大模型推理能力

R2Q: Towards Robust 2-Bit Large Language Models via Residual Refinement Quantization

R2Q: 向通过残差细化量化实现稳健的2位大语言模型

Jiayi Chen, Jieqi Shi, Jing Huo, Chen Wu

机构 * Nanjing University（南京大学） ； Microsoft AI（微软人工智能） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

AI总结 R2Q通过残差细化量化方法，在极端压缩下提升2位大语言模型的性能和稳定性。

PromptTailor: Multi-turn Intent-Aligned Prompt Synthesis for Lightweight LLMs

PromptTailor: 为轻量级大语言模型进行多轮意图对齐的提示合成

Yizhou Xu, Janet Davis

机构 * Whitman College（惠特曼学院） 纠错

专题命中 其他推理 ：chain-of-thought(abstract)；分类 cs.CL、cs.AI

AI总结 PromptTailor通过意图对齐的提示合成提升轻量级大语言模型的输出质量，以更少的模型调用次数实现更高的用户偏好率。

Comments EMNLP 2025 Workshop PALS. Additional note: There is a citation error on Evoke. The paper we are referring to is "Evoking critical thinking abilities in LLMs via reviewer-author prompt editing."

EEGAgent: A Unified Framework for Automated EEG Analysis Using Large Language Models

EEGAgent: 一种利用大语言模型进行自动化EEG分析的统一框架

Sha Zhao, Mingyi Peng, Haiteng Jiang, Tao Li, Shijian Li, Gang Pan

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

AI总结 EEGAgent利用大语言模型实现多任务EEG分析，提供灵活且可解释的自动化EEG处理与报告生成能力。

How to Find Fantastic AI Papers: Self-Rankings as a Powerful Predictor of Scientific Impact Beyond Peer Review

如何找到非凡的AI论文：自我排名作为预测科学影响的强大指标超越同行评审

Buxin Su, Natalie Collina, Garrett Wen, Didong Li, Kyunghyun Cho, Jianqing Fan, Bingxin Zhao, Weijie Su

机构 * University of Pennsylvania（宾夕法尼亚大学） ； Yale University（耶鲁大学） ； University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校） ； New York University（纽约大学） ； Princeton University（普林斯顿大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

AI总结 本文通过研究作者自我排名发现其能有效预测AI领域高影响力论文，优于同行评审。

From Pixels to Posts: Retrieval-Augmented Fashion Captioning and Hashtag Generation

从像素到帖子：基于检索的时尚描述与标签生成

Moazzam Umer Gondal, Hamad Ul Qudous, Daniya Siddiqui, Asma Ahmad Farhan

机构 * organization= School of Computing, National University of Computer \& Emerging Sciences (FAST) , city= Lahore , postcode= 54000 , country= Pakistan 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

AI总结 本文提出一种基于检索的时尚描述与标签生成方法，结合多件服装检测、属性推理和大语言模型，提升描述准确性和标签生成的视觉相关性。

Comments Submitted to Expert Systems with Applications

Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost

Kitty: 一种准确且高效的2位KV缓存量化方法，结合动态通道精度提升

Haojun Xia, Xiaoxia Wu, Jisen Li, Robert Wu, Junxiong Wang, Jue Wang, Chenxi Li, Aman Singhal, Alay Dilipbhai Shah, Alpay Ariyak, Donglin Zhuang, Zhongzhu Zhou, Ben Athiwaratkun, Zhen Zheng, Shuaiwen Leon Song

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

AI总结 Kitty通过混合精度KV缓存的算法-系统协同设计，实现2位量化在保持高精度的同时显著降低内存占用，提升推理效率。

Can we use LLMs to bootstrap reinforcement learning? -- A case study in digital health behavior change

能否利用大语言模型（LLM）来引导强化学习？——数字健康行为改变的案例研究

Nele Albers, Esra Cemre Su de Groot, Loes Keijsers, Manon H. Hillegers, Emiel Krahmer

专题命中 其他推理 ：chain-of-thought(abstract)；分类 cs.AI、cs.LG

AI总结 本文探讨了利用大语言模型生成用户交互样本以提升数字健康行为改变的强化学习效果，并通过实验验证了LLM生成样本的实用性与有效性。

Parameter Importance-Driven Continual Learning for Foundation Models

Lingxiang Wang, Hainan Zhang, Zhiming Zheng

机构 * Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University（未来区块链与隐私计算先进创新中心，北京航空航天大学） ； School of Artificial Intelligence, Beihang University（人工智能学院，北京航空航天大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Knowledge-Grounded Agentic Large Language Models for Multi-Hazard Understanding from Reconnaissance Reports

Chenchen Kuai, Zihao Li, Braden Rosen, Stephanie Paal, Navid Jafari, Jean-Louis Briaud, Yunlong Zhang, Youssef M. A. Hashash, Yang Zhou

机构 * organization= Department One , addressline= Address One , city= City One , postcode= 00000 , state= State One , country= Country One ； organization= Department Two , addressline= Address Two , city= City Two , postcode= 22222 , state= State Two , country= Country Two ； organization= Zachry Department of Civil \& Environmental Engineering, Texas A\&M University , addressline= 3136 TAMU , city= College Station , postcode= 77843 , state= TX , country= USA ； organization= Department of Engineering Technology ； Industrial Distribution, Texas A\&M University , city= College Station , postcode= 77843 , state= TX , country= USA ； organization= Department of Civil ； Environmental Engineering, University of Illinois Urbana-Champaign , city= Urbana , postcode= 61801 , state= IL , country= USA 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 17 pages, 5 figures

Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective

Zhuoyi Yang, Xu Guo, Tong Zhang, Huijuan Xu, Boyang Li

机构 * Department of Computer Science and Engineering, The Pennsylvania State University（宾夕法尼亚州立大学计算机科学与工程系） ； School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院） 纠错

专题命中 其他推理 ：chain-of-thought(abstract)；分类 cs.CL、cs.AI

Bias after Prompting: Persistent Discrimination in Large Language Models

Nivedha Sivakumar, Natalie Mackraz, Samira Khorshidi, Krishna Patel, Barry-John Theobald, Luca Zappella, Nicholas Apostoloff

机构 * Apple（苹果公司） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

On the Notion that Language Models Reason

Bertram Højer

机构 * Department of Computer Science（计算机科学系） ； IT University of Copenhagen（哥本哈根IT大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Accepted at the 1st Workshop on Epistemic Intelligence in Machine Learning, EurIPS 2025

H-Model: Dynamic Neural Architectures for Adaptive Processing

Dmytro Hospodarchuk

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments Independent research report, 24 pages including references and figures

ProFuser: Progressive Fusion of Large Language Models

Tianyuan Shi, Fanqi Wan, Canbin Huang, Xiaojun Quan, Chenliang Li, Ming Yan, Ji Zhang, Minhua Huang, Wu Kai

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Accepted to AAAI 2026

Xiaoice: Training-Free Video Understanding via Self-Supervised Spatio-Temporal Clustering of Semantic Features

Shihao Ji, Zihui Song

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments This paper is being withdrawn because we have identified a significant error in the implementation of our self-supervised clustering approach. Specifically, our feature aggregation step inadvertently leaked temporal information across frames, which violates the core assumption of our training-free method. We sincerely apologize to the research community

Multi-Turn Interactions for Text-to-SQL with Large Language Models

Guanming Xiong, Junwei Bao, Hongfei Jiang, Yang Song, Wen Zhao

机构 * Peking University（北京大学） ； Zuoyebang Education Technology Co., Ltd.（佐元邦教育科技有限公司） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments This work has been accepted to CIKM 2025

Aligning Diffusion Language Models via Unpaired Preference Optimization

Vaibhav Jindal, Hejian Sang, Chun-Mao Lai, Yanning Chen, Zhipeng Wang

机构 * LinkedIn Corporation（LinkedIn公司） ； University of California San Diego（加州大学圣地亚哥分校） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

GraphRAFT: Retrieval Augmented Fine-Tuning for Knowledge Graphs on Graph Databases

Alfred Clemedtson, Borun Shi

机构 * Neo4j 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

PerspAct: Enhancing LLM Situated Collaboration Skills through Perspective Taking and Active Vision

Sabrina Patania, Luca Annese, Anita Pellegrini, Silvia Serino, Anna Lambiase, Luca Pallonetto, Silvia Rossi, Simone Colombani, Tom Foulsham, Azzurra Ruggeri, Dimitri Ognibene

机构 * University of Milan-Bicocca（米兰-比科卡大学） ； University of Naples Federico II（那不勒斯费德里科二世大学） ； Oversonic Robotics（Oversonic机器人公司） ； University of Essex（埃塞克斯大学） ； TUM School of Social Sciences and Technology（慕尼黑技术大学社会科学与技术学院） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Accepted at IAS19

Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models

Kunhao Li, Wenhao Li, Di Wu, Lei Yang, Jun Bai, Ju Jia, Jason Xue

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Accepted at AAAI 2026 as a Conference Paper (Oral Presentation)

Explicit Knowledge-Guided In-Context Learning for Early Detection of Alzheimer's Disease

Puzhen Su, Yongzhu Miao, Chunxi Guo, Jintao Tang, Shasha Li, Ting Wang

机构 * College of Computer Science and Technology, National University of Defense Technology（计算机科学与技术学院，国防科技大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments This paper was accepted by IEEE BIBM 2025 conference

Revealing emergent human-like conceptual representations from language prediction

Ningyu Xu, Qi Zhang, Chao Du, Qiang Luo, Xipeng Qiu, Xuanjing Huang, Menghan Zhang

机构 * College of Computer Science and Artificial Intelligence（计算机科学与人工智能学院） ； Fudan University（复旦大学） ； Institute of Modern Languages and Linguistics（现代语言与语言学研究所） ； Shanghai Key Laboratory of Intelligent Information Processing（上海智能信息处理重点实验室） ； Research Institute of Intelligent Complex Systems（智能复杂系统研究所） ； Institute of Trustworthy Embodied Artificial Intelligence（可信具身人工智能研究所） ； State Key Laboratory of Genetics and Development of Complex Phenotypes（复杂表型遗传与发育国家重点实验室） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 66 pages. Accepted manuscript. Final version published in Proceedings of the National Academy of Sciences (PNAS): https://www.pnas.org/doi/10.1073/pnas.2512514122

Journal ref Proceedings of the National Academy of Sciences, U.S.A., 122 (44) e2512514122 (2025)

NVIDIA Nemotron Nano V2 VL

NVIDIA, :, Amala Sanjay Deshmukh, Kateryna Chumachenko, Tuomas Rintamaki, Matthieu Le, Tyler Poon, Danial Mohseni Taheri, Ilia Karmanov, Guilin Liu, Jarno Seppanen, Guo Chen, Karan Sapra, Zhiding Yu, Adi Renduchintala, Charles Wang, Peter Jin, Arushi Goel, Mike Ranzinger, Lukas Voegtle, Philipp Fischer, Timo Roman, Wei Ping, Boxin Wang, Zhuolin Yang, Nayeon Lee, Shaokun Zhang, Fuxiao Liu, Zhiqi Li, Di Zhang, Greg Heinrich, Hongxu Yin, Song Han, Pavlo Molchanov, Parth Mannan, Yao Xu, Jane Polak Scowcroft, Tom Balough, Subhashree Radhakrishnan, Paris Zhang, Sean Cha, Ratnesh Kumar, Zaid Pervaiz Bhat, Jian Zhang, Darragh Hanley, Pritam Biswas, Jesse Oliver, Kevin Vasques, Roger Waleffe, Duncan Riach, Oluwatobi Olabiyi, Ameya Sunil Mahabaleshwarkar, Bilal Kartal, Pritam Gundecha, Khanh Nguyen, Alexandre Milesi, Eugene Khvedchenia, Ran Zilberstein, Ofri Masad, Natan Bagrov, Nave Assaf, Tomer Asida, Daniel Afrimi, Amit Zuker, Netanel Haber, Zhiyu Cheng, Jingyu Xin, Di Wu, Nik Spirin, Maryam Moosaei, Roman Ageev, Vanshil Atul Shah, Yuting Wu, Daniel Korzekwa, Unnikrishnan Kizhakkemadam Sreekumar, Wanli Jiang, Padmavathy Subramanian, Alejandra Rico, Sandip Bhaskar, Saeid Motiian, Kedi Wu, Annie Surla, Chia-Chih Chen, Hayden Wolff, Matthew Feinberg, Melissa Corpuz, Marek Wawrzos, Eileen Long, Aastha Jhunjhunwala, Paul Hendricks, Farzan Memarian, Benika Hall, Xin-Yu Wang, David Mosallanezhad, Soumye Singhal, Luis Vega, Katherine Cheung, Krzysztof Pawelec, Michael Evans, Katherine Luna, Jie Lou, Erick Galinkin, Akshay Hazare, Kaustubh Purandare, Ann Guan, Anna Warno, Chen Cui, Yoshi Suhara, Shibani Likhite, Seph Mard, Meredith Price, Laya Sleiman, Saori Kaji, Udi Karpas, Kari Briski, Joey Conway, Michael Lightstone, Jan Kautz, Mohammad Shoeybi, Mostofa Patwary, Jonathen Cohen, Oleksii Kuchaiev, Andrew Tao, Bryan Catanzaro

机构 * NVIDIA 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Abductive Inference in Retrieval-Augmented Language Models: Generating and Validating Missing Premises

Shiyin Lin

机构 * Independent Researcher, Mountain View, CA94039, USA（独立研究者） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Memory- and Latency-Constrained Inference of Large Language Models via Adaptive Split Computing

Mingyu Sung, Vikas Palakonda, Suhwan Im, Sunghwan Moon, Il-Min Kim, Sangseok Yun, Jae-Mo Kang

机构 * Department of Artificial Intelligence, Kyungpook National University（人工智能系，庆北国立大学） ； Department of Electrical and Computer Engineering, Queen’s University（电气与计算机工程系，皇后大学） ； Department of Information and Communications Engineering, Pukyong National University（信息与通信工程系，浦项国立大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness

Fali Wang, Jihai Chen, Shuhua Yang, Ali Al-Lawati, Linli Tang, Hui Liu, Suhang Wang

机构 * Pennsylvania State University（宾夕法尼亚州立大学） ； Michigan State University（密歇根州立大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 24 pages, 19 figures-under review; more detailed than v1

Who Sees the Risk? Stakeholder Conflicts and Explanatory Policies in LLM-based Risk Assessment

Srishti Yadav, Jasmina Gajcin, Erik Miehling, Elizabeth Daly

机构 * IBM Research, Ireland（IBM研究院（爱尔兰）） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

AutoPDL: Automatic Prompt Optimization for LLM Agents

Claudio Spiess, Mandana Vaziri, Louis Mandel, Martin Hirzel

专题命中 其他推理 ：CoT(abstract)；分类 cs.AI、cs.LG

Comments An earlier version of this paper was published in AutoML 2025 Methods Track. This version adds missing standard deviations in Table 1

DeepSpecs: Expert-Level Questions Answering in 5G

Aman Ganapathy Manvattira, Yifei Xu, Ziyue Dang, Songwu Lu

机构 * University of California, Los Angeles（加州大学洛杉矶分校） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Measuring Algorithmic Partisanship via Zero-Shot Classification and Its Implications on Political Discourse

Nathan Junzi Chen

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 19 pages, 7 figures