arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of Science and Technology of China(中国科学技术大学)

2026-01-27 至 2026-01-27 共收录 15
2601.18733 2026-01-27 cs.RO cs.AI cs.CV

Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge

多智能体机器人系统(MARS)挑战的进展与创新

Li Kang, Heng Zhou, Xiufeng Song, Rui Li, Bruno N. Y. Chen, Ziye Wang, Ximeng Meng, Stone Tao, Yiran Qin, Xiaohong Liu, Ruimao Zhang, Lei Bai, Yilun Du, Hao Su, Philip Torr, Zhenfei Yin, Ruihao Gong, Yejun Zeng, Fengjun Zhong, Shenghao Jin, Jinyang Guo, Xianglong Liu, Xiaojun Jia, Tianqi Shan, Wenqi Ren, Simeng Qin, Jialing Yang, Xiaoyu Ma, Tianxing Chen, Zixuan Li, Zijian Cai, Yan Qin, Yusen Qin, Qiangyu Chen, Kaixuan Wang, Zhaoming Han, Yao Mu, Ping Luo, Yuanqi Yao, Haoming Song, Jan-Nico Zaech, Fabien Despinoy, Danda Pani Paudel, Luc Van Gool

机构 * SJTU(上海交通大学) Oxford(牛津大学) USTC(中国科学技术大学) Shanghai AI Lab(上海人工智能实验室) CMU(卡内基梅隆大学) HKU(香港大学) Tongji(同济大学) UC San Diego(南加州大学) CUHK-SZ(香港中文大学(深圳)) SYSU(华南理工大学) Harvard(哈佛大学)

AI总结 MARS挑战通过多智能体具身规划与控制任务,推动多智能体协作AI系统的发展。

Comments MARS Challenge @ NeurIPS 2025 Workshop on Space in Vision, Language, and Embodied AI. Challenge page: https://mars-eai.github.io/MARS-Challenge-Webpage/

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.18189 2026-01-27 cs.LG

Smooth, Sparse, and Stable: Finite-Time Exact Skeleton Recovery via Smoothed Proximal Gradients

平滑、稀疏且稳定:通过平滑近端梯度实现有限时间精确骨架恢复

Rui Wu, Yongjun Li

机构 * School of Management, University of Science and Technology of China(管理学院,中国科学技术大学)

AI总结 本文提出平滑近端梯度算法SPG-AHOC,通过混合顺序无环约束在有限时间内精确恢复因果图结构,解决了连续优化与离散图结构之间的根本性挑战。

Comments 20 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.11233 2026-01-27 cs.AI

STaR: Towards Effective and Stable Table Reasoning via Slow-Thinking Large Language Models

STaR:通过慢思考大语言模型实现有效的稳定表格推理

Huajian Zhang, Mingyue Cheng, Yucong Luo, Xiaoyu Tao

机构 * State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China(认知智能国家重点实验室,中国科学技术大学)

AI总结 STaR通过慢思考机制提升表格推理的有效性和稳定性,采用两阶段训练框架和不确定性量化技术,在领域内和领域外均取得优异表现。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.07713 2026-01-27 cs.CL

MemWeaver: A Hierarchical Memory from Textual Interactive Behaviors for Personalized Generation

MemWeaver: 一种从文本交互行为构建的分层记忆用于个性化生成

Shuo Yu, Mingyue Cheng, Daoyu Wang, Qi Liu, Zirui Liu, Ze Guo, Xiaoyu Tao

机构 * State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China(认知智能国家重点实验室,中国科学技术大学)

AI总结 MemWeaver通过构建分层记忆模型,利用文本交互行为捕捉用户兴趣的时间演变和语义关系,实现深度个性化内容生成。

Comments Accepted by The Web Conference 2026 (WWW'26) 12 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01327 2026-01-27 cs.LG cs.AI

Enhancing Federated Class-Incremental Learning via Spatial-Temporal Statistics Aggregation

通过时空统计聚合增强联邦类增量学习

Zenghao Guan, Guojun Zhu, Yucan Zhou, Wu Liu, Weiping Wang, Jiebo Luo, Xiaoyan Gu

机构 * University of Chinese Academy of Sciences(中国科学院大学) Tianjin University(天津大学) University of Science and Technology of China(中国科学技术大学) University of Rochester(罗切斯特大学) State Key Laboratory of Cyberspace Security Defense, Institute of Information Engineering(信息工程研究所网络空间安全防御国家重点实验室)

AI总结 本文提出STSA方法,通过时空统计聚合提升联邦类增量学习的性能,减少通信开销,适用于异构数据场景。

Comments WWW 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.17897 2026-01-27 cs.AI

UniCog: Uncovering Cognitive Abilities of LLMs through Latent Mind Space Analysis

UniCog: 通过潜在思维空间分析揭示大语言模型的认知能力

Jiayu Liu, Yinhe Long, Zhenya Huang, Enhong Chen

机构 * State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China(认知智能国家重点实验室,中国科学技术大学)

AI总结 UniCog通过潜在思维空间分析揭示大语言模型的认知能力,提出统一框架并提升推理性能

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.17789 2026-01-27 cs.AI

Neuro-Symbolic Verification on Instruction Following of LLMs

神经符号验证在大语言模型指令遵循上的应用

Yiming Su, Kunzhao Xu, Yanjie Gao, Fan Yang, Cheng Li, Mao Yang, Tianyin Xu

机构 * University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) University of Science and Technology of China(中国科学技术大学) Microsoft Research(微软研究院)

AI总结 本文提出NSVIF框架,通过神经符号方法验证大语言模型是否遵循指令,实验表明其在指令遵循验证中表现优异。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.17761 2026-01-27 cs.LG cs.AI cs.CL

AR-Omni: A Unified Autoregressive Model for Any-to-Any Generation

AR-Omni:一种统一的自回归模型用于任意到任意生成

Dongjie Cheng, Ruifeng Yuan, Yongqi Li, Runyang You, Wenjie Wang, Liqiang Nie, Lei Zhang, Wenjie Li

机构 * The Hong Kong Polytechnic University(香港理工大学) University of Science and Technology of China(中国科学技术大学) Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳))

AI总结 AR-Omni提出一种无需专家解码器的统一自回归模型,实现多模态任意到任意生成,解决模态不平衡、视觉保真度和稳定性与创造力平衡问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.17711 2026-01-27 cs.SD cs.AI eess.AS

CaSNet: Compress-and-Send Network Based Multi-Device Speech Enhancement Model for Distributed Microphone Arrays

CaSNet:基于压缩-发送网络的多设备语音增强模型用于分布式麦克风阵列

Chengqian Jiang, Jie Zhang, Haoyin Yan

机构 * NERC-SLIP, University of Science and Technology of China (USTC)(NERC-SLIP,中国科学技术大学)

AI总结 CaSNet是一种用于分布式麦克风阵列的压缩-发送网络,通过特征压缩和神经解码提升语音增强性能,减少带宽和能耗。

Comments this paper has been accept by ICASSP2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.17438 2026-01-27 cs.IR cs.LG

UniGRec: Unified Generative Recommendation with Soft Identifiers for End-to-End Optimization

UniGRec: 一种基于软标识符的统一生成推荐方法用于端到端优化

Jialei Li, Yang Zhang, Yimeng Bai, Shuai Zhu, Ziqi Xue, Xiaoyan Zhao, Dingxian Wang, Frank Yang, Andrew Rabinovich, Xiangnan He

机构 * University of Science and Technology of China(科学技术大学) National University of Singapore(国立新加坡大学) The Chinese University of Hong Kong(香港中文大学)

AI总结 UniGRec通过统一生成推荐框架解决端到端优化中的软标识符问题,提出退火推理对齐、码字均匀性正则化和双协作蒸馏机制,提升推荐性能。

Comments 11 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.17366 2026-01-27 cs.CV

UCAD: Uncertainty-guided Contour-aware Displacement for semi-supervised medical image segmentation

UCAD: 基于不确定性的轮廓感知位移用于半监督医学图像分割

Chengbo Ding, Fenghe Tang, Shaohua Kevin Zhou

机构 * University of Science and Technology of China(科学技术大学) Suzhou Institute for Advanced Research(苏州先进研究院) State Key Laboratory of Precision and Intelligent Chemistry(精密与智能化学国家重点实验室)

AI总结 UCAD通过基于不确定性的轮廓感知位移框架,提升半监督医学图像分割的准确性和一致性学习效果。

Comments Accepted by ISBI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.13256 2026-01-27 math.NA cs.LG cs.NA

Deep Neural networks for solving high-dimensional parabolic partial differential equations

深度神经网络求解高维抛物型偏微分方程

Wenzhong Zhang, Zheyuan Hu, Wei Cai, George EM Karniadakis

机构 * Suzhou Institute for Advanced Research, University of Science and Technology of China(中国科学技术大学苏州研究院) Department of Mathematics, Southern Methodist University(南方法国大学数学系) Department of Computer Science, School of Computing, National University of Singapore(新加坡国立大学计算机科学系) Department of Mathematics, Southern Methodist University (SMU)(南方法国大学数学系) Division of Applied Mathematics, Brown University(布朗大学应用数学系)

AI总结 本文介绍了利用深度神经网络求解高维抛物型PDEs的方法,探讨了三种主要范式及其应用,展示了方法的可扩展性和有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.24330 2026-01-27 cs.CV

SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning

SenseNova-MARS: 通过强化学习赋能多模态代理推理与搜索

Yong Xien Chng, Tao Hu, Wenwen Tong, Xueheng Li, Jiandong Chen, Haojia Yu, Jiefan Lu, Hewei Guo, Hanming Deng, Chengjun Xie, Gao Huang, Dahua Lin, Lewei Lu

机构 * SenseTime Research(商汤科技研究院) Tsinghua University(清华大学) University of Science and Technology of China(中国科学技术大学)

AI总结 SenseNova-MARS通过强化学习赋能多模态代理推理与搜索,提升视觉-语言模型在复杂视觉任务中的表现。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.13390 2026-01-27 cs.CV

Generalizing WiFi Gesture Recognition via Large-Model-Aware Semantic Distillation and Alignment

通过大模型感知的语义蒸馏与对齐实现WiFi手势识别的泛化

Feng-Qi Cui, Yu-Tong Guo, Tianyue Zheng, Jinyang Huang

机构 * Institute of Advanced Technology, University of Science and Technology of China(科学技术大学先进技术研究院) School of Computer Science and Information Engineering, Hefei University of Technology(合肥工业大学计算机科学与信息工程学院) School of Computer Science and Engineering, Southern University of Science and Technology(南方科技大学计算机科学与工程学院)

AI总结 GLSDA通过大模型感知的语义蒸馏与对齐提升WiFi手势识别的泛化能力,实现领域内和跨领域任务的高性能识别。

Comments Accepted by IEEE ICPADS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.16986 2026-01-27 cs.CL cs.AI cs.LG

Crystal-KV: Efficient KV Cache Management for Chain-of-Thought LLMs via Answer-First Principle

Crystal-KV: 通过答案优先原则高效管理链式推理LLM的KV缓存

Zihan Wang, Cheng Tang, Lei Gong, Cheng Li, Chao Wang, teng wang, Wenqi Lou, Xuehai Zhou

机构 * School of Computer Science and Technology, University of Science and Technology of China(计算机科学与技术学院,中国科学技术大学) University of Science and Technology of China(中国科学技术大学) Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(人工智能研究所,合肥综合性国家科学中心) Suzhou Institute for Advanced Research, University of Science and Technology of China(苏州先进研究院,中国科学技术大学)

AI总结 Crystal-KV通过答案优先原则高效管理链式推理LLM的KV缓存,提升缓存压缩和推理效率。

详情

展开后加载摘要…

URL PDF HTML 收藏