语言大模型 / LLM

DreamGarden: A Designer Assistant for Growing Games from a Single Prompt

DreamGarden：基于单一提示生成游戏的设计师助手

Sam Earle, Samyak Parajuli, Andrzej Banburski-Fahey

机构 * New York University \& Microsoft USA ； Microsoft USA ； New York University \& Microsoft ； Microsoft 纠错

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.CL、cs.AI

AI总结 DreamGarden通过基于大语言模型的规划器，将用户提供的高层次提示转化为分层行动计划，实现多样化游戏环境的开发，探索半自动助手和开放性模拟设计的未来方向。

Comments 30 pages + appendix, 11 figures, published at CHI 2025

Don't Pay Attention

Mohammad Hammoud, Devang Acharya

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.CL、cs.AI

Gradual Forgetting: Logarithmic Compression for Extending Transformer Context Windows

Billy Dickson, Zoran Tiganj

机构 * Department of Computer Science, Indiana University Bloomington（计算机科学系，印第安纳大学布卢明顿分校） ； Department of Psychological and Brain Sciences, Indiana University Bloomington（心理学与脑科学系，印第安纳大学布卢明顿分校） 纠错

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.CL、cs.AI

LongCodeBench: Evaluating Coding LLMs at 1M Context Windows

Stefano Rando, Luca Romani, Alessio Sampieri, Luca Franco, John Yang, Yuta Kyuragi, Fabio Galasso, Tatsunori Hashimoto

机构 * Panasonic AI Research（松下人工智能研究） 纠错

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.CL、cs.AI

PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs

Xilong Cheng, Yunxiao Qin, Yuting Tan, Zhengnan Li, Ye Wang, Hongjiang Xiao, Yuan Zhang

机构 * Communication University of China（中国传媒大学） ； State Key Laboratory of Media Convergence and Communication（媒体融合与传播国家重点实验室） 纠错

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.CL、cs.AI

Comments Pre-MIT Press publication version, has been accepted by TACL

Titans Revisited: A Lightweight Reimplementation and Critical Analysis of a Test-Time Memory Model

Gavriel Di Nepi, Federico Siciliano, Fabrizio Silvestri

机构 * Sapienza University of Rome（罗马萨皮恩扎大学） 纠错

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.AI、cs.LG

Mem4Nav: Boosting Vision-and-Language Navigation in Urban Environments with a Hierarchical Spatial-Cognition Long-Short Memory System

Lixuan He, Haoyu Dong, Zhenxing Chen, Yangcheng Yu, Jie Feng, Yong Li

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.CL、cs.AI

Comments The paper is currently under investigation regarding concerns of potential academic misconduct. While the investigation is ongoing, the authors have voluntarily requested to withdraw the manuscript

AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulation

Ming Wang, Peidong Wang, Lin Wu, Xiaocui Yang, Daling Wang, Shi Feng, Yuxin Chen, Bixuan Wang, Yifei Zhang

机构 * School of Computer Science and Engineering, Northeastern University（计算机科学与工程学院，东北大学） ； Mental Health Education Center, Northeastern University（心理健康教育中心，东北大学） ； School of Sociology and Psychology, Central University of Finance and Economics（社会学与心理学学院，中央财经大学） ； School of Psychology, Northeast Normal University（心理学学院，东北师范大学） 纠错

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.CL、cs.AI

Journal ref Findings of the Association for Computational Linguistics: ACL 2025

EntropyLong: Effective Long-Context Training via Predictive Uncertainty

Junlong Jia, Ziyang Chen, Xing Wu, Chaochen Gao, Zijia Lin, Debing Zhang, Songlin Hu, Binghui Guo

机构 * School of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院） ； Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） ； Tsinghua University（清华大学） 纠错

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.CL、cs.AI

Comments work in progress; Correspondence to: Xing Wu <wuxing@iie.ac.cn>

Enhancing Linear Attention with Residual Learning

Xunhao Lai, Jialiang Kang, Jianqiao Lu, Tong Lin, Pengyu Zhao

机构 * Peking University（北京大学） ； The University of Hong Kong（香港大学） ； Minimax 纠错

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.AI、cs.LG

Comments 15 pages, 4 figures

RAVEN: Resilient Aerial Navigation via Open-Set Semantic Memory and Behavior Adaptation

Seungchan Kim, Omar Alama, Dmytro Kurdydyk, John Keller, Nikhil Keetha, Wenshan Wang, Yonatan Bisk, Sebastian Scherer

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Davidson College（戴维森学院） 纠错

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.AI、cs.LG

ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge

Zeinab Sadat Taghavi, Ali Modarressi, Yunpu Ma, Hinrich Schütze

机构 * Center for Information and Language Processing, LMU Munich（信息与语言处理中心，慕尼黑大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心（MCML）） 纠错

专题命中 长上下文与记忆 ：prompting(abstract)；分类 cs.CL、cs.AI

ShadowServe: Interference-Free KV Cache Fetching for Distributed Prefix Caching

Xingyu Xiang, Raj Joshi, Yuhan Liu, Jiayi Yao, Chenxingyu Zhao, Junchen Jiang, Yang Zhou, Eddie Kohler, Minlan Yu

机构 * Harvard University（哈佛大学） ； University of Chicago（芝加哥大学） ； University of Washington（华盛顿大学） ； UC Davis（加州大学戴维斯分校） 纠错

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.AI、cs.LG

Fast Multipole Attention: A Scalable Multilevel Attention Mechanism for Text and Images

Yanming Kang, Giang Tran, Hans De Sterck

机构 * University of Waterloo（滑铁卢大学） 纠错

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.CL、cs.LG

LEGO: Spatial Accelerator Generation and Optimization for Tensor Applications

Yujun Lin, Zhekai Zhang, Song Han

机构 * Massachusetts Institute of Technology（麻省理工学院） 纠错

专题命中 长上下文与记忆 ：foundation model(abstract)；分类 cs.AI、cs.LG

Comments The first two authors have equal contributions; Published as a conference paper in HPCA 2025; 13 pages, 14 figures

LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation

Yiqun Shen, Song Yuan, Zhengze Zhang, Xiaoliang Wang, Daxin Jiang, Nguyen Cam-Tu

机构 * State Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家重点实验室，南京大学） ； School of Artificial Intelligence, Nanjing University（人工智能学院，南京大学） ； Stepfun 纠错

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.AI、cs.LG

A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challenges

Andrew Brown, Muhammad Roman, Barry Devereux

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.CL、cs.AI

Comments 58 page

A-SEA3L-QA: A Fully Automated Self-Evolving, Adversarial Workflow for Arabic Long-Context Question-Answer Generation

Kesen Wang, Daulet Toibazar, Pedro J. Moreno

机构 * Humain 纠错

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.CL、cs.AI

DTRNet: Dynamic Token Routing Network to Reduce Quadratic Costs in Transformers

Aman Sharma, Saeed Najafi, Parsa Farinneya, Benyamin Jamialahmadi, Marzieh S. Tahaei, Yuhe Fan, Mehdi Rezagholizadeh, Boxing Chen, Aref Jafari

机构 * Huawei（华为） 纠错

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.CL、cs.LG

Deep Tensor Network

Yifan Zhang

专题命中 长上下文与记忆 ：foundation model(abstract)；分类 cs.AI、cs.LG

Multi-Modal Drift Forecasting of Leeway Objects via Navier-Stokes-Guided CNN and Sequence-to-Sequence Attention-Based Models

Rahmat K. Adesunkanmi, Alexander W. Brandt, Masoud Deylami, Gustavo A. Giraldo Echeverri, Hamidreza Karbasian, Adel Alaeddini

机构 * Departments of Mechanical and Electrical Engineering, Southern Methodist University（机械与电气工程系，南方 Methodist 大学） 纠错

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.AI、cs.LG

Comments Submitted to IEEE

The Computational Complexity of Satisfiability in State Space Models

Eric Alsmann, Martin Lange

机构 * University of Kassel, Germany（卡塞尔大学） 纠错

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.AI、cs.LG

Comments Accepted at ECAI 25

El Agente: An Autonomous Agent for Quantum Chemistry

Yunheng Zou, Austin H. Cheng, Abdulrahman Aldossary, Jiaru Bai, Shi Xuan Leong, Jorge Arturo Campos-Gonzalez-Angulo, Changhyeok Choi, Cher Tian Ser, Gary Tom, Andrew Wang, Zijian Zhang, Ilya Yakavets, Han Hao, Chris Crebolder, Varinia Bernales, Alán Aspuru-Guzik

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.AI、cs.LG

Hebbian Memory-Augmented Recurrent Networks: Engram Neurons in Deep Learning

Daniel Szelogowski

机构 * Department of Computer Science University of Wisconsin-Whitewater（计算机科学系 威斯康星大学-惠蒂沃特） 纠错

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.AI、cs.LG

Comments 20 pages, 11 figures, 4 tables

Multi-Agent Interactive Question Generation Framework for Long Document Understanding

Kesen Wang, Daulet Toibazar, Abdulrahman Alfulayt, Abdulaziz S. Albadawi, Ranya A. Alkahtani, Asma A. Ibrahim, Haneen A. Alhomoud, Sherif Mohamed, Pedro J. Moreno

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.CL、cs.AI

Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization

Ermo Hua, Che Jiang, Xingtai Lv, Kaiyan Zhang, Youbang Sun, Yuchen Fan, Xuekai Zhu, Biqing Qi, Ning Ding, Bowen Zhou

机构 * Tsinghua University（清华大学） ； Northeastern University（东北大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Shanghai Jiaotong University（上海交通大学） 纠错

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted to ICML 2025

Mixture of Group Experts for Learning Invariant Representations

Lei Kang, Jia Li, Mi Tian, Hua Huang

机构 * Beijing Normal University（北京师范大学） 纠错

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.CL、cs.LG

ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning

Yichen Lu, Wei Dai, Jiaen Liu, Ching Wing Kwok, Zongheng Wu, Xudong Xiao, Ao Sun, Sheng Fu, Jianyuan Zhan, Yian Wang, Takatomo Saito, Sicheng Lai

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.CL、cs.AI

Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP

Omer Goldman, Alon Jacovi, Aviv Slobodkin, Aviya Maimon, Ido Dagan, Reut Tsarfaty

机构 * Bar-Ilan University（巴伊兰大学） 纠错

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.CL、cs.AI

Comments EMNLP 2024

Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection

Zheng Zhan, Liliang Ren, Shuohang Wang, Liyuan Liu, Yang Liu, Yeyun Gong, Yanzhi Wang, Yelong Shen

机构 * Microsoft（微软公司） ； Northeastern University（东北大学） 纠错

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.AI、cs.LG