arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of Texas at Austin(得克萨斯大学奥斯汀分校)

共收录 1213
2510.24974 2025-12-03 cs.LG

Conformational Rank Conditioned Committees for Machine Learning-Assisted Directed Evolution

构象排名条件化委员会用于机器学习辅助的定向进化

Mia Adler, Carrie Liang, Brian Peng, Oleg Presnyakov, Justin M. Baker, Jannelle Lauffer, Himani Sharma, Barry Merriman

机构 * Pomona College(波莫纳学院) The University of Texas at Austin(德克萨斯大学奥斯汀分校) University of Cambridge(剑桥大学) University of California, Irvine(加州大学尔湾分校) University of California, Los Angeles(加州大学洛杉矶分校) Avery Bio Inc(艾维生物公司)

AI总结 构象排名条件化委员会框架通过深度神经网络委员会分离epistemic和构象不确定性,提升SARS-CoV-2抗体发现效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.15746 2025-12-03 cs.NE cs.AI

Neural Cellular Automata for ARC-AGI

神经细胞自动机用于ARC-AGI

Kevin Xu, Risto Miikkulainen

机构 * The University of Texas at Austin(德克萨斯大学奥斯汀分校)

AI总结 本文提出利用神经细胞自动机处理ARC-AGI中的抽象网格任务,通过梯度训练实现高效少样本泛化。

Comments 8 pages, 5 figures

Journal ref Proceedings of the ALIFE 2025: Ciphers of Life: Proceedings of the Artificial Life Conference 2025. ALIFE 2025: Ciphers of Life: Proceedings of the Artificial Life Conference 2025. Kyoto, Japan. (pp. 127-134)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.00596 2025-12-02 cs.IR cs.AI

DLRREC: Denoising Latent Representations via Multi-Modal Knowledge Fusion in Deep Recommender Systems

DLRREC: 通过深度融合多模态知识在深度推荐系统中进行潜在表示去噪

Jiahao Tian, Zhenkai Wang

机构 * Georgia Institute of Technology(佐治亚理工学院) The University of Texas at Austin(德克萨斯大学奥斯汀分校)

AI总结 DLRREC通过深度融合多模态和协同知识,提升深度推荐系统中潜在表示的去噪能力,从而实现更精确的推荐性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.22150 2025-12-02 cs.LG cs.CL cs.IR

From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures

从拓扑到检索:利用统一签名解码嵌入空间

Florian Rottach, William Rudman, Bastian Rieck, Harrisen Scells, Carsten Eickhoff

机构 * University of Tübingen(图宾根大学) Fribourg University(弗里堡大学) Boehringer Ingelheim GmbH, Biberach (Riss), Germany(勃林格殷格翰公司) The University of Texas at Austin(德克萨斯大学奥斯汀分校)

AI总结 本文提出统一拓扑签名框架,用于全面表征文本嵌入空间,揭示模型架构驱动的相似性,并通过拓扑结构与排序有效性关联,提升文档检索性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.14972 2025-12-02 cs.HC cs.AI

Harmful Traits of AI Companions

AI伴侣的有害特性

W. Bradley Knox, Katie Bradford, Samanta Varela Castro, Desmond C. Ong, Sean Williams, Jacob Romanow, Carly Nations, Peter Stone, Samuel Baker

机构 * UT Austin — Department of Computer Science(德克萨斯大学奥斯汀分校计算机科学系) UT Austin — Department of Communication Studies(德克萨斯大学奥斯汀分校传播学系) UT Austin — Technology & Information Policy Institute(德克萨斯大学奥斯汀分校科技与信息政策研究所) UT Austin — Department of Psychology(德克萨斯大学奥斯汀分校心理学系) UT School of Law(德克萨斯大学法学院) UT Austin — Department of English(德克萨斯大学奥斯汀分校英语系) El Colegio Mexiquense, A.C. — Seminario de Instituciones, Sociedad Civil y Políticas Públicas(墨西哥埃尔科尔西奥学院,A.C. — 社会与公共政策研讨会) Sony AI(索尼人工智能)

AI总结 本文研究了AI伴侣可能带来的有害特性,分析了其潜在负面影响及因果路径,并提出减轻风险的设计建议。

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.05808 2025-12-02 cs.CV cs.MM

SizeGS: Size-aware Compression of 3D Gaussian Splatting via Mixed Integer Programming

SizeGS: 通过混合整数规划实现3D高斯点云的尺寸感知压缩

Shuzhao Xie, Jiahang Liu, Weixiang Zhang, Shijia Ge, Sicheng Pan, Chen Tang, Yunpeng Bai, Cong Zhang, Xiaoyi Fan, Zhi Wang

机构 * SIGS, Tsinghua University(清华大学SIGS实验室) Harbin Institute of Technology(哈尔滨工业大学) MMLab, The Chinese University of Hong Kong(香港中文大学MMLab) The University of Texas at Austin(德克萨斯大学奥斯汀分校) Jiangxing Intelligence Inc.(江行智能有限公司)

AI总结 SizeGS通过混合整数规划优化3DGS的超参数,实现高效尺寸感知压缩,提升压缩效率和视觉质量。

Comments Automatically compressing 3DGS into the desired file size while maximizing the visual quality

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.07507 2025-12-02 cs.CL

Thought2Text: Text Generation from EEG Signal using Large Language Models (LLMs)

Thought2Text: 使用大型语言模型(LLMs)从EEG信号生成文本

Abhijit Mishra, Shreya Shukla, Jose Torres, Jacek Gwizdka, Shounak Roychowdhury

机构 * School of Information University of Texas at Austin(信息学院 德克萨斯大学奥斯汀分校)

AI总结 Thought2Text利用大型语言模型从EEG信号生成文本,通过多阶段微调实现脑活动的可理解表达。

Comments Accepted to Findings of NAACL 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.00289 2025-12-02 cs.LG cs.RO

Data-Driven Modeling and Correction of Vehicle Dynamics

数据驱动建模与车辆动力学校正

Nguyen Ly, Caroline Tatsuoka, Jai Nagaraj, Jacob Levy, Fernando Palafox, David Fridovich-Keil, Hannah Lu

机构 * Department of Aerospace Engineering and Engineering Mechanics, The University of Texas at Austin(航空航天工程与工程力学系,德克萨斯大学奥斯汀分校) Department of Mathematics, The Ohio State University(数学系,俄亥俄州立大学) Department of Computer Science, The University of Texas at Austin(计算机科学系,德克萨斯大学奥斯汀分校) Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin(计算工程与科学研究所,德克萨斯大学奥斯汀分校)

AI总结 本文提出DRIPS和FML两种方法,用于数据驱动校正非自主车辆动力学,实现高效且准确的模型学习与误差修正。

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.12048 2025-12-02 cs.AI cs.HC cs.LG

A Survey on Bridging EEG Signals and Generative AI: From Image and Text to Beyond

关于将EEG信号与生成式AI连接的综述:从图像和文本到更广泛的领域

Shreya Shukla, Jose Torres, Akshaj Murhekar, Christina Liu, Abhijit Mishra, Jacek Gwizdka, Shounak Roychowdhury

机构 * School of Information, The University of Texas at Austin, Austin, TX, USA(信息学院,德克萨斯大学奥斯汀分校,奥斯汀,德克萨斯州)

AI总结 本综述探讨了将EEG信号转化为图像、文本和音频的生成式AI方法,分析了当前技术趋势与挑战,为未来研究提供参考。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.23450 2025-12-01 cs.CV

Object-Centric Data Synthesis for Category-level Object Detection

面向类别级目标检测的对象中心数据合成

Vikhyat Agarwal, Jiayi Cora Guo, Declan Hoban, Sissi Zhang, Nicholas Moran, Peter Cho, Srilakshmi Pattabiraman, Shantanu Joshi

机构 * University of Richmond(里士满大学) University of California, Los Angeles(加州大学洛杉矶分校) University of California, Berkeley(加州大学伯克利分校) University of Texas at Austin(德克萨斯大学奥斯汀分校) Analog Devices, Inc(安森科技公司)

AI总结 本文提出一种面向类别级目标检测的对象中心数据合成方法,通过不同数据合成技术提升模型在新目标类别上的检测性能。

Comments 10 pages, 10 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.01584 2025-12-01 cs.AI cs.LG

ReasoningWeekly: A General Knowledge and Verbal Reasoning Challenge for Large Language Models

ReasoningWeekly: 一个面向大语言模型的通用知识和逻辑推理挑战

Zixuan Wu, Francesca Lucchetti, Aleksander Boruch-Gruszecki, Jingmiao Zhao, Carolyn Jane Anderson, Joydeep Biswas, Federico Cassano, Arjun Guha

机构 * Northeastern University(东北大学) Wellesley College(韦尔斯利学院) University of Texas at Austin(德克萨斯大学奥斯汀分校) Cursor

AI总结 ReasoningWeekly是一个基于NPR周日谜题挑战的通用知识和逻辑推理基准,揭示了现有评估中不明显的模型能力差距,并发现了新的推理失败类型。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.20703 2025-11-27 cs.CY cs.AI cs.LG

PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach

PropensityBench: 通过代理方法评估大语言模型中的潜在安全风险

Udari Madhushani Sehwag, Shayan Shabihi, Alex McAvoy, Vikash Sehwag, Yuancheng Xu, Dalton Towers, Furong Huang

机构 * University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校) University of Texas at Austin(德克萨斯大学奥斯汀分校) University of Maryland, College Park(马里兰大学帕克分校)

AI总结 PropensityBench通过模拟危险能力评估大语言模型的潜在安全风险倾向,揭示模型在压力下可能选择高风险行为的倾向。

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.07694 2025-11-26 cs.CL

SAS: Simulated Attention Score

SAS: 模拟注意力分数

Chuanyang Zheng, Jiankai Sun, Yihang Gao, Yuehao Wang, Peihao Wang, Jing Xiong, Liliang Ren, Hao Cheng, Janardhan Kulkarni, Yelong Shen, Atlas Wang, Mac Schwager, Anderson Schneider, Xiaodong Liu, Jianfeng Gao

机构 * Morgan Stanley(摩根大通) Stanford(斯坦福大学) Microsoft Research(微软研究院) NUS(新加坡国立大学) UT Austin(得克萨斯大学奥斯汀分校) HKU(香港大学)

AI总结 SAS通过模拟更多注意力头和特征维度,以低成本提升模型性能,同时保持参数效率。

Comments Tech Report

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.19451 2025-11-26 eess.SY cs.RO cs.SY

Strong Duality and Dual Ascent Approach to Continuous-Time Chance-Constrained Stochastic Optimal Control

强对偶性与双上升方法在连续时间机会约束随机最优控制中的应用

Apurva Patil, Alfredo Duarte, Fabrizio Bisetti, Takashi Tanaka

机构 * Walker Department of Mechanical Engineering, University of Texas at Austin(德克萨斯大学奥斯汀分校机械工程系)

AI总结 本文提出了一种基于强对偶性的方法,用于求解连续时间机会约束随机最优控制问题,通过路径积分方法和梯度上升解决对偶问题,并验证了其在移动机器人导航中的有效性。

Comments arXiv admin note: substantial text overlap with arXiv:2504.17154

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18701 2025-11-25 cs.CV cs.AI cs.FL cs.LG

ObjectAlign: Neuro-Symbolic Object Consistency Verification and Correction

ObjectAlign: 神经符号对象一致性验证与修正

Mustafa Munir, Harsh Goel, Xiwen Wei, Minkyu Choi, Sahil Shah, Kartikeya Bhardwaj, Paul Whatmough, Sandeep Chinchali, Radu Marculescu

机构 * The University of Texas at Austin(德克萨斯大学奥斯汀分校) Qualcomm AI Research(高通人工智能研究)

AI总结 ObjectAlign通过结合感知度量与符号推理,有效检测并修正视频编辑中的对象一致性问题,提升视频质量。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.17865 2025-11-25 eess.SY cs.LG cs.SY

Generative Model Predictive Control in Manufacturing Processes: A Review

生成模型预测控制在制造过程中的应用:综述

Suk Ki Lee, Ronnie F. P. Stone, Max Gao, Wenlong Zhang, Zhenghui Sha, Hyunwoong Ko

机构 * School of Manufacturing Systems and Networks, Arizona State University(制造系统与网络学院,亚利桑那州立大学) Walker Department of Mechanical Engineering, University of Texas at Austin(机械工程系,德克萨斯大学奥斯汀分校)

AI总结 本文综述了生成ML在制造过程中的应用,探讨了其如何通过学习数据分布和管理不确定性来增强MPC,提出了未来研究方向和实际案例。

Comments 24 pages, 5 figures, Review article

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.14004 2025-11-24 cs.RO

Searching in Space and Time: Unified Memory-Action Loops for Open-World Object Retrieval

在空间和时间中搜索:统一的记忆-动作循环用于开放世界物体检索

Taijing Chen, Sateesh Kumar, Junhong Xu, Georgios Pavlakos, Joydeep Biswas, Roberto Martín-Martín

机构 * Department of Computer Science, The University of Texas at Austin(计算机科学系,德克萨斯大学奥斯汀分校)

AI总结 STAR框架通过统一记忆查询和具身动作,提升开放世界中时空物体检索的效率与准确性。

Comments https://amrl.cs.utexas.edu/STAR/

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.16639 2025-11-21 eess.AS cs.CL

Codec2Vec: Self-Supervised Speech Representation Learning Using Neural Speech Codecs

Codec2Vec: 基于神经语音编解码器的自监督语音表示学习

Wei-Cheng Tseng, David Harwath

机构 * Department of Computer Science University of Texas at Austin Texas, USA(计算机科学系 休斯顿大学 德州 美国)

AI总结 Codec2Vec通过离散音频编解码单元实现自监督语音表示学习,有效提升存储效率和训练速度,同时在SUPERB基准上表现优异。

Comments To be presented at ASRU 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.15994 2025-11-21 cs.AI cs.CL

CARE-RAG - Clinical Assessment and Reasoning in RAG

CARE-RAG - 临床评估与推理中的RAG

Deepthi Potluri, Aby Mammen Mathew, Jeffrey B DeWitt, Alexander L. Rasgon, Yide Hao, Junyuan Hong, Ying Ding

机构 * Department of Computer Science(计算机科学系) University of Texas at Austin(德克萨斯大学奥斯汀分校) Behavioral Science and Psychiatry(行为科学与精神病学) Department of Statistics(统计学系) University of Michigan(密歇根大学) School of Information(信息学院)

AI总结 CARE-RAG研究了检索增强生成在临床环境中的推理能力,提出评估框架以确保推理的准确性和一致性。

Comments The Second Workshop on GenAI for Health: Potential, Trust, and Policy Compliance

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.15145 2025-11-20 eess.AS cs.SD

Auden-Voice: General-Purpose Voice Encoder for Speech and Language Understanding

Mingyue Huo, Wei-Cheng Tseng, Yiwen Shao, Hao Zhang, Dong Yu

机构 * University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) University of Texas at Austin(德克萨斯大学奥斯汀分校) Tencent AI Lab, USA(腾讯AI实验室(美国))

Comments Submitted to ICASSP2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.14784 2025-11-20 stat.ML cs.LG math.ST stat.CO stat.ME stat.TH

Convex Clustering Redefined: Robust Learning with the Median of Means Estimator

Sourav De, Koustav Chowdhury, Bibhabasu Mandal, Sagar Ghosh, Swagatam Das, Debolina Paul, Saptarshi Chakraborty

机构 * Indian Statistical Institute, Kolkata(印度统计研究院,科希马) Department of Statistics and Data Science, University of Texas at Austin(德克萨斯大学奥斯汀分校统计与数据科学系) Electronics and Communication Sciences, Indian Statistical Institute, Kolkata(印度统计研究院,科希马电子与通信科学) Department of Statistics, University of Oxford(牛津大学统计系) Department of Statistics, University of Michigan(密歇根大学统计系)

Comments Accepted in AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.14778 2025-11-20 cs.AI

Learning Interestingness in Automated Mathematical Theory Formation

George Tsoukalas, Rahul Saha, Amitayush Thakur, Sabrina Reguyal, Swarat Chaudhuri

机构 * UT Austin(得克萨斯大学) Princeton University(普林斯顿大学) Stanford University(斯坦福大学)

Comments NeurIPS 2025 Spotlight

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.14002 2025-11-19 cs.SE cs.AI cs.LG cs.PL

FlakyGuard: Automatically Fixing Flaky Tests at Industry Scale

Chengpeng Li, Farnaz Behrang, August Shi, Peng Liu

机构 * The University of Texas at Austin(德克萨斯大学奥斯汀分校) Uber Technologies(优步技术)

Comments To appear in ASE 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.13993 2025-11-19 cs.CV

Learning Skill-Attributes for Transferable Assessment in Video

Kumar Ashutosh, Kristen Grauman

机构 * University of Texas at Austin(德克萨斯大学奥斯汀分校)

Comments NeurIPS 2025, Project webpage: https://vision.cs.utexas.edu/projects/CrossTrainer/

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.26324 2025-11-19 cs.LG cs.AI cs.DS math.ST stat.ML stat.TH

Posterior Sampling by Combining Diffusion Models with Annealed Langevin Dynamics

Zhiyang Xun, Shivam Gupta, Eric Price

机构 * UT Austin(得克萨斯大学) Microsoft Research(微软研究院)

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.13745 2025-11-19 cs.LG cs.CV cs.IT math.IT math.ST stat.ML stat.TH

Improved Sample Complexity Bounds for Diffusion Model Training

Shivam Gupta, Aditya Parulekar, Eric Price, Zhiyang Xun

机构 * UT Austin(德克萨斯大学)

Comments Bugfix

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.13699 2025-11-18 cs.LG cs.DS stat.ML

Efficient Calibration for Decision Making

Parikshit Gopalan, Konstantinos Stavropoulos, Kunal Talwar, Pranay Tankala

机构 * Apple(苹果公司) UT Austin(得克萨斯大学奥斯汀分校) Harvard(哈佛大学)

Comments 50 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12347 2025-11-18 eess.AS cs.CL cs.SD

VoiceCraft-X: Unifying Multilingual, Voice-Cloning Speech Synthesis and Speech Editing

Zhisheng Zheng, Puyuan Peng, Anuj Diwan, Cong Phuoc Huynh, Xiaohang Sun, Zhu Liu, Vimal Bhat, David Harwath

机构 * University of Texas at Austin(德克萨斯大学奥斯汀分校) Amazon(亚马逊)

Comments EMNLP 2025. Demo and code are available at https://zhishengzheng.com/voicecraft-x/

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.26546 2025-11-17 cs.SE cs.LG

Towards Verified Code Reasoning by LLMs

Meghana Sistla, Gogul Balakrishnan, Pat Rondon, José Cambronero, Michele Tufano, Satish Chandra

机构 * University of Texas at Austin(德克萨斯大学奥斯汀分校) Google DeepMind(谷歌DeepMind) Google(谷歌) Meta Platforms(元平台)

Comments 43 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.03442 2025-11-17 cs.CL cs.AI

Are language models rational? The case of coherence norms and belief revision

Thomas Hofweber, Peter Hase, Elias Stengel-Eskin, Mohit Bansal

机构 * Department of Philosophy University of North Carolina at Chapel Hill(哲学系北卡罗来纳大学教堂山分校) Department of Computer Science University of North Carolina at Chapel Hill(计算机科学系北卡罗来纳大学教堂山分校) Department of Computer Science University of Texas at Austin(计算机科学系德克萨斯大学奥斯汀分校)

Comments substantial expansions of sections 4 and 5, updated references, numerous smaller additions and clarifications

详情

展开后加载摘要…

URL PDF HTML 收藏