此，解决冲突需要两个输入，而现有方法都不保留：分别关于每个来源的证据，以及上下文正确频率的先验。我们在GRACE上测试这些主张，GRACE是一个基准测试，该基准会介入固定问题的知识图谱上下文，从而分别测量模型所知、上下文所说和真实。在那里，四个族的每个基线在正确的语境上都强或在错误的语境上强，绝不会同时在两者上。然后我们构建两个输入：模型以笔记形式陈述其知识，一个小型策略以校准置信度表达每个音符，读者以两个声音回答，选择器根据先前应用的精确先验偏移来承诺或放弃。当$\pi$设置为正确上下文的真实份额时，系统在每种GRACE上下文混合中都比最佳基线高出最多26个百分点。其总体得分分别为45.3和35.0（Qwen3.5-35B-A3B，Llama-3.1-8B），而最佳基线分别为29.4和27.5。在预注册的ClashEval中，它以12点和26点优势击败了同骨干的CK-PLUG和TCR。模型缺乏知识时，正如理论预测的那样，收益将消失。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36169

Authors: Minh Pham Van, Cong Tran

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.36169.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36169

Published: 2026-10-28T02:34:59.553Z

8. Learning Human Sports Motion Feasibility via Quantile Regression on Tracking Data

Abstract:We study time-to-arrival (TTA) in sports: the shortest plausible time a player needs to reach an arbitrary location on the pitch given their current kinematic state, estimated as the lower envelope of observed locomotion times. Rather than modeling space ownership through position density estimation or closed-form physics-based models, we cast TTA as a conditional quantile regression problem, estimating the lower quantile of locomotion time so the model learns a player’s lower-envelope arrival time. We train the model on optical tracking data from all 64 matches of the PFF FC FIFA World Cup 2022 dataset, and evaluate a lightweight multilayer perceptron against six player-motion models from the literature, re-expressed as TTA predictors, and a learned reachable- hull baseline. Across our evaluation metrics, the MLP consistently outperforms every physics-based baseline. To probe the generality of the learned locomotion model, we further evaluate it on basketball tracking data and a single-game NFL tracking dataset, analyzing the transferability of player motion dynamics across sports. Our project is available at this https URL.

中文摘要

摘要：我们研究体育运动中的到达时间（TTA）：基于球员当前的运动学状态到达场上任意位置所需的最短可行时间，该时间估计为观测到的运动时间的下包络线。我们没有通过位置密度估计或闭式物理模型来建模空间占有情况，而是将TTA定义为条件分位数回归问题，估计运动时间的下分位数，从而让模型学习球员的下包络到达时间。我们在PFF FC 2022 FIFA世界杯数据集中所有64场比赛的光学跟踪数据上训练模型，并将轻量级多层感知器（MLP）与文献中六个球员运动模型（重新表达为TTA预测器）以及一个学习的可达外壳基线进行评估。在我们的评价指标中，MLP始终优于所有基于物理的基线模型。为了探究学习到的运动模型的普遍性，我们进一步在篮球跟踪数据和一场NFL比赛的跟踪数据上对其进行了评估，分析球员运动动态在不同运动项目中的可迁移性。我们的项目可通过此https URL获取。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36183

Authors: Marc Gutiérrez-Pérez, Antonio Agudo

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.36183.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36183

Published: 2026-10-28T02:34:59.553Z

9. Skill Dreaming: Evolving Repository Skills through Pull Request Streams

Abstract:Large language model (LLM) agents increasingly rely on reusable skills for complex software engineering tasks, making skill libraries essential for repository development and maintenance. However, repository-specific skills must evolve with changing code structures, implementation conventions, and maintenance requirements. Pull requests (PRs) provide a natural source of such knowledge by recording how repositories evolve through implementation and review. Meanwhile, new PRs must follow repository-specific implementation patterns, modify related components consistently, and ensure that existing tests continue to pass while adding coverage for new functionality. This creates a mutually reinforcing cycle: PRs provide knowledge for updating skills, while these skills improve future PRs, maintain repositories, and support further skill evolution. To enable this co-evolution of PRs, repositories, and skills, we propose Skill Dreaming, a framework that learns from PR streams to guide continuous repository development and maintenance. Given a repository and its PR history, Skill Dreaming builds a repository-specific skill library by extracting executable knowledge from validated PRs and continuously refines the skills as new PR information becomes available. These skills guide coding agents not only in implementing requested features but also in maintaining associated tests, documentation, compatibility, and repository conventions. By integrating PR analysis, skill management, code execution, and continuous integration, Skill Dreaming provides an end-to-end workflow for applying learned skills to repository changes and incorporating subsequent PR outcomes into future skill updates.

中文摘要

摘要：大型语言模型（LLM）代理越来越依赖可重复使用的技能来完成复杂的软件工程任务，这使得技能库对于代码库的开发和维护至关重要。然而，特定代码库的技能必须随着代码结构、实现约定和维护需求的变化而发展。拉取请求（PR）提供了这种知识的自然来源，因为它记录了代码库通过实现和审查的演变过程。与此同时，新PR必须遵循特定代码库的实现模式，一致地修改相关组件，并确保在添加新功能覆盖的同时，现有测试仍能通过。这形成了一个相互促进的循环：PR为更新技能提供知识，而这些技能又改善了未来的PR，维护代码库，并支持技能的进一步演变。为了实现PR、代码库和技能的共同进化，我们提出了Skill Dreaming框架，该框架从PR流中学习，以指导代码库的持续开发和维护。在给定代码库及其PR历史的情况下，Skill Dreaming通过从已验证的PR中提取可执行知识构建特定代码库的技能库，并随着新PR信息的出现不断优化这些技能。这些技能不仅引导编码代理实现所需功能，还指导其维护相关测试、文档、兼容性和代码库约定。通过整合PR分析、技能管理、代码执行和持续集成，Skill Dreaming提供了一个端到端工作流程，用于将学到的技能应用于代码库的变化，并将随后PR的结果纳入未来的技能更新。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36188

Authors: Xinyuan Song, Hasibul Haque, Jay Somasundaram, Ryan Turner, Bowen Zhu, Liang Zhao

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.36188.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36188

Published: 2026-10-28T02:34:59.553Z

10. MARQ: A Modular, LLM-Agnostic Requirement Quality Assessor Infused with Systems Engineering Knowledge

Abstract:Requirements engineering (RE) is foundational to systems engineering (SE), as requirement defects can propagate downstream and adversely affect development outcomes. Although large language models (LLMs) are promising for requirement quality assessment, prior work shows that off-the-shelf models miss a large share of expert-identified defects, perform unevenly across quality criteria, and vary across executions. This study investigates whether infusing expert-derived SE knowledge can improve LLM-based requirement quality evaluation beyond off-the-shelf capability. We present MARQ, a modular, LLM-agnostic prototype that supplements LLMs with a criterion-specific knowledge stack operationalizing INCOSE requirement quality criteria and evaluated against off-the-shelf baselines on an expert-labeled NASA requirement set using Claude Opus 5, GPT-5.6 Sol, and the open-weight Gemma 3 12B, with 100 executions per model. MARQ achieves median F1 scores of 0.80 for Claude Opus 5, 0.62 for GPT-5.6 Sol, and 0.53 for Gemma 3 12B, compared with off-the-shelf baselines of 0.55, 0.52, and 0.18, respectively. However, the nature of these gains is model-dependent. Claude Opus 5 improves defect detection and false-alarm control; GPT-5.6 Sol gains detection and better execution-level consistency at the cost of more false alarms; and Gemma 3 12B reaches the performance of off-the-shelf proprietary models, although it remains highly variable. Criterion-level analysis shows gains concentrated in Correctness and Conformance, trade-offs between misses and false alarms within individual criteria, and model-dependent responses across several criteria. These findings position SE knowledge infusion as a promising model-agnostic pathway for strengthening trustworthy LLM-based RE support while underscoring the need for criterion-specific interventions and human-in-the-loop review.

中文摘要

摘要：需求工程（RE）是系统工程（SE）的基础，因为需求缺陷可能向下游传播，并对开发结果产生不利影响。尽管大型语言模型（LLM）在需求质量评估方面具有潜力，但已有研究表明，现成模型遗漏了大量专家识别的缺陷，在不同质量标准上的表现不均，并且执行结果存在波动。本研究探讨了注入专家衍生的SE知识能否在现成模型的基础上提升基于LLM的需求质量评估。我们提出了MARQ，一种模块化、LLM无关的原型，它通过特定标准的知识栈补充LLM，实现了INCOSE需求质量标准，并在专家标注的NASA需求集上使用Claude Opus 5、GPT-5.6 Sol以及开源权重的Gemma 3 12B进行了评估，每个模型执行100次。MARQ实现的中位F1分数分别为Claude Opus 5的0.80、GPT-5.6 Sol的0.62和Gemma 3 12B的0.53，而现成模型的基线分别为0.55、0.52和0.18。然而，这些提升的性质依赖于模型。Claude Opus 5在缺陷检测和误报控制方面有所改善；GPT-5.6 Sol在检测率和执行级一致性方面取得提升，但代价是更多的误报；Gemma 3 12B达到了现成专有模型的性能，尽管仍然波动较大。按标准分析显示，提升集中在正确性和符合性上，单个标准内存在遗漏与误报的权衡，并且在多个标准上表现出模型依赖的响应。这些发现表明，SE知识注入是一条有前景的、与模型无关的途径，可增强可信的LLM需求工程支持，同时强调了对特定标准的干预和人工参与审查的必要性。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36234

Authors: Jannatul Shefa, Alejandro Salado, Paul Wach, Taylan G. Topcu

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.36234.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36234

Published: 2026-10-28T02:34:59.553Z

Evaluation Domain Papers

1. Counting the Bandages: On measuring the time that AI saves

中文摘要

摘要：我思考了人工智能辅助节省时间意味着什么。我对比了两种观点：一种是秒表视角，即节省的时间就是时钟记录的时间；另一种是账本视角，即节省的时间是一个反事实，必须与工作中漏掉的错误一起衡量，我支持后者。论证分为四部分。我定义了一对不依赖模型的量：节省时间和额外漏过缺陷，并由此构建一个决策数值：收支平衡缺陷成本。我给出了一种检查基线模型，其中，直到模型足够好无需检查前，校准员工的漏缺陷率不依赖于模型的好坏；检查时间随模型错误率的对数增长；过度信任可以在时钟上节省分钟，但总体时间成本更大。我展示了随机研究能识别和不能识别的内容，并从公开数据中复制了METR的开发者研究：相同的246个问题根据估计量支持19%或24%的减速（未调整偶然不平衡时为34%），AI在其中的帮助比例介于3%到82%之间。最后，我重新陈述了已发表的记录，用声明的界限替代导入的点假设。在GDPval自身的“审查每一输出”工作流程中，仅审查时间就将GPT-5的加速上限限制在3.6倍；边界以外的顾问速度更快，但错误更多。最后，我在一项小型的预先设定实验中测试了模型的两个预测，实验涉及AI审查员检查由AI起草的相同类型的简报，这些简报基于模型训练数据收集后的SEC文件。当告知起草者的真实错误率时，审查者随着错误率上升而增加检查次数，但表现出全有或全无的模式，在提示成本达到收支平衡处切换。当告知起草者的错误率比实际低十倍时，审查者少检查了9个图中的7个，并在22.5%的简报中放过一个错误图，而不是完全零错误：速度更快且更糟，完全是因为减少了投入的努力。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.35942

Authors: Solomon Shalom Lijo

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.35942.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.35942

Published: 2026-10-28T02:35:26.857Z

2. Enhancing Deep Learning Model Performance through Data Generation Strategies: Classification of Olive Tree Diseases

中文摘要

摘要：深度学习模型在广泛的领域中表现出极高的有效性，尤其是在植物疾病诊断中。然而，它们的性能往往受到数据不足和类别不平衡等挑战的限制。在我们的工作中，我们提出了一种全面的数据生成策略以克服这些限制。首先，我们应用各种数据生成技术，包括传统的数据增强方法、CutMix、MixUp，以及使用深度卷积生成对抗网络（DCGANs）生成的合成图像，来创建新的数据样本。其次，我们在三种场景中利用这些生成的数据：(S1) 平衡原始数据集中的类别分布，(S2) 增加每个类别的样本数量，(S3) 在保持类别平衡的同时扩展数据集。第三，我们使用预训练和微调权重的EfficientNetV2B0架构评估这些数据分布（S1、S2、S3）对模型性能的影响。实验结果显示分类准确率有显著提高，强调了数据多样性和类别平衡的重要作用。这些发现突出了所提出的数据生成与分布策略在提升数据集质量方面的有效性和适应性，具有在植物疾病检测和精准农业中应用的良好前景。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.35984

Authors: Hicham El Akhal, Abderrahim Waga, Aissa Ben Yahya, Abdelbaki El Belrhiti El Alaoui

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.35984.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.35984

Published: 2026-10-28T02:35:26.857Z

3. The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents

中文摘要

摘要：多模态智能可以被视为通过交互实现的世界与智能体之间的人类引导共进化。然而，这一过程的扩展面临两个瓶颈：构建异质且可验证的环境成本高昂，以及手动开发的迭代无法跟上任务多样性和复杂度的增长。一个关键见解是，不同模态和表面形式的任务可以共享相同的底层能力需求。因此，我们引入了“三位一体”（The Trinity），这是一个递归自我改进框架，通过三种角色——创造者（Creator）、探索者（Explorer）和进化者（Evolver）——将世界生成与开发迭代相结合。基于经过验证的执行轨迹，Evolver 将任务组织的基础从表面类别转向共享能力需求，把原始任务树重新组织为分层能力树。我们提出了“能力驱动的 Real2Sim2Real”：对于同一节点下的异质任务，创造者将它们的共同需求抽象为简化、可验证的模拟世界用于能力学习，同时在原始任务上的评估衡量迁移效果。沿着这棵能力树，探索者通过选择性继承逐步进化可复用的能力模块，形成一个开发树，在固定拓扑内验证的更新会在迭代中累计。生成的开发模块在不同能力上实现了专门化，从而促使形成“能力感知开发路由器”，利用公共任务信息从树中选择兼容的模块配置。我们进化出的开发模块在28个训练基准上的平均性能提升了34个点，在18个未见基准上提升了26个点，包括两个真实世界的具身任务。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36077

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.36077.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36077

Published: 2026-10-28T02:35:26.857Z

4. CohortFlow: A Steerable Clinical Cohort Curation Agent with Localized Semantic Correction

中文摘要

摘要：用于临床队列策展的语言模型代理应能适应不断变化的资格标准，而无需反复处理未更改的要求。我们引入了CohortFlow，一种可引导的代理，它将自然语言修正表示为对结构化队列规范的局部更新，并将其与持久的执行图进行协调。明确记录的语义依赖关系使受影响的计算能够被选择性地作废，同时保留有效的先前结果。在基于临床试验资格标准的100个场景（共126轮修正）上，局部引导在要求微观F1上实现了77.0%，而使用相同8B模型的完全重新生成为76.4%，这一小幅数值优势在统计上并不显著（$p=0.493$）。它在完成后将平均修正延迟降低了64.8%，在执行过程中降低了44.3%，并减少了38.1%的模型调用。在对MIMIC进行的另一个概念验证评估中，所有13个队列状态均成功执行，同时修正轨迹展示了对未受影响计算的选择性保留以及对更改或相关节点的重新计算。综上所述，这些结果表明，局部语义引导可以在保持较高要求级准确性的同时，大幅减少修正延迟和模型调用。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36100

Authors: Neil Chen, Adrian Serapio, Hanxue Gu, Evan Lee, Kang Wang, Yang Yang

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.36100.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36100

Published: 2026-10-28T02:35:26.857Z

5. Why and How to Do Science When AI Is Better at It: A Framework Grounded in Human Understanding and Direction

中文摘要

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36116

Authors: Hoda Heidari, Aydin Mohseni

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.36116.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36116

Published: 2026-10-28T02:35:26.857Z

6. From Structural Feedback to Prompt Policies: Learning Faithful Text-to-Image Prompt Editors

中文摘要

摘要：提示优化应在不改变用户所请求场景的情况下改善用户收到的图像。然而，即使全局文本—图像相似度保持高水平，风格化重写也可能削弱对象属性和关系。我们提出了 StruPO，一种结构感知的提示编辑器，它使用校准后的场景图作为策略条件和基于图像监督的共享表示。该图揭示了应保留的内容，而删除、重排和插入提供了一种与令牌对齐的方式来修改提示。这将来自外部批评的结构反馈转化为可重用编辑策略的训练信号。从该信号学习需要处理不确定的基础关系和随机图像生成。StruPO 通过平滑奖励塑造保持基础关系的信心，并在计算群体相对优势之前对每次编辑的多张图像求平均值。实验涵盖三个不相交的 2000 条提示测试集和四个固定生成骨干，并与学习型提示优化器、迭代结构反馈、扩散模型微调以及推理时注意力控制进行比较。StruPO 改善了忠实度与美学的折衷，在关系保真度上表现出一致提升。独立的自动评估器和 15 名标注者的研究提供了补充证据，且随着关系复杂度增加，人类偏好差距也随之增大。受控消融实验将这些提升与图条件、本地编辑和基于图像的学习联系起来。由此产生的策略在图校准后即可一次性生成可重用的优化文本，无需迭代的批评—重写循环。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36146

Authors: Wentao Ye, Yali Ye, Zhiqing Xiao, Ru Peng, Xinpeng Ti, Liyao Li, Zhanming Shen, Peng Lu, Jie Zhang, Haobo Wang

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.36146.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36146

Published: 2026-10-28T02:35:26.857Z

7. Don’t Pick a Winner: Knowledge Conflicts Need a Prior, Not a Rule

中文摘要

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36169

Authors: Minh Pham Van, Cong Tran

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.36169.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36169

Published: 2026-10-28T02:35:26.857Z

8. Learning Human Sports Motion Feasibility via Quantile Regression on Tracking Data

中文摘要

摘要：我们研究体育运动中的到达时间（TTA）：基于球员当前的运动学状态到达场上任意位置所需的最短可行时间，该时间估计为观测到的运动时间的下包络。与其通过位置密度估计或基于物理的封闭形式模型来建模空间占有，我们将TTA视为条件分位数回归问题，估计运动时间的下分位数，使模型学习球员的下包络到达时间。我们在PFF FC 2022年FIFA世界杯数据集中所有64场比赛的光学跟踪数据上训练该模型，并将一个轻量级多层感知机与文献中的六种球员运动模型（重新表达为TTA预测器）以及一个学习到的可达外壳基线进行评估。在我们的评价指标中，MLP始终优于所有基于物理的基线。为了探讨所学习的运动模型的通用性，我们进一步在篮球跟踪数据和单场NFL跟踪数据上进行了评估，分析球员运动动力学在不同运动之间的可迁移性。我们的项目可通过此https网址获得。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36183

Authors: Marc Gutiérrez-Pérez, Antonio Agudo

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.36183.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36183

Published: 2026-10-28T02:35:26.857Z

9. Skill Dreaming: Evolving Repository Skills through Pull Request Streams

中文摘要

摘要：大型语言模型（LLM）代理越来越依赖可重复使用的技能来完成复杂的软件工程任务，这使得技能库对于代码库的开发和维护至关重要。然而，特定代码库的技能必须随着代码结构、实现约定和维护需求的变化而发展。拉取请求（PR）提供了这种知识的自然来源，因为它记录了代码库通过实现和审查如何演变。与此同时，新的PR必须遵循特定代码库的实现模式，一致地修改相关组件，并确保在添加新功能覆盖的同时，现有测试仍能通过。这形成了一个相互促进的循环：PR为更新技能提供知识，而这些技能又改善了未来的PR，维护代码库，并支持技能的进一步演变。为了实现PR、代码库和技能的共同进化，我们提出了Skill Dreaming，这是一个从PR流中学习以指导持续代码库开发和维护的框架。给定一个代码库及其PR历史，Skill Dreaming通过从经过验证的PR中提取可执行知识构建特定代码库的技能库，并在新PR信息可用时不断完善这些技能。这些技能不仅指导编码代理实现请求的功能，还指导其维护相关测试、文档、兼容性和代码库约定。通过整合PR分析、技能管理、代码执行和持续集成，Skill Dreaming提供了一个端到端的工作流程，用于将学到的技能应用于代码库变更，并将后续PR结果纳入未来的技能更新中。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36188

Authors: Xinyuan Song, Hasibul Haque, Jay Somasundaram, Ryan Turner, Bowen Zhu, Liang Zhao

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.36188.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36188

Published: 2026-10-28T02:35:26.857Z

10. MARQ: A Modular, LLM-Agnostic Requirement Quality Assessor Infused with Systems Engineering Knowledge

中文摘要

摘要：需求工程（RE）是系统工程（SE）的基础，因为需求缺陷可能向下游传播，并对开发结果产生不利影响。尽管大型语言模型（LLM）在需求质量评估方面具有潜力，但已有研究表明，现成模型遗漏了大量专家识别的缺陷，在不同质量标准上的表现不均，并且执行结果存在波动。本研究探讨了注入专家衍生的SE知识是否能够在现成模型的基础上提升基于LLM的需求质量评估。我们提出了MARQ，一种模块化、LLM无关的原型，它通过特定标准的知识栈补充LLM，实现了INCOSE需求质量标准，并在专家标注的NASA需求集上使用Claude Opus 5、GPT-5.6 Sol以及开源权重的Gemma 3 12B进行了评估，每个模型执行100次。MARQ实现的中位F1分数分别为Claude Opus 5的0.80、GPT-5.6 Sol的0.62和Gemma 3 12B的0.53，而现成模型的基线分别为0.55、0.52和0.18。然而，这些提升的性质依赖于模型。Claude Opus 5在缺陷检测和误报控制方面有所改善；GPT-5.6 Sol在检测能力和执行级一致性方面取得提升，但代价是更多的误报；Gemma 3 12B达到了现成专有模型的性能，尽管仍然波动较大。按标准分析显示，提升集中在正确性和符合性上，单个标准内存在遗漏与误报的权衡，并且在多个标准上表现出模型依赖的响应。这些发现表明，SE知识注入是一条有前景的、与模型无关的途径，用于增强可信赖的基于LLM的RE支持，同时强调了针对特定标准的干预和人工参与审查的必要性。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36234

Authors: Jannatul Shefa, Alejandro Salado, Paul Wach, Taylan G. Topcu

Categories: cs.AI

PDF URL: https://arxiv.org/pdf/2610.36234.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36234

Published: 2026-10-28T02:35:26.857Z

VLM Domain Papers

1. ObjectTwin: Measuring the Asset Correspondence Gap for Capture-Anchored Digital Twins

Abstract:Object-wise reconstruction increasingly inserts generated meshes into captured scenes as editable proxies for observed objects. This use creates a requirement absent from isolated-asset scores and pose estimates: at the captured metric state, the proxy should reproduce calibrated observations of the same instance. We present ObjectTwin, a scan-grounded measurement protocol that freezes the instance, cameras, scan-projected support and recorded depth, metric anchor, and evaluation denominator, then replaces only the object representation. The resulting asset correspondence gap measures lost observation agreement relative to scan-derived visible geometry without treating the scan as complete physical ground truth. Across two indoor RGB-D capture domains and two generation backends, visible, anchored generated assets lose 0.302-0.497 MaskIoU under this replacement. Every tested scene-level estimate is positive, while same-input generator preference reverses across capture domains. Coverage and overlap-depth analyses locate disagreement in both visible support and surface placement; the evaluated conservative pose refinement does not systematically recover it. These results establish capture correspondence as a separately measurable interface between generated-asset quality and stronger physical or task-level evaluation.

中文摘要

摘要：面向对象的重建越来越多地将生成的网格插入捕获的场景中，作为可编辑的代理来表示观测到的对象。这种使用方式产生了一种在孤立资产评分和姿态估计中不存在的需求：在捕获的度量状态下，代理应当重现同一实例的校准观测。我们提出了ObjectTwin，这是一种基于扫描的测量协议，它固定实例、相机、扫描投影支撑和记录的深度、度量锚点以及评估分母，然后仅替换对象表示。由此产生的资产对应差距衡量了相对于扫描生成的可见几何体丢失的观测一致性，同时不将扫描视为完整的物理真实。跨越两个室内RGB-D捕获域和两个生成后端，在这种替换下，可见、有锚点的生成资产的MaskIoU损失为0.302-0.497。每个测试的场景级估计都是正值，而相同输入的生成器偏好在不同捕获域间发生反转。覆盖率和重叠深度分析表明分歧存在于可见支撑和表面放置中；评估的保守姿态优化并未系统地恢复它。这些结果确立了捕获对应作为生成资产质量与更强的物理或任务级评估之间可单独测量的接口。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.35904

Authors: Zhenghe Guo

Categories: cs.CV

PDF URL: https://arxiv.org/pdf/2610.35904.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.35904

Published: 2026-10-28T02:35:56.405Z

2. Task-Utility IQA: Rethinking Image Quality Assessment in Embodied Tasks

Abstract:Image quality assessment (IQA) underpins embodied imaging pipelines by judging whether visual quality satisfies downstream tasks, yet most existing methods learn task-agnostic scores aligned with generic human ratings on static benchmarks. This objective mismatches embodied and interactive settings, where image adequacy depends on task goals, context, and action requirements that shape an agent’s decisions. We argue that IQA should shift from score regression to goal-conditioned judgment defined by embodied task utility. To this end, we propose an MLLM-based embodied IQA agent framework that reasons about task requirements, grounds quality evidence, and produces decision-facing assessments. A compact VisDrone evidence study shows that conventional perceptual metrics and generic MLLM-based IQA scores are weak proxies for downstream VLM task success, while a task-conditioned utility score better predicts whether visual input supports the target task. These findings support a task-utility-oriented reframing of IQA for embodied, explainable, and decision-aware visual perception.

中文摘要

摘要：图像质量评估（IQA）通过判断视觉质量是否满足下游任务，支撑了具身成像流程。然而，大多数现有方法学习与静态基准上的通用人类评分一致的任务不可知分数。这一目标与具身和交互式环境不匹配，在这些环境中，图像的适用性取决于任务目标、上下文以及影响智能体决策的操作需求。我们认为，IQA 应该从分数回归转向由具身任务效用定义的目标条件判断。为此，我们提出了一个基于 MLLM 的具身 IQA 智能体框架，该框架能够推理任务需求、建立质量证据，并生成面向决策的评估。一个紧凑的 VisDrone 证据研究表明，传统的感知指标和通用 MLLM 基于 IQA 的分数对于下游 VLM 任务的成功预测能力较弱，而任务条件效用分数则能够更好地预测视觉输入是否支持目标任务。这些发现支持将 IQA 重新框定为以任务效用为导向的具身、可解释和决策感知的视觉感知方法。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.35905

Authors: Jirong Zha, Yanwei Liao, Yemin Wang, Xiangmin Yi, Siqi Peng, Yingfeng Chen, Chen Gao, Xinlei Chen

Categories: cs.CV

PDF URL: https://arxiv.org/pdf/2610.35905.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.35905

Published: 2026-10-28T02:35:56.405Z

3. Physiognomy Revisited: How Vision-Language Models Encode Sensitive Attributes Through Image Transformation

Abstract:Emergent generative AI technologies, while remarkably beneficial across several tasks and domains, can suffer from unforeseen vulnerabilities and difficult-to-anticipate failure modes. Such failure modes can disparately affect vulnerable communities. This paper investigates two well-known vision language models (VLMs) and inspects how these models encode protected identities while generating images. We show that when VLMs are requested to transform human face images to reflect race identities (e.g., Hispanic, Black, White, or Asian) and sexual orientation (e.g., gay or straight), VLMs often comply with such requests. We demonstrate that compliance (and refusal) is non-deterministic, group-sensitive, and generated images are statistically distinguishable, often accentuating deep-seated stereotypes. We further show that representation biases introduced during image generation can re-emerge in textual reasoning and characterization tasks. Finally, we show that this worrisome finding is not limited to racial identity or sexual orientation, image generation can perpetuate bias around criminality, raising concerning possibilities of AI-assisted profiling.

中文摘要

摘要：新兴的生成型人工智能技术虽然在多个任务和领域中具有显著的益处，但可能存在不可预见的脆弱性和难以预测的失败模式。这些失败模式可能会对弱势群体产生不同程度的影响。本文研究了两种知名的视觉语言模型（VLMs），并检查这些模型在生成图像时如何编码受保护的身份信息。我们显示，当VLM被要求将人脸图像转换以反映种族身份（例如，西班牙裔、黑人、白人或亚洲人）和性取向（例如，同性恋或异性恋）时，VLM通常会遵从这样的请求。我们证明，遵从（以及拒绝）是非确定性的、群体敏感的，并且生成的图像在统计上是可区分的，常常加深根深蒂固的刻板印象。我们进一步展示，在图像生成过程中引入的表征偏差可以在文本推理和特征描述任务中重新出现。最后，我们表明，这一令人担忧的发现不限于种族身份或性取向，图像生成还可能延续关于犯罪的偏见，引发了人工智能辅助画像的令人关注的可能性。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.35910 (HTTP 429)

Authors: Soumyajit Datta, Arka Dutta, Ashiqur R. KhudaBukhsh

Categories: cs.CV

PDF URL: https://arxiv.org/pdf/2610.35910.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.35910

Published: 2026-10-28T02:35:56.405Z

4. Learning and Reasoning with Geometry: How Generation Helps Spatial Understanding

Abstract:Image and video generators can produce spatially consistent visual content, but how to use this capability to improve spatial understanding remains underexplored. We study this problem from two perspectives: geometric supervision during training and explicit geometric evidence during inference. To this end, we introduce a unified geometric understanding and generation model (GeoUG) that integrates depth and multi-view generation with spatial understanding. First, we design a multi-scale depth codec that enables metric-depth generation using a pretrained visual autoencoder, and show that joint training yields task-dependent gains in spatial understanding. Second, we introduce 3DCueBench to control geometric difficulty while balancing selected 2D cues, and find that generated depth provides larger reasoning gains on questions requiring fine-grained geometric discrimination. Building on this finding, we develop adaptive interleaved reasoning, in which GeoUG first drafts an answer and then decides whether to generate geometric evidence to confirm or revise it. We train this decision through reinforcement learning, balancing accuracy gains over retaining the draft against generation cost. GeoUG achieves circular accuracies of 97.9%, 90.8%, and 94.2% on CV-Bench-3D, 3DCueBench, and DA-2K with fewer generation calls than always generating.

中文摘要

摘要：图像和视频生成器可以生成空间一致的视觉内容，但如何利用这种能力来提升空间理解仍未被充分研究。我们从两个角度研究这个问题：训练期间的几何监督和推理期间的显式几何证据。为此，我们提出了一个统一的几何理解与生成模型（GeoUG），将深度和多视图生成与空间理解相结合。首先，我们设计了一个多尺度深度编码器，使其能够使用预训练视觉自编码器生成度量深度，并表明联合训练可以在空间理解任务中带来依赖任务的收益。其次，我们引入了3DCueBench，用以在控制几何难度的同时平衡选定的二维线索，并发现生成的深度在需要细粒度几何区分的问题上提供了更大的推理收益。基于这一发现，我们开发了自适应交错推理，其中GeoUG首先起草答案，然后决定是否生成几何证据以确认或修正答案。我们通过强化学习训练这一决策，在保留草稿带来的准确性提升与生成成本之间进行平衡。GeoUG在CV-Bench-3D、3DCueBench和DA-2K上的循环准确率分别达到97.9%、90.8%和94.2%，所需生成调用次数少于始终进行生成的方法。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36022

Authors: Rui Yang, Yanwei Li, Sili Chen, Jingjia Huang, Yi Lin, Hengshuang Zhao

Categories: cs.CV

PDF URL: https://arxiv.org/pdf/2610.36022.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36022

Published: 2026-10-28T02:35:56.405Z

5. Any3R: Feedforward 3D Reconstruction from Any Camera Type

Abstract:Geometry foundation models recover camera poses and dense geometry from a set of images with a feed-forward network, but they expect pinhole images. That assumption is inside the backbone too: the positional encoding and the training loss both bind an image position to a direction in space, and both depend on the lens. We condition both on the dense ray field, the unit direction through every pixel, which describes any central camera without a lens type, distortion coefficients or a bound on field of view. Angular coordinates give the rotary encoding the measured ray angle of each patch, evaluated per view, and solid-angle weighting scales the point loss by the area each pixel covers on the sphere, so neither the encoding nor the supervision depends on the lens. Any3R is therefore a feed-forward model that takes any central camera, and is robust to mixing many camera types per scene, with no retraining per lens. On a benchmark of thirteen central cameras across three datasets, where every method reconstructs with its own predicted camera poses, it is the most consistently accurate method. Any3R enables scalable 3D reconstruction from heterogeneous crowdsourced and archival imagery collections sourced across diverse camera types. Project page: this https URL

中文摘要

摘要：几何基础模型通过前馈网络从一组图像中恢复相机姿态和稠密几何，但它们假定使用针孔图像。这一假设也存在于主干网络中：位置编码和训练损失都将图像位置绑定到空间中的方向，并且都依赖于镜头。我们将两者都以稠密光线场为条件，该光线场是穿过每个像素的单位方向，能够描述任何中心相机，而无需考虑镜头类型、畸变系数或视场限制。角坐标为旋转编码提供每个视图中每个块测量的光线角度，固体角加权根据每个像素在球面上覆盖的面积调整点损失，因此编码和监督都不依赖于镜头。因此，Any3R 是一个前馈模型，可以处理任何中心相机，并且在每个场景混合多种相机类型时具有鲁棒性，无需针对每个镜头进行再训练。在包含三组数据集共十三台中心相机的基准测试中，每种方法都用其预测的相机姿态进行重建，Any3R 是最稳定且准确的方法。Any3R 使得从异构众包和档案影像集合进行可扩展的 3D 重建成为可能，这些影像来自多种相机类型。项目页面：此 https URL

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36150

Authors: Jingong Chen, Qingwen Zhang, Youming Deng, Chulwoo Pack, Olaf Wysocki, Boris Jutzi, Kwanghee Won, Kyle Gao

Categories: cs.CV

PDF URL: https://arxiv.org/pdf/2610.36150.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36150

Published: 2026-10-28T02:35:56.405Z

6. PrinGS: Privacy Preservation in Gaussian Splatting

Abstract:3D Gaussian Splatting (3DGS) has rapidly become the preferred representation for high-fidelity novel view synthesis and 3D scene reconstruction. However, the learned representation encodes sensitive visual information including human faces, license plates, documents, and computer screens, raising significant privacy concerns when trained splats are shared or deployed. In this work, we address the underexplored problem of privacy preservation in Gaussian Splatting by proposing a representation-level anonymization framework that directly anonymizes a trained splat. Given a trained splat and a user-provided reference view identifying sensitive content, our method localizes the corresponding regions in the underlying 3D representation and directly anonymizes them, ensuring that the sensitive information is absent from all subsequently rendered novel views while preserving the overall scene geometry and visual fidelity. We achieve this post-training anonymization in less than 1 second. Furthermore, we extend our framework with a privacy-by-design training strategy that prevents sensitive content from being embedded into the representation during optimization, enabling the generation of privacy-preserving splats directly from training images. Our method achieves a remarkably low Face Similarity Measure (FSM) of 9.79% at a retained Face Detection Rate (FDR) of 39.47% and makes sensitive text completely unreadable with an OCR Character Error Rate of 1.00. Our work aims to serve as the primary stepping stone towards privacy-aware 3D representations and motivates further research along these directions.

中文摘要

摘要：三维高斯点绘（3D Gaussian Splatting，3DGS）迅速成为高保真新视角合成和三维场景重建的首选表示方法。然而，所学习的表示会编码敏感的视觉信息，包括人脸、车牌、文档和电脑屏幕，当训练好的点绘被共享或部署时，会引发严重的隐私问题。在本工作中，我们针对高斯点绘中尚未充分探索的隐私保护问题，提出了一种表示级匿名化框架，可直接对训练好的点绘进行匿名化。给定训练好的点绘和用户提供的标识敏感内容的参考视图，我们的方法能够在底层三维表示中定位对应区域并直接对其进行匿名化，从而确保所有随后的新视角渲染中不包含敏感信息，同时保持整体场景几何和视觉保真度。我们在不到1秒的时间内实现了这种训练后匿名化。此外，我们还扩展了框架，引入隐私设计的训练策略，防止敏感内容在优化过程中被嵌入表示中，从而可以直接从训练图像生成具备隐私保护功能的点绘。我们的方法在保留人脸检测率（FDR）39.47%的情况下，实现了显著低的人脸相似度度量（FSM）9.79%，并使敏感文字完全无法读取，OCR字符错误率为1.00。我们的工作旨在作为面向隐私的三维表示的主要起点，并激励在该方向上进行进一步研究。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36168 (HTTP 429)

Authors: Gaurav Behera, Abhinav Raundhal, Archisha Panda, Saumya Balina, Gargi Shroff, Ponnurangam Kumaraguru

Categories: cs.CV

PDF URL: https://arxiv.org/pdf/2610.36168.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36168

Published: 2026-10-28T02:35:56.405Z

7. Beyond the Estimate: Wiener-Informed Decoding for Easier Training of Pixel-Space Flow Models

Abstract:Learning velocity fields directly in pixel space is difficult and slow. We show that coarse second-order image statistics can ease this task: frozen Wiener estimates improve velocity learning, with gains extending beyond the linear predictions they explicitly provide. Moreover, we observe similar but complementary gains from frozen bases and pixel decoding. These observations motivate Wiener-informed Decoding (WiD), which uses statistical knowledge both for direct prediction and to organize decoder computation without modifying native blocks. WiD combines a trainable Wiener prediction path with coefficient interfaces that inject features into the native decoder and return its predicted coefficient corrections, with these components initialized with data statistics. All introduced parameters, including the spectrum and coordinate transforms, are trained jointly under the original pixel-space velocity objective. Across model scales and decoder architectures, WiD accelerates training and improves generation quality with modest parameter overhead. It also yields smoother gradient trajectories and remains effective with representation alignment. WiD improves class-conditional and text-to-image generation across different resolutions. On ImageNet 256 x 256, PixelDiT-XL with WiD reaches FID 1.53 after 500 epochs, achieving comparable quality to PixelDiT with 37.5% fewer training epochs. Statistical denoisers contribute beyond the estimate: their computational structure can also ease pixel-space training.

中文摘要

摘要：在像素空间中直接学习速度场既困难又缓慢。我们表明，粗略的二阶图像统计可以简化这一任务：冻结的维纳估计能够改善速度学习，其收益超出了它们所明确提供的线性预测。此外，我们观察到来自冻结基和像素解码的类似但互补的收益。这些观察促使提出了维纳信息解码（WiD），它利用统计知识既用于直接预测，也用于组织解码器计算，而无需修改原生模块。WiD 将可训练的维纳预测路径与系数接口相结合，这些接口将特征注入原生解码器并返回其预测的系数修正，并且这些组件以数据统计初始化。所有引入的参数，包括频谱和坐标变换，均在原始像素空间速度目标下共同训练。在不同的模型规模和解码器架构下，WiD 提升了训练速度并提高了生成质量，同时参数开销适中。它还产生了更平滑的梯度轨迹，并在表示对齐下仍然有效。WiD 提高了不同分辨率下的类别条件和文本到图像的生成质量。在 ImageNet 256 x 256 上，带有 WiD 的 PixelDiT-XL 在 500 个训练周期后达到 FID 1.53，实现了与 PixelDiT 相当的质量，同时训练周期减少了 37.5%。统计去噪器的贡献不仅限于估计：它们的计算结构也可以简化像素空间的训练。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36192

Authors: Ziqiao Wang, Yang You

Categories: cs.CV

PDF URL: https://arxiv.org/pdf/2610.36192.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36192

Published: 2026-10-28T02:35:56.405Z

8. Learning to Read Braille: Benchmarking and Improving Braille Recognition Capabilities of VLMs

Abstract:Despite rapid progress in visual understanding and document transcription, modern vision-language models (VLMs) struggle with a fundamental accessibility task: reading Braille from images. We introduce BrailleBench, a manually curated benchmark of 259 real-world Grade-1 and Grade-2 Braille images. We evaluate proprietary, open-weight, OCR-specialized, and tool-assisted multimodal systems and find that standalone general-purpose models perform poorly at directly transcribing Braille images, whereas tool-assisted systems perform much better. We design a synthetic Braille generation pipeline with diverse layouts and image perturbations. A 2B VLM model trained on our synthetic data reaches 87% exact match on Grade-1 and 61% on Grade-2 BrailleBench, outperforming standalone VLMs and achieving the highest Grade-2 exact match score among the evaluated systems. We further show that high accuracy on synthetic validation data does not guarantee high accuracy on real photographs in our experiments: models trained on prior synthetic data reach up to 96% on their synthetic validation set but at most 3.26% on Grade-1 BrailleBench. Our results identify an accessibility-relevant capability gap in multimodal systems and show that targeted synthetic supervision can improve real-world Braille transcription.

中文摘要

摘要：尽管在视觉理解和文档转录方面取得了快速进展，现代视觉-语言模型（VLMs）在一项基本的可访问性任务上仍存在困难：从图像中读取盲文。我们引入了BrailleBench，这是一个手工整理的、包含259张真实世界一级和二级盲文图像的基准数据集。我们评估了专有模型、开放权重模型、OCR专用模型以及工具辅助的多模态系统，发现独立的通用模型在直接转录盲文图像方面表现不佳，而工具辅助系统表现则好得多。我们设计了一个具有多样布局和图像扰动的合成盲文生成流程。在我们的合成数据上训练的2B VLM模型在BrailleBench一级盲文上达到87%的完全匹配率，在二级盲文上达到61%，超过了独立VLM模型，并在评估系统中取得了最高的二级盲文完全匹配分数。我们进一步展示了在实验中，在合成验证数据上的高准确率并不能保证在真实照片上的高准确率：在先前合成数据上训练的模型在其合成验证集上最高可达96%，但在BrailleBench一级盲文上的最高准确率仅为3.26%。我们的结果揭示了多模态系统在可访问性相关能力上的差距，并表明针对性的合成监督可以改善真实世界的盲文转录性能。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36195

Authors: Kartik Jangra, Atharva Gawane, Siddharth Pulipaka, Hemachandran Karah, Raj Dabre

Categories: cs.CV

PDF URL: https://arxiv.org/pdf/2610.36195.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36195

Published: 2026-10-28T02:35:56.405Z

9. UT-HMR: Uncertainty-Guided Temporal Modeling for Robust 3D Human Mesh Recovery

Abstract:Monocular 3D human mesh recovery (HMR) remains unreliable under weak observations caused by long camera-to-person distances, occlusion, and motion blur. In challenging scenarios such as sports, these factors make the problem highly ambiguous, as different 3D poses may yield similar 2D projections. This ambiguity is especially severe for one-stage HMR, which recovers all meshes directly from the full image without person crops or external 2D cues. To handle this ambiguity, we present UT-HMR ( Uncertainty-guided Temporal HMR), to our knowledge the first one-stage HMR framework to capture correlated pose uncertainty across joints. Each person query predicts a Gaussian distribution over the full SMPL pose with a compact low-rank-plus-diagonal covariance, which is converted into joint-wise precision weights for heteroscedastic supervision while keeping inference deterministic. Temporal early fusion further injects neighboring-frame evidence before pose decoding, supplying the visual evidence needed to resolve the ambiguity that the uncertainty captures. With a lightweight ViT-B backbone, UT-HMR achieves state-of-the-art results on VIP-HockeyPose-v2 (ice hockey) and WorldPose (soccer), reducing MPJPE, PA-MPJPE, and PVE by up to 4.7%, 3.8%, and 5.6%, and remains competitive on 3DPW against methods with larger backbones and higher input resolutions.

中文摘要

摘要：单目三维人体网格重建（HMR）在摄像机与人物距离过远、遮挡和运动模糊导致的弱观测下仍然不可靠。在体育等具有挑战性的场景中，这些因素使问题高度模糊，因为不同的三维姿态可能产生相似的二维投影。这种模糊对于单阶段HMR尤为严重，单阶段HMR直接从完整图像恢复所有网格，而不需要人物裁剪或外部二维线索。为应对这种模糊，我们提出了UT-HMR（不确定性引导的时序HMR），据我们所知，这是首个能够捕捉关节间相关姿态不确定性的一阶段HMR框架。每个人物查询预测整个SMPL姿态的高斯分布，采用紧凑的低秩加对角协方差，并将其转换为关节精度权重，用于异方差监督，同时保持推理的确定性。时序早期融合在姿态解码前进一步注入邻帧证据，提供解决不确定性捕捉的模糊所需的视觉证据。借助轻量级ViT-B骨干网络，UT-HMR在VIP-HockeyPose-v2（冰球）和WorldPose（足球）上实现了最先进的结果，MPJPE、PA-MPJPE和PVE分别降低了最多4.7%、3.8%和5.6%，并且在3DPW上仍与使用更大骨干和更高输入分辨率的方法保持竞争力。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36203

Authors: Zhibo Wang, Sirisha Rambhatla, Yuhao Chen, Maria Koshkina, David Clausi

Categories: cs.CV

PDF URL: https://arxiv.org/pdf/2610.36203.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36203

Published: 2026-10-28T02:35:56.405Z

10. Diagnosing and Correcting Bias in MLLM for Long Video Understanding

Abstract:Long-video question answering is challenging since the answer often hinges on a few decisive moments scattered throughout the video, while memory constraints force Multimodal Large Language Models (MLLMs) to sample frames at extremely low rates, resulting in sparsity that risks omitting key evidence. Though aggressively enlarging the context size is intuitive, we argue that performance remains fundamentally constrained by the bias, \emph{i.e.}, the misleading cues caused by spurious \textit{linguistic} correlations and salient yet irrelevant \textit{visual} observations. In this paper, we first introduce {S-MME}, a benchmark designed to systematically diagnose shortcut-biased behavior in MLLMs. To mitigate this failure, we further propose a training-free framework, Counterfactual Long-video Evidence-Aware Reasoning (CLEAR). By treating the full video-question pair as a complete view, CLEAR estimates bias effects via augmented views by only keeping the question or locally salient visual clips. Then, we intervene hidden states to mitigate the discrepancy at inference such that the correct answer can be predicted confidently. With experimental studies across five benchmarks, we show that our method is generalizable and can be integrated in different MLLMs, yielding consistent gains in prediction and robustness. We hope CLEAR can offer a complementary direction in test-time scaling for long-video understanding.

中文摘要

摘要：长视频问答具有挑战性，因为答案通常依赖于散布在视频中的少数关键时刻，而内存限制迫使多模态大语言模型（MLLMs）以极低的帧率抽取视频帧，导致稀疏性，从而有遗漏关键证据的风险。尽管激进地扩大上下文大小是直观的做法，但我们认为性能仍然受到偏差的根本限制，即由虚假语言关联和显著但无关的视觉观察造成的误导性线索。在本文中，我们首先介绍了 {S-MME}，一个用于系统诊断 MLLMs 快捷偏差行为的基准。为了缓解这种失败，我们进一步提出了一个无需训练的框架：反事实长视频证据感知推理（CLEAR）。通过将完整的视频-问题对视为一个完整视图，CLEAR 通过增强视图估计偏差效应，仅保留问题或局部显著视觉片段。然后，我们在推理时干预隐藏状态以减轻差异，使正确答案能够自信预测。通过在五个基准上的实验研究，我们表明该方法具有通用性，能够集成到不同的 MLLMs 中，在预测和稳健性上产生一致的提升。我们希望 CLEAR 能为长视频理解的测试时扩展提供一个互补的方向。

LLM Analysis

LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.36210

Authors: Xusheng Liang, Jianqiao Sun, Hao Zhang, Yulei Niu, Hengshuang Zhao, Jiawei Ma

Categories: cs.CV

PDF URL: https://arxiv.org/pdf/2610.36210.pdf

CoolPaper URL: https://papers.cool/arxiv/2610.36210

Published: 2026-10-28T02:35:56.405Z