语言大模型 / LLM

2510.15480 2025-10-20 cs.SE cs.AI 89%

Selecting and Combining Large Language Models for Scalable Code Clone Detection

Muslim Chochlov, Gul Aftab Ahmed, James Vincent Patten, Yuanhua Han, Guoxian Lu, David Gregg, Jim Buckley

机构 * University of Limerick（利默里克大学）； Trinity College Dublin（都柏林三一学院）； Huawei Technologies Co., Ltd.（华为技术有限公司）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI

2509.20639 2025-10-20 cs.CR cs.AI 89%

A Framework for Rapidly Developing and Deploying Protection Against Large Language Model Attacks

Adam Swanda, Amy Chang, Alexander Chen, Fraser Burch, Paul Kassianik, Konstantin Berlin

机构 * Cisco Systems（思科系统）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI

2510.15227 2025-10-20 eess.AS cs.SD 88%

LongCat-Audio-Codec: An Audio Tokenizer and Detokenizer Solution Designed for Speech Large Language Models

Xiaohan Zhao, Hongyu Xiang, Shengze Ye, Song Li, Zhengkun Tian, Guanyu Chen, Ke Ding, Guanglu Wan

机构 * LongCat Team（LongCat团队）； Meituan（美团）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)

2509.20186 2025-10-20 cs.CL cs.LG 82%

Thinking Augmented Pre-training

Liang Wang, Nan Yang, Shaohan Huang, Li Dong, Furu Wei

机构 * Microsoft Research（微软研究院）

专题命中预训练与数据：LLM(abstract)；large language model(abstract)；language model(abstract)；post-training(abstract)

Comments 19 pages; v4 fixes an issue for HumanEval scores

2510.15851 2025-10-20 cs.CL cs.LG 79%

SpeechLLMs for Large-scale Contextualized Zero-shot Slot Filling

Kadri Hacioglu, Manjunath K E, Andreas Stolcke

机构 * Uniphore

专题命中预训练与数据：large language model(abstract)；language model(abstract)；foundation model(abstract)；分类 cs.CL、cs.LG

Comments 13 pages, EMNLP 2025

2312.12634 2025-10-20 cs.CV cs.AI cs.CL cs.RO 73%

MotionScript: Natural Language Descriptions for Expressive 3D Human Motions

Payam Jome Yazdian, Rachel Lagasse, Hamid Mohammadi, Eric Liu, Li Cheng, Angelica Lim

机构 * School of Computing Science, Simon Fraser University（西蒙弗雷泽大学计算机科学系）； Dept. of Electrical and Computer Engineering, University of Alberta（阿尔伯塔大学电气与计算机工程系）

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Project webpage: https://pjyazdian.github.io/MotionScript

2510.15162 2025-10-20 cs.CV cs.CL 70%

Train a Unified Multimodal Data Quality Classifier with Synthetic Data

Weizhi Wang, Rongmei Lin, Shiyang Li, Colin Lockard, Ritesh Sarkhel, Sanket Lokegaonkar, Jingbo Shang, Xifeng Yan, Nasser Zalmout, Xian Li

机构 * UC Santa Barbara（加州大学圣芭芭拉分校）； Amazon Stores Foundational AI（亚马逊商店基础人工智能）； UC San Diego（加州大学圣地亚哥分校）

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments EMNLP 2025 Findings

2510.15508 2025-10-20 cs.LG cs.NA math.NA stat.ML 57%

Theoretical Refinement of CLIP by Utilizing Linear Structure of Optimal Similarity

Naoki Yoshida, Satoshi Hayakawa, Yuhta Takida, Toshimitsu Uesaka, Hiromi Wakaki, Yuki Mitsufuji

机构 * The University of Tokyo（东京大学）； Sony Group Corporation（索尼集团公司）； Sony AI（索尼人工智能）

专题命中预训练与数据：pretraining(abstract)；分类 cs.LG

2510.10248 2025-10-20 cs.LG cs.AI 90%

Reasoning-Enhanced Large Language Models for Molecular Property Prediction

Jiaxi Zhuang, Yaorui Shi, Jue Hou, Yunong He, Mingwei Ye, Mingjun Xu, Yuming Su, Linfeng Zhang, Ying Qian, Linfeng Zhang, Guolin Ke, Hengxing Cai

机构 * DP Technology（DP技术公司）； Shanghai Jiao Tong University（上海交通大学）； East China Normal University（华东师范大学）

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；SFT(abstract)；分类 cs.AI、cs.LG

2408.10774 2025-10-20 cs.AI cs.CL 88%

Flexora: Flexible Low Rank Adaptation for Large Language Models

Chenxing Wei, Yao Shu, Ying Tiffany He, Fei Richard Yu

机构 * College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院）； Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东人工智能与数字经济实验室）； Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； School of Information Technology, Carleton University（卡尔顿大学信息科技学院）

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI

Comments 40 pages, 15 figures

2510.02569 2025-10-20 cs.CL 85%

Transcribe, Translate, or Transliterate: An Investigation of Intermediate Representations in Spoken Language Models

Tolúlopé Ògúnrèmí, Christopher D. Manning, Dan Jurafsky, Karen Livescu

机构 * Stanford University（斯坦福大学）； Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）

专题命中指令微调：language model(title,abstract)；large language model(abstract)；instruction tuning(abstract)；分类 cs.CL

Comments ASRU 2025

2510.15047 2025-10-20 cs.LG cs.CL 82%

Internalizing World Models via Self-Play Finetuning for Agentic RL

Shiqi Chen, Tongyao Zhu, Zian Wang, Jinghan Zhang, Kangrui Wang, Siyang Gao, Teng Xiao, Yee Whye Teh, Junxian He, Manling Li

机构 * City University of Hong Kong（香港城市大学）； Northwestern University（西北大学）； The Hong Kong University of Science and Technology（香港科学与技术大学）； Oxford University（牛津大学）； Allen Institute for AI (AI2)（人工智能研究所）； University of Washington（华盛顿大学）； National University of Singapore（新加坡国立大学）； The Hong Kong Polytechnic University（香港理工大学）

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；SFT(abstract)

2502.12859 2025-10-20 cs.CL cs.AI 82%

PAFT: Prompt-Agnostic Fine-Tuning

Chenxing Wei, Yao Shu, Mingwen Ou, Ying Tiffany He, Fei Richard Yu

机构 * College of Computer Science and Software Engineering, Shenzhen University, China（深圳大学计算机科学与软件工程学院）； Tsinghua Shenzhen International Graduate School, Tsinghua University, China（清华大学深圳国际研究生院）； Guangdong Lab of AI and Digital Economy (SZ), China（广东人工智能与数字经济实验室（深圳））； Hong Kong University of Science and Technology (Guangzhou), China（香港科技大学（广州））； School of Information Technology, Carleton University, Canada（卡尔顿大学信息科技学院）

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；SFT(abstract)

Comments 24 pages, 9 figures

2510.15200 2025-10-20 econ.TH cs.AI 79%

The Economics of AI Foundation Models: Openness, Competition, and Governance

Fasheng Xu, Xiaoyu Wang, Wei Chen, Karen Xie

机构 * School of Business, University of Connecticut（康奈尔大学商学院）； Faculty of Business, The Hong Kong Polytechnic University（香港理工大学商学院）

专题命中指令微调：foundation model(title,abstract)；分类 cs.AI

2510.09473 2025-10-20 cs.CV cs.LG 79%

D-TPT: Dimensional Entropy Maximization for Calibrating Test-Time Prompt Tuning in Vision-Language Models

Jisu Han, Wonjun Hwang

专题命中指令微调：language model(title,abstract)；分类 cs.LG

Comments Corrected typos

2409.14967 2025-10-20 math.DS cs.FL 78%

On Countable SFT Covers of Sparse Multidimensional Shift Spaces

Ilkka Törmä

专题命中指令微调：SFT(title,abstract)

Comments 38 pages, 9 figures

2510.15772 2025-10-20 cs.AI 70%

Self-evolving expertise in complex non-verifiable subject domains: dialogue as implicit meta-RL

Richard M. Bailey

机构 * University of Oxford（牛津大学）

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 50 pages, 4 figures

2510.15004 2025-10-20 cs.SE cs.AI 70%

Automated Snippet-Alignment Data Augmentation for Code Translation

Zhiming Zhang, Qingfu Zhu, Xianzhen Luo, Yixuan Wang, Bohan Li, Wanxiang Che

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.AI

2510.15857 2025-10-20 cs.CV 67%

BLIP3o-NEXT: Next Frontier of Native Image Generation

Jiuhai Chen, Le Xue, Zhiyang Xu, Xichen Pan, Shusheng Yang, Can Qin, An Yan, Honglu Zhou, Zeyuan Chen, Lifu Huang, Tianyi Zhou, Junnan Li, Silvio Savarese, Caiming Xiong, Ran Xu

机构 * Salesforce Research（Salesforce研究部）； University of Maryland（马里兰大学）； Virginia Tech（弗吉尼亚理工大学）； New York University（纽约大学）； UC Davis（加州大学戴维斯分校）

专题命中指令微调：foundation model(abstract)；post-training(abstract)

2510.15564 2025-10-20 cs.CV 67%

Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation

Xiaoming Zhu, Xu Huang, Qinghongbing Xie, Zhi Deng, Junsheng Yu, Yirui Guan, Zhongyuan Liu, Lin Zhu, Qijun Zhao, Ligang Liu, Long Zeng

机构 * Tsinghua University（清华大学）； Tencent（腾讯）； Southeast University（东南大学）； University of Science and Technology of China（中国科学技术大学）

专题命中指令微调：large language model(abstract)；language model(abstract)

2510.15374 2025-10-20 cs.AI cs.LG 62%

Towards Flash Thinking via Decoupled Advantage Policy Optimization

Zezhong Tan, Hang Gao, Xinhong Ma, Feng Zhang, Ziqiang Dong

机构 * Alibaba Inc.（阿里巴巴公司）； Peking University（北京大学）

专题命中指令微调：SFT(abstract)；分类 cs.AI、cs.LG

2509.01842 2025-10-20 cs.LG cs.AI 62%

GradES: Significantly Faster Training in Transformers with Gradient-Based Early Stopping

Qifu Wen, Xi Zeng, Zihan Zhou, Shuaijun Liu, Mehdi Hosseinzadeh, Ningxin Su, Reza Rawassizadeh

机构 * Department of Computer Science, Boston University Metropolitan College（波士顿大学计算机科学系）； Information Hub, The Hong Kong University of Science and Technology, Guangzhou（香港科技大学广州信息中心）； School of Engineering and Technology, Duy Tan University, Da Nang, Vietnam（杜益大学工程科技学院，岘港，越南）； Department of AI, School of Computer Science and Engineering, Galgotias University, Greater Noida, India（加洛吉亚大学人工智能系，诺伊达，印度）

专题命中指令微调：language model(abstract)；分类 cs.AI、cs.LG

Comments 20 pages, 5 figures

2510.15317 2025-10-20 cs.AI 57%

VERITAS: Leveraging Vision Priors and Expert Fusion to Improve Multimodal Data

Tingqiao Xu, Ziru Zeng, Jiayu Chen

机构 * Shanghai Jiao Tong University（上海交通大学）； Fudan University（复旦大学）

专题命中指令微调：SFT(abstract)；分类 cs.AI

Comments Accepted to EMNLP 2025 (Main Conference)

2504.15933 2025-10-20 cs.GR cs.LG 57%

Low-Rank Adaptation of Neural Fields

Anh Truong, Ahmed H. Mahmoud, Mina Konaković Luković, Justin Solomon

机构 * Department of Electrical Engineering ； Computer Science Massachusetts Institute of Technology 32 Vassar St Cambridge MA 02139 USA ； Computer Science \& Artificial Intelligence Laboratory Massachusetts Institute of Technology 32 Vassar St Cambridge MA 02139 USA ； Massachusetts Institute of Technology

专题命中指令微调：LLM(abstract)；分类 cs.LG

Comments SIGGRAPH Asia 2025

Journal ref SIGGRAPH Asia 2025 Conference Papers

2503.01067 2025-10-20 cs.LG 57%

All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning

Gokul Swamy, Sanjiban Choudhury, Wen Sun, Zhiwei Steven Wu, J. Andrew Bagnell

机构 * Carnegie Mellon University（卡内基梅隆大学）； Cornell University（康奈尔大学）

专题命中指令微调：foundation model(abstract)；分类 cs.LG

2510.15716 2025-10-20 cs.AI 87%

Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences

Keertana Chidambaram, Karthik Vinary Seetharaman, Vasilis Syrgkanis

机构 * Stanford University（斯坦福大学）

专题命中后训练与偏好优化：preference optimization(title,abstract)；large language model(abstract)；language model(abstract)；RLHF(abstract)

2510.07242 2025-10-20 cs.CL cs.LG 79%

Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense

Leitian Tao, Ilia Kulikov, Swarnadeep Saha, Tianlu Wang, Jing Xu, Sharon Li, Jason E Weston, Ping Yu

机构 * FAIR at Meta（Meta 的 FAIR）； University of Wisconsin–Madison（威斯康星大学麦迪逊分校）

专题命中后训练与偏好优化：large language model(abstract)；language model(abstract)；post-training(abstract)；分类 cs.CL、cs.LG

Comments 21 pages

2502.13349 2025-10-20 cs.CL 88%

Event Segmentation Applications in Large Language Model Enabled Automated Recall Assessments

Ryan A. Panela, Alex J. Barnett, Morgan D. Barense, Björn Herrmann

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments 35 pages, 8 figures

2410.16655 2025-10-20 cs.SE cs.AI 86%

Memory-Efficient Large Language Models for Program Repair with Semantic-Guided Patch Generation

Thanh Le-Cong, Bach Le, Toby Murray

机构 * The University of Melbourne（墨尔本大学）

专题命中长上下文与记忆：large language model(title)；language model(title)；LLM(abstract)；分类 cs.AI

Comments Accepted to ICSE 2026, Research Track

2510.15103 2025-10-20 cs.CL cs.AI 79%

Continual Learning via Sparse Memory Finetuning

Jessy Lin, Luke Zettlemoyer, Gargi Ghosh, Wen-Tau Yih, Aram Markosyan, Vincent-Pierre Berges, Barlas Oğuz

机构 * FAIR at Meta（Meta 的 FAIR 部门）； University of California, Berkeley（加州大学伯克利分校）

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；pretraining(abstract)；分类 cs.CL、cs.AI

1. 预训练与数据 8 篇