大模型推理能力

Do Edges Matter? Investigating Edge-Enhanced Pre-Training for Medical Image Segmentation

Paul Zaha, Lars Böcking, Simeon Allmendinger, Leopold Müller, Niklas Kühl

机构 * University of Bayreuth（拜罗伊特大学） ； Fraunhofer FIT（弗劳恩霍夫 FIT 研究所） 纠错

专题命中 规划推理 ：planning(abstract)；分类 cs.LG

Comments 11 pages, 5 figures, Third International Workshop on Data Engineering in Medical Imaging (DEMI 2025)

On the Generalization vs Fidelity Paradox in Knowledge Distillation

Suhas Kamasetty Ramesh, Ayan Sengupta, Tanmoy Chakraborty

机构 * Department of Electrical Engineering（电气工程系） ； Indian Institute of Technology Delhi（印度理工学院德里） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles

Yelim Ahn, Jaejin Lee

专题命中 规划推理 ：reasoning(abstract)；分类 cs.AI

Comments 15 pages

MAO-ARAG: Multi-Agent Orchestration for Adaptive Retrieval-Augmented Generation

Yiqun Chen, Erhan Zhang, Lingyong Yan, Shuaiqiang Wang, Jizhou Huang, Dawei Yin, Jiaxin Mao

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL

VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges

Yuxuan Wang, Yiqi Song, Cihang Xie, Yang Liu, Zilong Zheng

机构 * NLCo Lab, State Key Laboratory of General Artificial Intelligence, BIGAI（NLCo实验室、国家一般人工智能重点实验室、BIGAI） ； School of Computer Science & Technology, Beijing Institute of Technology（计算机科学与技术学院、北京理工大学） ； Computer Science and Engineering, University of California（计算机科学与工程系、加州大学） ； Wangxuan Institute of Computer Technology, Peking University（王轩计算机技术研究所、北京大学） 纠错

专题命中 规划推理 ：planning(abstract)；分类 cs.CL

Comments To appear at ICCV 2025

Attention-Enhanced Prompt Decision Transformers for UAV-Assisted Communications with AoI

Chi Lu, Yiyang Ni, Zhe Wang, Xiaoli Shi, Jun Li, Shi Jin

专题命中 规划推理 ：planning(abstract)

Revenue Optimization in Wireless Video Caching Networks: A Privacy-Preserving Two-Stage Solution

Yijing Zhang, Md-Ferdous Pervej, Andreas F. Molisch

专题命中 规划推理 ：planning(abstract)

Comments Under review for possible publication in the IEEE Transactions on Communications

An Appraisal-Based Approach to Human-Centred Explanations

Rukshani Somarathna, Madhawa Perera, Tom Gedeon, Matt Adcock

专题命中 规划推理 ：reasoning(abstract)

Multimodal 3D Reasoning Segmentation with Complex Scenes

Xueying Jiang, Lewei Lu, Ling Shao, Shijian Lu

专题命中 视觉空间推理 ：reasoning(title,abstract)

Kestrel: 3D Multimodal LLM for Part-Aware Grounded Description

Mahmoud Ahmed, Junjie Fei, Jian Ding, Eslam Mohamed Bakr, Mohamed Elhoseiny

机构 * King Abdullah University of Science and Technology（卡斯特大学） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)；分类 cs.CL

Boosting Robotic Manipulation Generalization with Minimal Costly Data

Liming Zheng, Feng Yan, Fanfan Liu, Chengjian Feng, Yufeng Zhong, Lin Ma

专题命中 视觉空间推理 ：reasoning(abstract)；分类 cs.LG

Evaluating Variance in Visual Question Answering Benchmarks

Nikitha SR

机构 * Media and Data Science Research Lab, Adobe（媒体与数据科学研究实验室，Adobe） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)

Comments Accepted in ICCV 2025 Workshop on What's Next in Multimodal Foundational Models

EfficientGFormer: Multimodal Brain Tumor Segmentation via Pruned Graph-Augmented Transformer

Fatemeh Ziaeetabar

机构 * School of Mathematics, Statistics and Computer Science, College of Science, University of Tehran（数学、统计与计算机科学学院，科学学院，德黑兰大学） ； University of Tehran（德黑兰大学） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)

BAR Conjecture: the Feasibility of Inference Budget-Constrained LLM Services with Authenticity and Reasoning

Jinan Zhou, Rajat Ghosh, Vaishnavi Bhargava, Debojyoti Dutta, Aryan Singhal

机构 * Nutanix 纠错

专题命中 测试时计算 ：reasoning(title,abstract)；分类 cs.LG

CTR-Driven Ad Text Generation via Online Feedback Preference Optimization

Yanda Chen, Zihui Ren, Qixiang Gao, Jiale Chen, Si Chen, Xubin Li, Tiezheng Ge, Bo Zheng

专题命中 测试时计算 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)

Comments 13 pages, 7 figures, 8 tables

Scaling Vision Pre-Training to 4K Resolution

Baifeng Shi, Boyi Li, Han Cai, Yao Lu, Sifei Liu, Marco Pavone, Jan Kautz, Song Han, Trevor Darrell, Pavlo Molchanov, Hongxu Yin

机构 * UC Berkeley（加州大学伯克利分校） ； NVIDIA（英伟达） 纠错

专题命中 测试时计算 ：test-time compute(abstract)

Comments CVPR 2025. Project Page: https://nvlabs.github.io/PS3

Hierarchical Reasoning Model

Guan Wang, Jin Li, Yuhao Sun, Xing Chen, Changling Liu, Yue Wu, Meng Lu, Sen Song, Yasin Abbasi Yadkori

机构 * Sapient Intelligence 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)；chain-of-thought(abstract)；CoT(abstract)；planning(abstract)

Accelerating LLM Reasoning via Early Rejection with Partial Reward Modeling

Seyyed Saeid Cheshmi, Azal Ahmad Khan, Xinran Wang, Zirui Liu, Ali Anwar

机构 * University of Minnesota（明尼苏达大学） 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)；math reasoning(abstract)；分类 cs.AI、cs.LG

Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models

Linan Yue, Yichao Du, Yizhi Wang, Weibo Gao, Fangzhou Yao, Li Wang, Ye Liu, Ziyu Xu, Qi Liu, Shimin Di, Min-Ling Zhang

机构 * School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院） ； Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education（教育部计算机网络与信息集成重点实验室） ； University of Science and Technology of China（中国科学技术大学） ； Alibaba Group（阿里巴巴集团） 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)；chain-of-thought(abstract)；分类 cs.AI

Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following

Qingyu Ren, Qianyu He, Bowei Zhang, Jie Zeng, Jiaqing Liang, Yanghua Xiao, Weikang Zhou, Zeye Sun, Fei Yu

机构 * Shanghai Key Laboratory of Data Science, College of Computer Science and Artificial Intelligence, Fudan University（上海数据科学关键实验室，计算机科学与人工智能学院，复旦大学） ； School of Data Science, Fudan University（数据科学学院，复旦大学） ； Ant Group（蚂蚁集团） 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.AI

Multi-Object Sketch Animation by Scene Decomposition and Motion Planning

Jingyu Liu, Zijie Xin, Yuhan Fu, Ruixiang Zhao, Bangxiang Lan, Xirong Li

专题命中 复杂问题求解 ：planning(title,abstract)

Comments Accepted by ICCV 2025

Tree-of-Code: A Tree-Structured Exploring Framework for End-to-End Code Generation and Execution in Complex Task Handling

Ziyi Ni, Yifan Li, Ning Yang, Dou Shen, Pin Lv, Daxiang Dong

机构 * The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（认知与决策智能复杂系统重点实验室，自动化研究所，中国科学院） ； School of Artificial Intelligence, University of Chinese Academy of Science（人工智能学院，中国科学院大学） ； Baidu, Inc.（百度公司） ； Global Innovation Exchange Institution, Tsinghua University（全球创新交换机构，清华大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract,comments)；分类 cs.AI

Comments This idea was first submitted to the NeuralPS Workshop "System 2 Reasoning At Scale" in September 2024. Its OpenReview: https://openreview.net/forum?id=8NKAL8Ngxk&noteId=8NKAL8Ngxk. It was then submitted to the NAACL 2025 in October 2024, which is recorded in: https://openreview.net/forum?id=S0ZUWD3Vy5&noteId=S0ZUWD3Vy5. Now this paper has been accepted for publication in ACL 2025 Findings

CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization

Yixi Ding, Jiaying Wu, Tongyao Zhu, Yanxia Qin, Qian Liu, Min-Yen Kan

机构 * National University of Singapore（新加坡国立大学） ； Singapore University of Technology and Design（新加坡科技设计大学） ； Sea AI Lab（Sea AI实验室） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL

Comments Accepted to KDD 2025 SciSoc LLM Workshop: Large Language Models for Scientific and Societal Advances

T-GRAG: A Dynamic GraphRAG Framework for Resolving Temporal Conflicts and Redundancy in Knowledge Retrieval

Dong Li, Yichen Niu, Ying Ai, Xiang Zou, Biqing Qi, Jianxing Liu

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI

Transformers in Pseudo-Random Number Generation: A Dual Perspective on Theory and Practice

Ran Li, Lingshu Zeng

机构 * Ran Li School of Information Science and Technology, Northeast Normal University, Changchun, China（Ran Li 信息科学与技术学院，东北师范大学，中国长春） 纠错

专题命中 复杂问题求解 ：chain-of-thought(abstract)；分类 cs.LG

Comments 27 pages, 4 figures

Intent-Based Network for RAN Management with Large Language Models

Fransiscus Asisi Bimo, Maria Amparo Canaveras Galdon, Chun-Kai Lai, Ray-Guang Cheng, Edwin K. P. Chong

机构 * National Taiwan University of Science and Technology（台湾科技大学） ； NVIDIA（NVIDIA公司） ； Colorado State University（科罗拉多州立大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI

Comments 5 pages, 3 figures, submitted to IEEE Globecom 2025

WIP: Enhancing Game-Based Learning with AI-Driven Peer Agents

Chengzhang Zhu, Cecile H. Sam, Yanlai Wu, Ying Tang

专题命中 复杂问题求解 ：reasoning(abstract)

KeyMPs: One-Shot Vision-Language Guided Motion Generation by Sequencing DMPs for Occlusion-Rich Tasks

Edgar Anarossi, Yuhwan Kwon, Hirotaka Tahara, Shohei Tanaka, Keisuke Shirai, Masashi Hamaya, Cristian C. Beltran-Hernandez, Atsushi Hashimoto, Takamitsu Matsubara

机构 * Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology（信息科学系，科学技术研究生学校，科学技术研究所） ； Department of Electrical and Electronic Engineering, Faculty of Engineering Science, Kansai University（电气电子工程系，工学科学大学） ； Department of Electronics, Kobe City College of Technology（电子系，神户市立技术学院） ； OMRON SINIC X Corporation（OMRON SINIC X公司） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

Comments Published in IEEE Access, Jul 14 2025

Journal ref IEEE Access, vol. 13, pp. 125420-125441, 2025

Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models

Yule Liu, Jingyi Zheng, Zhen Sun, Zifan Peng, Wenhan Dong, Zeyang Sha, Shiwen Cui, Weiqiang Wang, Xinlei He

专题命中 推理评测 ：reasoning(title,abstract)；CoT(abstract)；分类 cs.CL、cs.AI

TripTailor: A Real-World Benchmark for Personalized Travel Planning

Yuanzhe Shen, Kaimin Wang, Changze Lv, Xiaoqing Zheng, Xuanjing Huang

机构 * School of Computer Science, Fudan University（复旦大学计算机科学学院） 纠错

专题命中 推理评测 ：planning(title,abstract)；reasoning(abstract)；分类 cs.AI

Comments Accepted to ACL 2025 Findings