语言大模型 / LLM

Neural Computation Without Slots: Steps Towards Biologically Plausible Memory and Attention in Natural and Artificial Intelligence

Shaunak Bhandarkar, James L. McClelland

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

Comments 19 main text pages, 7 main text figures; 33 supplementary pages, 13 supplementary figures

Explicit Memory through Online 3D Gaussian Splatting Improves Class-Agnostic Video Segmentation

Anthony Opipari, Aravindhan K Krishnan, Shreekant Gayaka, Min Sun, Cheng-Hao Kuo, Arnie Sen, Odest Chadwicke Jenkins

机构 * University of Michigan（密歇根大学） ； Amazon Inc.（亚马逊公司） 纠错

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

Comments Accepted in IEEE Robotics and Automation Letters September 2025

FidelityGPT: Correcting Decompilation Distortions with Retrieval Augmented Generation

Zhiping Zhou, Xiaohong Li, Ruitao Feng, Yao Zhang, Yuekang Li, Wenbu Feng, Yunqian Wang, Yuqing Li

专题命中 长上下文与记忆 ：LLM(abstract)

OmniVIC: A Self-Improving Variable Impedance Controller with Vision-Language In-Context Learning for Safe Robotic Manipulation

Heng Zhang, Wei-Hsing Huang, Gokhan Solak, Arash Ajoudani

机构 * Human-Robot Interfaces and Interaction Lab, Istituto Italiano di Tecnologia, Genoa, Italy（人机交互实验室，意大利理工学院，热那亚） ； Georgia Institute of Technology, Atlanta, USA（佐治亚理工学院，美国亚特兰大） 纠错

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

Comments Code, video and RAG dataset are available at \url{https://sites.google.com/view/omni-vic}

PFGS: Pose-Fused 3D Gaussian Splatting for Complete Multi-Pose Object Reconstruction

Ting-Yu Yen, Yu-Sheng Chiu, Shih-Hsuan Hung, Peter Wonka, Hung-Kuo Chu

机构 * National Tsing Hua University（清华大学） 纠错

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

Learning Hanzi Character Through VR-Based Mortise-Tenon

Conglin Ma, Jiatong Li, Sen-Zhe Xu, Ju Dai, Jie Liu, Feng Zhou

专题命中 长上下文与记忆 ：LLM(abstract)

LSVOS 2025 Challenge Report: Recent Advances in Complex Video Object Segmentation

Chang Liu, Henghui Ding, Kaining Ying, Lingyi Hong, Ning Xu, Linjie Yang, Yuchen Fan, Mingqi Gao, Jingkun Chen, Yunqi Miao, Gengshen Wu, Zhijin Qin, Jungong Han, Zhixiong Zhang, Shuangrui Ding, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Jiaqi Wang, Chang Soo Lim, Joonyoung Moon, Donghyeon Cho, Tingmin Li, Yixuan Li, Yang Yang, An Yan, Leilei Cao, Feng Lu, Ran Hong, Youhai Jiang, Fengjie Zhu, Yujie Xie, Hongyang Zhang, Zhihui Liu, Shihai Ruan, Quanzhu Niu, Dengxian Gong, Shihao Chen, Tao Zhang, Yikang Zhou, Haobo Yuan, Lu Qi, Xiangtai Li, Shunping Ji, Ran Hong, Feng Lu, Leilei Cao, An Yan, Alexey Nekrasov, Ali Athar, Daan de Geus, Alexander Hermans, Bastian Leibe

专题命中 长上下文与记忆 ：LLM(abstract)

Comments 16 pages, 9 figures

Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

Lin Long, Yichen He, Wentao Ye, Yiyuan Pan, Yuan Lin, Hang Li, Junbo Zhao, Wei Li

机构 * Zhejiang University（浙江大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

专题命中 长上下文与记忆 ：prompting(abstract)

VGGT-X: When VGGT Meets Dense Novel View Synthesis

Yang Liu, Chuanchen Luo, Zimo Tang, Junran Peng, Zhaoxiang Zhang

机构 * NLPR, MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所国家智能机器人实验室、智能信息所） ； University of Chinese Academy of Sciences（中国科学院大学） ； Huazhong University of Science and Technology（华中科技大学） ； Shandong University（山东大学） ； University of Science and Technology Beijing（北京科技大学） ； Linketic 纠错

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

Comments Project Page: https://dekuliutesla.github.io/vggt-x.github.io/

Learning Frequency and Memory-Aware Prompts for Multi-Modal Object Tracking

Boyue Xu, Ruichao Hou, Tongwei Ren, Dongming zhou, Gangshan Wu, Jinde Cao

机构 * State Key Laboratory for Novel Software Technology（新型软件技术国家重点实验室） ； School of Information Science and Engineering（信息科学与工程学院） ； School of Mathematics（数学学院） ； Purple Mountain Laboratories（紫金山实验室） 纠错

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

SSR-ZSON: Zero-Shot Object Navigation via Spatial-Semantic Relations within a Hierarchical Exploration Framework

Xiangyi Meng, Delun Li, Zihao Mao, Yi Yang, Wenjie Song

机构 * School of Automation, Beijing Institute of Technology（自动化学院，北京理工大学） 纠错

专题命中 长上下文与记忆 ：LLM(abstract)

Interpretable Embeddings of Speech Enhance and Explain Brain Encoding Performance of Audio Models

Riki Shimizu, Richard J. Antonello, Chandan Singh, Nima Mesgarani

机构 * Mortimer B. Zuckerman Mind Brain Behavior Institute（莫蒂默·B·齐克曼脑行为研究所） ； Columbia University（哥伦比亚大学） ； Microsoft Research（微软研究院） 纠错

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

Comments 19 pages, 5 figures

AnchoredAI: Contextual Anchoring of AI Comments Improves Writer Agency and Ownership

Martin Lou, Jackie Crowley, Samuel Dodson, Dongwook Yoon

专题命中 长上下文与记忆 ：LLM(abstract)

Static or Dynamic: Towards Query-Adaptive Token Selection for Video Question Answering

Yumeng Shi, Quanyu Long, Wenya Wang

机构 * Nanyang Technological University（南洋理工大学） 纠错

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

Comments Accepted to EMNLP 2025 (main)

ForestSplats: Deformable transient field for Gaussian Splatting in the Wild

Wongi Park, Myeongseok Nam, Siwon Kim, Sangwoo Jo, Soomok Lee

机构 * Ajou University（阿乔大学） ； Minds and Company（Mind and Company） 纠错

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

Memory-Anchored Multimodal Reasoning for Explainable Video Forensics

Chen Chen, Runze Li, Zejun Zhang, Pukun Zhao, Fanqing Zhou, Longxiang Wang, Haojian Huang

专题命中 长上下文与记忆 ：pretraining(abstract)

GRACE: Graph-Guided Repository-Aware Code Completion through Hierarchical Code Fusion

Xingliang Wang, Baoyi Wang, Chen Zhi, Junxiao Han, Xinkui Zhao, Jianwei Yin, Shuiguang Deng

专题命中 长上下文与记忆 ：LLM(abstract)

GestoBrush: Facilitating Graffiti Artists' Digital Creation Experiences through Embodied AR Interactions

Ruiqi Chen, Qingyang He, Hanxi Bao, Jung Choi, Xin Tong

专题命中 长上下文与记忆 ：prompting(abstract)

Comments Accepted to VINCI 2025; 8 pages, 3 figures

Spatially-Enhanced Recurrent Memory for Long-Range Mapless Navigation via End-to-End Reinforcement Learning

Fan Yang, Per Frivik, David Hoeller, Chen Wang, Cesar Cadena, Marco Hutter

机构 * 1 Robotic Systems Lab, ETH Zurich, Zurich, Switzerland 2 Spatial AI \& Robotics Lab, University at Buffalo, Buffalo, NY, USA 纠错

专题命中 长上下文与记忆 ：pretraining(abstract)

Comments 22 pages

Txt2Sce: Scenario Generation for Autonomous Driving System Testing Based on Textual Reports

Pin Ji, Yang Feng, Zongtai Li, Xiangchi Zhou, Jia Liu, Jun Sun, Zhihong Zhao

专题命中 长上下文与记忆 ：LLM(abstract)

Content-Aware Foveated Camera for Multi-Target Tracking

Zihan Zang, Do Young Kim, Yifeng Zeng, Liang Gao

专题命中 长上下文与记忆 ：SLM(abstract)

Enhancing Document VQA Models via Retrieval-Augmented Generation

Eric López, Artemis Llabrés, Ernest Valveny

机构 * Computer Vision Center, Universitat Autònoma de Barcelona, Spain（巴塞罗那自治大学计算机视觉中心） 纠错

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

Comments Accepted at Workshop on Machine Learning in Document Analysis and Recognition (ICDAR WML 2025), Wuhan, China

MAG-Nav: Language-Driven Object Navigation Leveraging Memory-Reserved Active Grounding

Weifan Zhang, Tingguang Li, Yuzhen Liu

机构 * Tencent Robotics X（腾讯机器人X） ； Harbin Institute of Technology（哈尔滨工业大学） 纠错

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

SAMITE: Position Prompted SAM2 with Calibrated Memory for Visual Object Tracking

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

机构 * Nanyang Technological University（南洋理工大学） ； Singapore University of Technology and Design（新加坡科技设计大学） ； University of Cologne（科隆大学） ； SenseTime Research（商汤科技研究院） 纠错

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

RANa: Retrieval-Augmented Navigation

Gianluca Monaci, Rafael S. Rezende, Romain Deffayet, Gabriela Csurka, Guillaume Bono, Hervé Déjean, Stéphane Clinchant, Christian Wolf

机构 * Naver Labs Europe（纳维尔实验室欧洲） 纠错

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

SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree

Shuangrui Ding, Rui Qian, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Yuhang Cao, Yuwei Guo, Dahua Lin, Jiaqi Wang

机构 * The Chinese University of Hong Kong（香港中文大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； CPII under InnoHK（创新香港下的CPII） 纠错

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

Comments ICCV 2025, Project page: https://mark12ding.github.io/project/SAM2Long/ ; github page: https://github.com/Mark12Ding/SAM2Long/

Signatures of asymmetry: Gravitational wave memory and the parity violation

Indranil Chakraborty, Susmita Jana, S. Shankaranarayanan

专题命中 长上下文与记忆 ：prompting(abstract)

Comments References have been updated, and minor typos have been corrected. Matches with the published version in PRD letters

EchoVoices: Preserving Generational Voices and Memories for Seniors and Children

Haiying Xu, Haoze Liu, Mingshi Li, Siyu Cai, Guangxuan Zheng, Yuhuang Jia, Jinghua Zhao, Yong Qin

机构 * College of Computer Science, Nankai University（南开大学计算机科学学院） 纠错

专题命中 长上下文与记忆 ：LLM(abstract)

Portability of Optimizations from SC to TSO

Akshay Gopalakrishnan, Clark Verbrugge

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

Comments Submitted Manuscript. This pre-print has not undergone any post-review modifications/improvements

Evaluating the Critical Risks of Amazon's Nova Premier under the Frontier Model Safety Framework

Satyapriya Krishna, Ninareh Mehrabi, Abhinav Mohanty, Matteo Memelli, Vincent Ponzo, Payal Motwani, Rahul Gupta

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