语言大模型 / LLM - arXivDaily 专题

2501.10132 2025-01-20 cs.CL 70%

ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario

Lucen Zhong, Zhengxiao Du, Xiaohan Zhang, Haiyi Hu, Jie Tang

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

2412.04778 2025-01-20 cs.LG 70%

IterL2Norm: Fast Iterative L2-Normalization

ChangMin Ye, Yonguk Sim, Youngchae Kim, SeongMin Jin, Doo Seok Jeong

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

Comments Design, Automation & Test in Europe Conference 2025

2412.15519 2024-12-30 cs.LG 70%

PreNeT: Leveraging Computational Features to Predict Deep Neural Network Training Time

Alireza Pourali, Arian Boukani, Hamzeh Khazaei

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

Comments 11 pages, Conference

2409.10907 2024-12-17 cs.CL cs.IR 70%

Attention-Seeker: Dynamic Self-Attention Scoring for Unsupervised Keyphrase Extraction

Erwin D. López Z., Cheng Tang, Atsushi Shimada

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

Comments This version has been accepted for presentation at COLING 2025, and all peer-reviewed changes have been incorporated

2412.09036 2024-12-13 cs.CL 70%

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty

Meizhi Zhong, Xikai Liu, Chen Zhang, Yikun Lei, Yan Gao, Yao Hu, Kehai Chen, Min Zhang

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

2403.11021 2024-12-04 cs.CV cs.AI 70%

Towards Neuro-Symbolic Video Understanding

Minkyu Choi, Harsh Goel, Mohammad Omama, Yunhao Yang, Sahil Shah, Sandeep Chinchali

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

Comments Accepted by The European Conference on Computer Vision (ECCV) 2024

2309.00378 2024-12-03 cs.CL cs.CV cs.HC 70%

Long-Term Ad Memorability: Understanding & Generating Memorable Ads

Harini SI, Somesh Singh, Yaman K Singla, Aanisha Bhattacharyya, Veeky Baths, Changyou Chen, Rajiv Ratn Shah, Balaji Krishnamurthy

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

Comments Published in WACV-2025

2411.16732 2024-11-27 cs.CL cs.IR 70%

Multi-Reranker: Maximizing performance of retrieval-augmented generation in the FinanceRAG challenge

Joohyun Lee, Minji Roh

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

2411.12449 2024-11-21 cs.CL cs.IR 70%

Neon: News Entity-Interaction Extraction for Enhanced Question Answering

Sneha Singhania, Silviu Cucerzan, Allen Herring, Sujay Kumar Jauhar

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

2411.12778 2024-11-21 cs.HC cs.AI 70%

Lucia: A Temporal Computing Platform for Contextual Intelligence

Weizhe Lin, Junxiao Shen

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

2402.07440 2024-11-19 cs.IR cs.LG 70%

Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT

Jon Saad-Falcon, Daniel Y. Fu, Simran Arora, Neel Guha, Christopher Ré

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

Comments International Conference on Machine Learning (ICML) 2024

2411.07396 2024-11-13 cs.CL 70%

Toward Optimal Search and Retrieval for RAG

Alexandria Leto, Cecilia Aguerrebere, Ishwar Bhati, Ted Willke, Mariano Tepper, Vy Ai Vo

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

Comments Accepted to NeurIPS 2024 Workshop ATTRIB

2407.01523 2024-11-13 cs.CV cs.CL 70%

MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations

Yubo Ma, Yuhang Zang, Liangyu Chen, Meiqi Chen, Yizhu Jiao, Xinze Li, Xinyuan Lu, Ziyu Liu, Yan Ma, Xiaoyi Dong, Pan Zhang, Liangming Pan, Yu-Gang Jiang, Jiaqi Wang, Yixin Cao, Aixin Sun

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

Comments Accepted to NeurIPS 2024 Datasets and Benchmarks Track (Spotlight)

2312.05269 2024-11-07 cs.CV cs.LG 70%

LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos

Ying Wang, Yanlai Yang, Mengye Ren

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

2405.07518 2024-11-06 cs.AR cs.AI 70%

SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts

Raghu Prabhakar, Ram Sivaramakrishnan, Darshan Gandhi, Yun Du, Mingran Wang, Xiangyu Song, Kejie Zhang, Tianren Gao, Angela Wang, Karen Li, Yongning Sheng, Joshua Brot, Denis Sokolov, Apurv Vivek, Calvin Leung, Arjun Sabnis, Jiayu Bai, Tuowen Zhao, Mark Gottscho, David Jackson, Mark Luttrell, Manish K. Shah, Edison Chen, Kaizhao Liang, Swayambhoo Jain, Urmish Thakker, Dawei Huang, Sumti Jairath, Kevin J. Brown, Kunle Olukotun

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

Comments 2024 57th IEEE/ACM International Symposium on Microarchitecture (MICRO)

2310.01801 2024-10-31 cs.CL 70%

Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

Suyu Ge, Yunan Zhang, Liyuan Liu, Minjia Zhang, Jiawei Han, Jianfeng Gao

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

Comments ICLR 2024

2405.17991 2024-10-22 cs.CV cs.AI 70%

VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections

Roy Miles, Pradyumna Reddy, Ismail Elezi, Jiankang Deng

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

Comments NeurIPS 2024. Code available at https://github.com/roymiles/VeLoRA

2312.09075 2024-10-21 cs.CL 70%

Towards Verifiable Text Generation with Evolving Memory and Self-Reflection

Hao Sun, Hengyi Cai, Bo Wang, Yingyan Hou, Xiaochi Wei, Shuaiqiang Wang, Yan Zhang, Dawei Yin

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

Comments EMNLP 2024 Main Conference

2308.05822 2024-10-21 cs.CV cs.AI cs.HC 70%

Encode-Store-Retrieve: Augmenting Human Memory through Language-Encoded Egocentric Perception

Junxiao Shen, John Dudley, Per Ola Kristensson

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

2410.11272 2024-10-16 cs.CL 70%

Cognitive Overload Attack:Prompt Injection for Long Context

Bibek Upadhayay, Vahid Behzadan, Amin Karbasi

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

Comments 40 pages, 31 Figures

2410.08791 2024-10-14 cs.LG 70%

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

Reza Abbasi, Sernam Lim

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

2410.07590 2024-10-11 cs.CV cs.CL 70%

TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text

Songshuo Lu, Hua Wang, Yutian Rong, Zhi Chen, Yaohua Tang

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

2406.07138 2024-10-11 cs.CL 70%

An Efficient Recipe for Long Context Extension via Middle-Focused Positional Encoding

Tong Wu, Yanpeng Zhao, Zilong Zheng

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

Comments Accepted by NeurIPS 2024

2407.01527 2024-10-10 cs.CL 70%

KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches

Jiayi Yuan, Hongyi Liu, Shaochen Zhong, Yu-Neng Chuang, Songchen Li, Guanchu Wang, Duy Le, Hongye Jin, Vipin Chaudhary, Zhaozhuo Xu, Zirui Liu, Xia Hu

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

2406.12018 2024-10-10 cs.CL 70%

CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling

Yu Bai, Xiyuan Zou, Heyan Huang, Sanxing Chen, Marc-Antoine Rondeau, Yang Gao, Jackie Chi Kit Cheung

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

Comments EMNLP 2024 Main Conference

2410.04698 2024-10-08 cs.CL 70%

MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs

Lei Wang, Shan Dong, Yuhui Xu, Hanze Dong, Yalu Wang, Amrita Saha, Ee-Peng Lim, Caiming Xiong, Doyen Sahoo

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

Comments Work-in-Progress

2410.04167 2024-10-08 cs.CE cs.LG physics.comp-ph 70%

Beyond Language: Applying MLX Transformers to Engineering Physics

Stavros Kassinos, Alessio Alexiadis

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

Comments 63 pages, 31 figure, research paper, code shared under an MIT license on GitHub

2410.02719 2024-10-04 cs.CL 70%

UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation

Zixuan Li, Jing Xiong, Fanghua Ye, Chuanyang Zheng, Xun Wu, Jianqiao Lu, Zhongwei Wan, Xiaodan Liang, Chengming Li, Zhenan Sun, Lingpeng Kong, Ngai Wong

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

2409.00997 2024-10-03 cs.CL 70%

DataSculpt: Crafting Data Landscapes for Long-Context LLMs through Multi-Objective Partitioning

Keer Lu, Xiaonan Nie, Zheng Liang, Da Pan, Shusen Zhang, Keshi Zhao, Weipeng Chen, Zenan Zhou, Guosheng Dong, Bin Cui, Wentao Zhang

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

2406.13167 2024-09-27 cs.CL 70%

QRMeM: Unleash the Length Limitation through Question then Reflection Memory Mechanism

Bo Wang, Heyan Huang, Yixin Cao, Jiahao Ying, Wei Tang, Chong Feng

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

Comments EMNLP 2024 Findings

1. 长上下文与记忆 4789 篇

ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario

IterL2Norm: Fast Iterative L2-Normalization

PreNeT: Leveraging Computational Features to Predict Deep Neural Network Training Time

Attention-Seeker: Dynamic Self-Attention Scoring for Unsupervised Keyphrase Extraction

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty

Towards Neuro-Symbolic Video Understanding

Long-Term Ad Memorability: Understanding & Generating Memorable Ads

Multi-Reranker: Maximizing performance of retrieval-augmented generation in the FinanceRAG challenge

Neon: News Entity-Interaction Extraction for Enhanced Question Answering

Lucia: A Temporal Computing Platform for Contextual Intelligence

Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT

Toward Optimal Search and Retrieval for RAG

MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations

LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos

SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts

Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections

Towards Verifiable Text Generation with Evolving Memory and Self-Reflection

Encode-Store-Retrieve: Augmenting Human Memory through Language-Encoded Egocentric Perception

Cognitive Overload Attack:Prompt Injection for Long Context

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text

An Efficient Recipe for Long Context Extension via Middle-Focused Positional Encoding

KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches

CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling

MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs

Beyond Language: Applying MLX Transformers to Engineering Physics

UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation

DataSculpt: Crafting Data Landscapes for Long-Context LLMs through Multi-Objective Partitioning

QRMeM: Unleash the Length Limitation through Question then Reflection Memory Mechanism