arXivDaily arXiv每日学术速递 周一至周五更新

大厂专区

Hugging Face

共收录 56
2506.06725 2026-01-30 cs.AI cs.LG

WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-making

WorldLLM: 通过好奇心驱动的理论构建改进LLM的世界建模

Guillaume Levy, Cedric Colas, Pierre-Yves Oudeyer, Thomas Carta, Clement Romac

机构 * Inria(法国国家信息与自动化技术研究院) Univ. of Bordeaux(波尔多大学) MIT(麻省理工学院) Hugging Face

AI总结 WorldLLM通过结合贝叶斯推断和好奇心驱动的强化学习,改进LLM在结构化环境中的世界建模能力,提升预测精度并生成可解释的环境理论。

Comments This project's code can be found at https://github.com/flowersteam/WorldLLM. This project was presented at RLDM 2025 (https://rldm.org/)

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.12481 2026-01-30 cs.LG cs.AI

SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling

SAC-GLAM:通过软演员-评论员和回顾重标记改进LLM代理的在线强化学习

Loris Gaven, Clement Romac, Thomas Carta, Sylvain Lamprier, Olivier Sigaud, Pierre-Yves Oudeyer

机构 * Inria (Flowers)(Inria(Flowers)) University of Bordeaux(波尔多大学) Hugging Face Univ Angers(昂热大学) LERIA SFR MATHSTIC(MATHSTIC联合研究机构) Sorbonne Université(索邦大学) ISIR

AI总结 SAC-GLAM通过结合软演员-评论员算法和回顾重标记,改进LLM代理的在线强化学习,提升其在复杂环境中的策略学习能力。

Comments This work has been presented at the IMOL workshop at NeurIPS 2025 (https://neurips.cc/virtual/2024/101058)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.08697 2025-12-19 cs.SE cs.AI cs.CL

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

BigCodeArena: 通过执行揭示更多可靠的代码生成人类偏好

Terry Yue Zhuo, Xiaolong Jin, Hange Liu, Juyong Jiang, Tianyang Liu, Chen Gong, Bhupesh Bishnoi, Vaisakhi Mishra, Marek Suppa, Noah Ziems, Saiteja Utpala, Ming Xu, Guangyu Song, Kaixin Li, Yuhan Cao, Bo Liu, Zheng Liu, Sabina Abdurakhmanova, Wenhao Yu, Mengzhao Jia, Jihan Yao, Kenneth Hamilton, Kumar Shridhar, Minh Chien Vu, Dingmin Wang, Jiawei Liu, Zijian Wang, Qian Liu, Binyuan Hui, Meg Risdal, Ahsen Khaliq, Atin Sood, Zhenchang Xing, Wasi Uddin Ahmad, John Grundy, David Lo, Banghua Zhu, Xiaoning Du, Torsten Scholak, Leandro von Werra

机构 * Monash University(墨尔本大学) CSIRO’s Data61(CSIRO的数据61) Purdue University(普渡大学) Independent(独立) HKUST (Guangzhou)(香港科技大学(广州)) UCSD(加州大学圣地亚哥分校) UVA(弗吉尼亚大学) CNRS, France(法国国家科学研究中心) IBM Cisco(思科) Comenius University in Bratislava(布拉提斯拉瓦康门纽斯大学) University of Notre Dame(Notre Dame大学) Uber Tano Labs(Tano实验室) NUS(国立大学新加坡) Institute of Automation, CAS(中国科学院自动化研究所) Tencent AI Lab(腾讯AI实验室) University of Washington(华盛顿大学) Nevsky Collective(Nevsky集体) ETH Zurich(苏黎世联邦理工学院) Detomo Inc(Detomo公司) University of Oxford(牛津大学) UIUC(伊利诺伊大学香槟分校) Google(谷歌) NVIDIA Singapore Management University(新加坡管理学院) ServiceNow Research(ServiceNow研究) Hugging Face

AI总结 BigCodeArena通过执行揭示更多可靠的代码生成人类偏好,提出自动评分基准评估LLM编码质量。

Comments Built with love by the BigCode community :)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.03073 2025-12-04 cs.CY cs.AI

Economies of Open Intelligence: Tracing Power & Participation in the Model Ecosystem

开源智能的经济效应:追踪模型生态系统中的权力与参与

Shayne Longpre, Christopher Akiki, Campbell Lund, Atharva Kulkarni, Emily Chen, Irene Solaiman, Avijit Ghosh, Yacine Jernite, Lucie-Aimée Kaffee

机构 * MIT Data Provenance Initiative(MIT数据溯源计划) Data Provenance Initiative(数据溯源计划) ScaDS.AI Leipzig(ScaDS.AI莱比锡) University of Edinburgh(爱丁堡大学) University of Southern California(南加州大学) UNC at Chapel Hill(北卡罗来纳大学教堂山分校) Hugging Face

AI总结 研究分析了开放模型经济中权力和参与的变化,揭示了开发者中介者的作用及市场权力的重新分配。

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.14652 2025-11-27 cs.CY cs.AI cs.LG

Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor

AI中的严谨性:进行严谨的AI工作需要一种更广泛、负责任的AI导向的严谨性观念

Alexandra Olteanu, Su Lin Blodgett, Agathe Balayn, Angelina Wang, Fernando Diaz, Flavio du Pin Calmon, Margaret Mitchell, Michael Ekstrand, Reuben Binns, Solon Barocas

机构 * Microsoft Research(微软研究院) Cornell Tech(康奈尔科技学院) Carnegie Mellon University(卡内基梅隆大学) Harvard University(哈佛大学) Hugging Face(Hugging Face公司) Drexel University(德雷塞尔大学) University of Oxford(牛津大学)

AI总结 本文提出AI研究需更广泛的严谨性观念,涵盖方法论、背景知识、规范标准、理论构念、报告方式及推论支持等方面,以提升AI工作的责任性和严谨性。

Comments 21 pages, 1 figure, 1 table, accepted at NeurIPS'25 position papers track

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.00444 2025-11-04 cs.IR cs.AI

LIR: The First Workshop on Late Interaction and Multi Vector Retrieval @ ECIR 2026

Benjamin Clavié, Xianming Li, Antoine Chaffin, Omar Khattab, Tom Aarsen, Manuel Faysse, Jing Li

机构 * Mixedbread AI The Hong Kong Polytechnic University(香港理工大学) LightOn MIT(麻省理工学院) HuggingFace CentraleSupélec(中央理工学院) National Institute of Informatics (NII)(日本信息处理学会)

Comments Accepted workshop at ECIR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.23141 2025-10-28 eess.AS cs.LG

Treble10: A high-quality dataset for far-field speech recognition, dereverberation, and enhancement

Sarabeth S. Mullins, Georg Götz, Eric Bezzam, Steven Zheng, Daniel Gert Nielsen

机构 * Treble Technologies(Treble技术公司) Hugging Face(Hugging Face公司)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17950 2025-10-22 cs.RO

RoboChallenge: Large-scale Real-robot Evaluation of Embodied Policies

Adina Yakefu, Bin Xie, Chongyang Xu, Enwen Zhang, Erjin Zhou, Fan Jia, Haitao Yang, Haoqiang Fan, Haowei Zhang, Hongyang Peng, Jing Tan, Junwen Huang, Kai Liu, Kaixin Liu, Kefan Gu, Qinglun Zhang, Ruitao Zhang, Saike Huang, Shen Cheng, Shuaicheng Liu, Tiancai Wang, Tiezhen Wang, Wei Sun, Wenbin Tang, Yajun Wei, Yang Chen, Youqiang Gui, Yucheng Zhao, Yunchao Ma, Yunfei Wei, Yunhuan Yang, Yutong Guo, Ze Chen, Zhengyuan Du, Ziheng Zhang, Ziming Liu, Ziwei Yan

机构 * Dexmal Hugging Face Project(Hugging Face项目)

Comments Authors are listed in alphabetical order. The official website is located at https://robochallenge.ai

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.19222 2025-09-24 cs.LG

Video Killed the Energy Budget: Characterizing the Latency and Power Regimes of Open Text-to-Video Models

Julien Delavande, Regis Pierrard, Sasha Luccioni

机构 * Hugging Face

Comments 10 pages. Accepted as an oral presentation at the NeurIPS 2025 NextVid Workshop (San Diego, December 6, 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.23719 2025-07-01 cs.LG cs.AI

DABstep: Data Agent Benchmark for Multi-step Reasoning

Alex Egg, Martin Iglesias Goyanes, Friso Kingma, Andreu Mora, Leandro von Werra, Thomas Wolf

机构 * Adyen(阿德耶恩) Hugging Face

Comments 13 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2305.16264 2025-07-01 cs.CL cs.AI cs.LG

Scaling Data-Constrained Language Models

Niklas Muennighoff, Alexander M. Rush, Boaz Barak, Teven Le Scao, Aleksandra Piktus, Nouamane Tazi, Sampo Pyysalo, Thomas Wolf, Colin Raffel

机构 * Hugging Face Harvard University(哈佛大学) University of Turku(图尔库大学)

Comments 50 pages (9 main), 39 figures, 15 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.20920 2025-06-27 cs.CL

FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language

Guilherme Penedo, Hynek Kydlíček, Vinko Sabolčec, Bettina Messmer, Negar Foroutan, Amir Hossein Kargaran, Colin Raffel, Martin Jaggi, Leandro Von Werra, Thomas Wolf

机构 * Hugging Face EPFL(瑞士联邦理工学院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.18787 2025-06-24 cs.CV

3D Arena: An Open Platform for Generative 3D Evaluation

Dylan Ebert

机构 * Hugging Face

Comments 9 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.09346 2025-06-16 cs.HC cs.AI cs.CY

"It's not a representation of me": Examining Accent Bias and Digital Exclusion in Synthetic AI Voice Services

Shira Michel, Sufi Kaur, Sarah Elizabeth Gillespie, Jeffrey Gleason, Christo Wilson, Avijit Ghosh

机构 * Northeastern University(东北大学) Hugging Face University of Connecticut(康奈尔大学)

Comments This paper has been accepted to FAccT 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06091 2025-06-10 cs.CL

MIRIAD: Augmenting LLMs with millions of medical query-response pairs

Qinyue Zheng, Salman Abdullah, Sam Rawal, Cyril Zakka, Sophie Ostmeier, Maximilian Purk, Eduardo Reis, Eric J. Topol, Jure Leskovec, Michael Moor

机构 * Department of Biosystems Science and Engineering, ETH Zurich(生物系统科学与工程系,苏黎世联邦理工学院) Department of Computer Science, Stanford University(计算机科学系,斯坦福大学) Department of Internal Medicine, Mayo Clinic(内科医学系,梅奥诊所) Hugging Face Department of Radiology, Stanford University(放射学系,斯坦福大学) Hasso-Plattner-Institute for Digital Engineering, University of Potsdam(数字工程研究所,波茨坦大学) Center for Artificial Intelligence in Medicine and Imaging, Stanford, CA, USA(医学与成像人工智能中心,斯坦福,CA,美国) Scripps Translational Science Institute, San Diego, CA, USA(斯克里普斯转化科学研究所,圣地亚哥,CA,美国)

Comments Preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.05209 2025-06-06 cs.CL cs.LG

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

Nikhil Kandpal, Brian Lester, Colin Raffel, Sebastian Majstorovic, Stella Biderman, Baber Abbasi, Luca Soldaini, Enrico Shippole, A. Feder Cooper, Aviya Skowron, John Kirchenbauer, Shayne Longpre, Lintang Sutawika, Alon Albalak, Zhenlin Xu, Guilherme Penedo, Loubna Ben Allal, Elie Bakouch, John David Pressman, Honglu Fan, Dashiell Stander, Guangyu Song, Aaron Gokaslan, Tom Goldstein, Brian R. Bartoldson, Bhavya Kailkhura, Tyler Murray

机构 * University of Toronto(多伦多大学) Vector Institute(向量研究所) Hugging Face EleutherAI The Allen Institute for Artificial Intelligence(人工智能研究所) Teraflop AI Cornell University(康奈尔大学) University of Maryland, College Park(马里兰大学学院市分校) MIT(麻省理工学院) CMU(卡内基梅隆大学) Lila Sciences Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01844 2025-06-03 cs.LG cs.RO

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

Mustafa Shukor, Dana Aubakirova, Francesco Capuano, Pepijn Kooijmans, Steven Palma, Adil Zouitine, Michel Aractingi, Caroline Pascal, Martino Russi, Andres Marafioti, Simon Alibert, Matthieu Cord, Thomas Wolf, Remi Cadene

机构 * Hugging Face Sorbonne University(索邦大学) École Normale Supérieure Paris-Saclay(巴黎萨克雷高等师范学院)

Comments 24 pages. Code and assets: https://github.com/huggingface/lerobot

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.13467 2025-06-02 cs.LG cs.AI cs.DC

LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs

Chansung Park, Juyong Jiang, Fan Wang, Sayak Paul, Jing Tang

机构 * Electronics and Telecommunications Research Institute(电子电信研究院) The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)) The Hong Kong University of Science and Technology(香港科技大学) Hugging Face

Comments The first three authors contributed equally to this work; Accepted by ACL 2025 (Main)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.18609 2025-05-28 cs.CL

RASMALAI: Resources for Adaptive Speech Modeling in Indian Languages with Accents and Intonations

Ashwin Sankar, Yoach Lacombe, Sherry Thomas, Praveen Srinivasa Varadhan, Sanchit Gandhi, Mitesh M Khapra

机构 * Indian Institute of Technology Madras(印度理工学院马德拉斯学院) Huggingface AI4Bharat, WSAI(AI4Bharat,WSAI)

Comments Accepted at Interspeech 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.17082 2025-05-26 cs.CL cs.AI

GemMaroc: Unlocking Darija Proficiency in LLMs with Minimal Data

Abderrahman Skiredj, Ferdaous Azhari, Houdaifa Atou, Nouamane Tazi, Ismail Berrada

机构 * College of Computing, Mohammed VI Polytechnic University(计算学院,穆莱·伊斯梅尔polytechnic大学) Hugging Face National Institute of Posts and Telecoms(国家电信研究所)

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.17933 2025-05-23 cs.CL cs.AI

BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism

Martin Fajcik, Martin Docekal, Jan Dolezal, Karel Ondrej, Karel Beneš, Jan Kapsa, Pavel Smrz, Alexander Polok, Michal Hradis, Zuzana Neverilova, Ales Horak, Radoslav Sabol, Michal Stefanik, Adam Jirkovsky, David Adamczyk, Petr Hyner, Jan Hula, Hynek Kydlicek

机构 * Brno University of Technology(布拉格技术大学) Masaryk University(马萨里大学) University of Helsinki(赫尔辛基大学) Czech Technical University in Prague(布拉格捷克技术大学) University of Ostrava(奥斯特拉瓦大学) CIIRC(捷克信息与通信研究中心) Hugging Face

Comments Accepted to TACL

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.10046 2025-05-16 cs.CV

Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis

Bingda Tang, Boyang Zheng, Xichen Pan, Sayak Paul, Saining Xie

机构 * New York University(纽约大学) Hugging Face

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.01487 2025-05-07 cs.AI

FastRM: An efficient and automatic explainability framework for multimodal generative models

Gabriela Ben-Melech Stan, Estelle Aflalo, Man Luo, Shachar Rosenman, Tiep Le, Sayak Paul, Shao-Yen Tseng, Vasudev Lal

机构 * Intel Labs(英特尔实验室) Hugging Face

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.17674 2025-04-25 cs.CL cs.LG

Energy Considerations of Large Language Model Inference and Efficiency Optimizations

Jared Fernandez, Clara Na, Vashisth Tiwari, Yonatan Bisk, Sasha Luccioni, Emma Strubell

机构 * Carnegie Mellon University(卡内基梅隆大学) Hugging Face

Comments 16 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.16080 2025-04-23 cs.CV

From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning

Le Zhuo, Liangbing Zhao, Sayak Paul, Yue Liao, Renrui Zhang, Yi Xin, Peng Gao, Mohamed Elhoseiny, Hongsheng Li

机构 * CUHK MMLab(香港中文大学多模态实验室) KAUST(科威特科学与技术研究中心) Hugging Face(Hugging Face公司) Shanghai AI Lab(上海人工智能实验室)

Comments All code, checkpoints, and datasets are available at \url{https://diffusion-cot.github.io/reflection2perfection}

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.14286 2025-04-23 cs.LG

SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM

Xiaojiang Zhang, Jinghui Wang, Zifei Cheng, Wenhao Zhuang, Zheng Lin, Minglei Zhang, Shaojie Wang, Yinghan Cui, Chao Wang, Junyi Peng, Shimiao Jiang, Shiqi Kuang, Shouyu Yin, Chaohang Wen, Haotian Zhang, Bin Chen, Bing Yu

机构 * Kuaishou Kwaipilot Team(快手Kwaipilot团队) HuggingFace

详情

展开后加载摘要…

URL PDF HTML 收藏