语言大模型 / LLM

Long-Context Modeling Networks for Monaural Speech Enhancement: A Comparative Study

Qiquan Zhang, Moran Chen, Zeyang Song, Hexin Liu, Xiangyu Zhang, Haizhou Li

专题命中 长上下文与记忆 ：language model(abstract)

Comments Accepted by WASPAA 2025, 5 pages

Journal ref WASPAA 2025

SAMed-2: Selective Memory Enhanced Medical Segment Anything Model

Zhiling Yan, Sifan Song, Dingjie Song, Yiwei Li, Rong Zhou, Weixiang Sun, Zhennong Chen, Sekeun Kim, Hui Ren, Tianming Liu, Quanzheng Li, Xiang Li, Lifang He, Lichao Sun

机构 * Lehigh University, Bethlehem, PA, USA（莱斯大学） ； Massachusetts General Hospital（麻省总医院） ； Harvard Medical School（哈佛医学院） ； University of Georgia, Athens, GA, USA（佐治亚大学） ； University of Notre Dame, Notre Dame, IN, USA（Notre Dame 大学） 纠错

专题命中 长上下文与记忆 ：foundation model(abstract)

Comments Accepted by MICCAI 2025

Leveraging Transformer Models to Capture Multi-Scale Dynamics in Biomolecules by nano-GPT

Wenqi Zeng, Lu Zhang, Yuan Yao

专题命中 长上下文与记忆 ：language model(abstract)

MobileRAG: A Fast, Memory-Efficient, and Energy-Efficient Method for On-Device RAG

Taehwan Park, Geonho Lee, Min-Soo Kim

专题命中 长上下文与记忆 ：language model(abstract)

Comments 14 pages

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation

Shuaiye Lu, Linjiang Zhou, Xiaochuan Shi

机构 * Wuhan University（武汉大学） 纠错

专题命中 长上下文与记忆 ：language model(abstract)

Memory-enhanced Retrieval Augmentation for Long Video Understanding

Huaying Yuan, Zheng Liu, Minghao Qin, Hongjin Qian, Yan Shu, Zhicheng Dou, Ji-Rong Wen, Nicu Sebe

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学光华学院人工智能学院） ； Beijing Academy of Artificial Intelligence（北京人工智能研究院） ； University of Trento（特伦托大学） ； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） 纠错

专题命中 长上下文与记忆 ：language model(abstract)

GenUP: Generative User Profilers as In-Context Learners for Next POI Recommender Systems

Wilson Wongso, Hao Xue, Flora D. Salim

专题命中 长上下文与记忆 ：LLM(abstract)

DyNaVLM: Zero-Shot Vision-Language Navigation System with Dynamic Viewpoints and Self-Refining Graph Memory

Zihe Ji, Huangxuan Lin, Yue Gao

机构 * SJTU Paris Elite Institute of Technology, Shanghai Jiao Tong University（上海交通大学巴黎精英技术研究所） ； Department of Automation, Shanghai Jiao Tong University（上海交通大学自动化系） ； MoE Key Lab of Artificial Intelligence and AI Institute, Shanghai Jiao Tong University（上海交通大学人工智能与AI研究所） 纠错

专题命中 长上下文与记忆 ：language model(abstract)

Object Concepts Emerge from Motion

Haoqian Liang, Xiaohui Wang, Zhichao Li, Ya Yang, Naiyan Wang

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Xiaomi EV（小米电动车） 纠错

专题命中 长上下文与记忆 ：foundation model(abstract)

Flashback: Memory-Driven Zero-shot, Real-time Video Anomaly Detection

Hyogun Lee, Haksub Kim, Ig-Jae Kim, Yonghun Choi

机构 * Korea Institute of Science and Technology (KIST)（韩国科学技术院） 纠错

专题命中 长上下文与记忆 ：LLM(abstract)

Comments 12 pages, 5 figures

Unlocking the Power of SAM 2 for Few-Shot Segmentation

Qianxiong Xu, Lanyun Zhu, Xuanyi Liu, Guosheng Lin, Cheng Long, Ziyue Li, Rui Zhao

专题命中 长上下文与记忆 ：foundation model(abstract)

Comments This paper is accepted by ICML'25

Search is All You Need for Few-shot Anomaly Detection

Qishan Wang, Jia Guo, Shuyong Gao, Haofen Wang, Li Xiong, Junjie Hu, Hanqi Guo, Wenqiang Zhang

机构 * Academy for Engineering and Technology Fudan University（复旦大学工程与技术学院） ； School of Biomedical Engineering Tsinghua University（清华大学生物医学工程学院） ； School of Computer Science Fudan university（复旦大学计算机学院） ； College of Design & Innovation Tongji University（同济大学设计与创新学院） ； School of Physics and Mechanical & Electrical Engineering Hexi University（河西大学物理与机械电子工程学院） ； Engineering Research Center of AI&Robotics, Ministry of Education（教育部人工智能与机器人工程研究中心） ； Academy for Engineering&Technology Fudan university（复旦大学工程与技术学院） 纠错

专题命中 长上下文与记忆 ：foundation model(abstract)

MoSAM: Motion-Guided Segment Anything Model with Spatial-Temporal Memory Selection

Qiushi Yang, Yuan Yao, Miaomiao Cui, Liefeng Bo

机构 * Institute for Intelligent Computing（智能计算研究院） 纠错

专题命中 长上下文与记忆 ：prompting(abstract)

Rethinking PM Crash Consistency in the CXL Era

João Oliveira, João Gonçalves, Miguel Matos

专题命中 长上下文与记忆 ：prompting(abstract)

Comments 5 pages (2 extra pages for references), 1 figure, 2 algorithms

Analysis of Attention in Video Diffusion Transformers

Yuxin Wen, Jim Wu, Ajay Jain, Tom Goldstein, Ashwinee Panda

专题命中 长上下文与记忆 ：language model(abstract)

Autono: A ReAct-Based Highly Robust Autonomous Agent Framework

Zihao Wu

专题命中 长上下文与记忆 ：LLM(abstract)

Comments 10 pages, 3 figures

DynFocus: Dynamic Cooperative Network Empowers LLMs with Video Understanding

Yudong Han, Qingpei Guo, Liyuan Pan, Liu Liu, Yu Guan, Ming Yang

专题命中 长上下文与记忆 ：LLM(abstract)

Comments Accepted by CVPR 25

CHOIR: Chat-based Helper for Organizational Intelligence Repository

Sangwook Lee, Adnan Abbas, Yan Chen, Sang Won Lee

专题命中 长上下文与记忆 ：prompting(abstract)

Comments 4 pages

Towards Fast, Memory-based and Data-Efficient Vision-Language Policy

Haoxuan Li, Sixu Yan, Yuhan Li, Xinggang Wang

专题命中 长上下文与记忆 ：language model(abstract)

Comments 11 pages, 7 figures, 6 tables

Bayesian Fields: Task-driven Open-Set Semantic Gaussian Splatting

Dominic Maggio, Luca Carlone

专题命中 长上下文与记忆 ：foundation model(abstract)

Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding

Xingjian Diao, Chunhui Zhang, Weiyi Wu, Zhongyu Ouyang, Peijun Qing, Ming Cheng, Soroush Vosoughi, Jiang Gui

专题命中 长上下文与记忆 ：foundation model(abstract)

Comments Accepted at NAACL 2025

MemPal: Leveraging Multimodal AI and LLMs for Voice-Activated Object Retrieval in Homes of Older Adults

Natasha Maniar, Samantha W. T. Chan, Wazeer Zulfikar, Scott Ren, Christine Xu, Pattie Maes

专题命中 长上下文与记忆 ：LLM(abstract)

Comments 15 pages

Optical fibres with memory effects and their quantum communication capacities

Francesco Anna Mele, Giacomo De Palma, Marco Fanizza, Vittorio Giovannetti, Ludovico Lami

专题命中 长上下文与记忆 ：prompting(abstract)

Comments In the second version, we improved the presentation of our results

Journal ref IEEE Transactions on Information Theory 70(12), 8844-8869 (2024)

LVP-CLIP:Revisiting CLIP for Continual Learning with Label Vector Pool

Yue Ma, Huantao Ren, Boyu Wang, Jingang Jin, Senem Velipasalar, Qinru Qiu

专题命中 长上下文与记忆 ：language model(abstract)

Comments submitted to CVPR2025

Towards Real-Time Open-Vocabulary Video Instance Segmentation

Bin Yan, Martin Sundermeyer, David Joseph Tan, Huchuan Lu, Federico Tombari

专题命中 长上下文与记忆 ：foundation model(abstract)

A dynamic parallel method for performance optimization on hybrid CPUs

Luo Yu, Liu Yucheng, Shen Haihao

专题命中 长上下文与记忆 ：LLM(abstract)

LiVOS: Light Video Object Segmentation with Gated Linear Matching

Qin Liu, Jianfeng Wang, Zhengyuan Yang, Linjie Li, Kevin Lin, Marc Niethammer, Lijuan Wang

专题命中 长上下文与记忆 ：foundation model(abstract)

Comments Code&models: https://github.com/uncbiag/LiVOS

BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping

Taolin Zhang, Jinpeng Wang, Hang Guo, Tao Dai, Bin Chen, Shu-Tao Xia

专题命中 长上下文与记忆 ：language model(abstract)

Comments NeurIPS 2024

Remember and Recall: Associative-Memory-based Trajectory Prediction

Hang Guo, Yuzhen Zhang, Tianci Gao, Junning Su, Pei Lv, Mingliang Xu

专题命中 长上下文与记忆 ：language model(abstract)

MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion

Bardienus Duisterhof, Lojze Zust, Philippe Weinzaepfel, Vincent Leroy, Yohann Cabon, Jerome Revaud

专题命中 长上下文与记忆 ：foundation model(abstract)