{"total":390,"rows":[{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832,"area":"inference"},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740,"area":null},{"id":"2410.10813","title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","created":"2024-10-14","cited_by_count":707,"area":null},{"id":"2310.01801","title":"Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs","created":"2023-10-03","cited_by_count":474,"area":"inference"},{"id":"2310.06839","title":"LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression","created":"2023-10-10","cited_by_count":453,"area":"inference"},{"id":"2305.14788","title":"Adapting Language Models to Compress Contexts","created":"2023-05-24","cited_by_count":356,"area":null},{"id":"2403.12968","title":"LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression","created":"2024-03-19","cited_by_count":348,"area":"inference"},{"id":"2310.15213","title":"Function Vectors in Large Language Models","created":"2023-10-23","cited_by_count":308,"area":null},{"id":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301,"area":"lr"},{"id":"2310.05736","title":"LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models","created":"2023-10-09","cited_by_count":287,"area":null},{"id":"2312.01552","title":"The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning","created":"2023-12-04","cited_by_count":257,"area":"lr"},{"id":"2310.04408","title":"RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation","created":"2023-10-06","cited_by_count":256,"area":"rag"},{"id":"2502.12067","title":"TokenSkip: Controllable Chain-of-Thought Compression in LLMs","created":"2025-02-17","cited_by_count":249,"area":"lr"},{"id":"2307.06949","title":"HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models","created":"2023-07-13","cited_by_count":225,"area":null},{"id":"2305.16300","title":"Landmark Attention: Random-Access Infinite Context Length for Transformers","created":"2023-05-25","cited_by_count":213,"area":null},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2310.07240","title":"CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving","created":"2023-10-11","cited_by_count":203,"area":"inference"},{"id":"2404.07143","title":"Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention","created":"2024-04-10","cited_by_count":200,"area":null},{"id":"2307.06945","title":"In-context Autoencoder for Context Compression in a Large Language Model","created":"2023-07-13","cited_by_count":199,"area":"inference"},{"id":"2310.06201","title":"Compressing Context to Enhance Inference Efficiency of Large Language Models","created":"2023-10-09","cited_by_count":189,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2403.09054","title":"Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference","created":"2024-03-14","cited_by_count":126,"area":"inference"},{"id":"2405.13792","title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token","created":"2024-05-22","cited_by_count":125,"area":"rag"},{"id":"2412.11664","title":"C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness","created":"2024-12-16","cited_by_count":119,"area":"lr"},{"id":"2403.09636","title":"Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference","created":"2024-03-14","cited_by_count":116,"area":null},{"id":"2404.02039","title":"A Survey on Large Language Model-Based Game Agents","created":"2024-04-02","cited_by_count":112,"area":"agents"},{"id":"2401.03462","title":"Long Context Compression with Activation Beacon","created":"2024-01-07","cited_by_count":104,"area":"inference"},{"id":"2502.15589","title":"LightThinker: Thinking Step-by-Step Compression","created":"2025-02-21","cited_by_count":104,"area":"lr"},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2407.18003","title":"Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption","created":"2024-07-25","cited_by_count":97,"area":"inference"},{"id":"2506.06266","title":"Cartridges: Lightweight and general-purpose long context representations via self-study","created":"2025-06-06","cited_by_count":86,"area":"inference"},{"id":"2501.07278","title":"Lifelong Learning of Large Language Model based Agents: A Roadmap","created":"2025-01-13","cited_by_count":83,"area":"agents"},{"id":"2406.12275","title":"VoCo-LLaMA: Towards Vision Compression with Large Language Models","created":"2024-06-18","cited_by_count":79,"area":"mllm"},{"id":"2402.13598","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","created":"2024-02-21","cited_by_count":76,"area":null},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72,"area":null},{"id":"2410.12388","title":"Prompt Compression for Large Language Models: A Survey","created":"2024-10-16","cited_by_count":67,"area":"inference"},{"id":"2407.09014","title":"CompAct: Compressing Retrieved Documents Actively for Question Answering","created":"2024-07-12","cited_by_count":64,"area":"rag"},{"id":"2405.10637","title":"Layer-Condensed KV Cache for Efficient Inference of Large Language Models","created":"2024-05-17","cited_by_count":59,"area":"inference"},{"id":"2310.05707","title":"Guiding Language Model Reasoning with Planning Tokens","created":"2023-10-09","cited_by_count":58,"area":"lr"},{"id":"2310.15166","title":"Large Language Models are Visual Reasoning Coordinators","created":"2023-10-23","cited_by_count":58,"area":"lr"},{"id":"2401.08392","title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)","created":"2024-01-16","cited_by_count":58,"area":"agents"},{"id":"2506.06105","title":"Text-to-LoRA: Instant Transformer Adaption","created":"2025-06-06","cited_by_count":58,"area":null},{"id":"2402.18700","title":"Learning to Compress Prompt in Natural Language Formats","created":"2024-02-28","cited_by_count":55,"area":null},{"id":"2410.03111","title":"LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy","created":"2024-10-04","cited_by_count":51,"area":"inference"},{"id":"2406.15334","title":"Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning","created":"2024-06-21","cited_by_count":50,"area":"mllm"},{"id":"2505.18227","title":"Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality","created":"2025-05-23","cited_by_count":50,"area":"inference"},{"id":"2310.03046","title":"EcoAssistant: Using LLM Assistant More Affordably and Accurately","created":"2023-10-03","cited_by_count":49,"area":null},{"id":"2406.14528","title":"DeciMamba: Exploring the Length Extrapolation Potential of Mamba","created":"2024-06-20","cited_by_count":49,"area":"ssm"},{"id":"2404.01077","title":"Efficient Prompting Methods for Large Language Models: A Survey","created":"2024-04-01","cited_by_count":47,"area":null},{"id":"2408.03094","title":"500xCompressor: Generalized Prompt Compression for Large Language Models","created":"2024-08-06","cited_by_count":47,"area":"inference"},{"id":"2601.16746","title":"SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents","created":"2026-01-23","cited_by_count":44,"area":"agents"},{"id":"2312.03414","title":"Compressed Context Memory For Online Language Model Interaction","created":"2023-12-06","cited_by_count":43,"area":null},{"id":"2602.15902","title":"Doc-to-LoRA: Learning to Instantly Internalize Contexts","created":"2026-02-13","cited_by_count":43,"area":"lr"},{"id":"2308.08758","title":"Discrete Prompt Compression with Reinforcement Learning","created":"2023-08-17","cited_by_count":42,"area":"inference"},{"id":"2407.01527","title":"KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches","created":"2024-07-01","cited_by_count":42,"area":"inference"},{"id":"2501.09655","title":"A Survey of Research in Large Language Models for Electronic Design Automation","created":"2025-01-16","cited_by_count":41,"area":null},{"id":"2405.03279","title":"Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning","created":"2024-05-06","cited_by_count":40,"area":"rag"},{"id":"2406.15486","title":"SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention","created":"2024-06-17","cited_by_count":39,"area":null},{"id":"2410.02678","title":"Distilling an End-to-End Voice Assistant Without Instruction Training Data","created":"2024-10-03","cited_by_count":39,"area":null},{"id":"2510.00446","title":"LongCodeZip: Compress Long Context for Code Language Models","created":"2025-10-01","cited_by_count":39,"area":null},{"id":"2502.15734","title":"Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation","created":"2025-02-05","cited_by_count":36,"area":"rag"},{"id":"2508.09968","title":"Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models","created":"2025-08-13","cited_by_count":35,"area":"lr"},{"id":"2406.11194","title":"In-Context Editing: Learning Knowledge from Self-Induced Distributions","created":"2024-06-17","cited_by_count":34,"area":null},{"id":"2401.07872","title":"The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey","created":"2024-01-15","cited_by_count":33,"area":null},{"id":"2410.05004","title":"Fast State Restoration in LLM Serving with HCache","created":"2024-10-07","cited_by_count":33,"area":"rag"},{"id":"2603.29919","title":"SkillReducer: Optimizing LLM Agent Skills for Token Efficiency","created":"2026-03-31","cited_by_count":33,"area":"agents"},{"id":"2402.05140","title":"Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains","created":"2024-02-06","cited_by_count":30,"area":null},{"id":"2404.02319","title":"Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization","created":"2024-04-02","cited_by_count":30,"area":"rag"},{"id":"2306.09306","title":"Propagating Knowledge Updates to LMs Through Distillation","created":"2023-06-15","cited_by_count":28,"area":null},{"id":"2401.04858","title":"User Embedding Model for Personalized Language Prompting","created":"2024-01-10","cited_by_count":28,"area":null},{"id":"2502.13063","title":"Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity","created":"2025-02-18","cited_by_count":28,"area":"inference"},{"id":"2312.08901","title":"Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning","created":"2023-12-14","cited_by_count":26,"area":"lr"},{"id":"2404.12318","title":"Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment","created":"2024-04-18","cited_by_count":26,"area":"alignment"},{"id":"2410.02703","title":"Selective Attention Improves Transformer","created":"2024-10-03","cited_by_count":26,"area":null},{"id":"2412.16545","title":"Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models","created":"2024-12-21","cited_by_count":26,"area":null},{"id":"2503.11751","title":"reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs","created":"2025-03-14","cited_by_count":25,"area":"alignment"},{"id":"2402.13449","title":"CAMELoT: Towards Large Language Models with Training-Free Consolidated Associative Memory","created":"2024-02-21","cited_by_count":24,"area":null},{"id":"2406.02376","title":"Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs","created":"2024-06-04","cited_by_count":24,"area":"inference"},{"id":"2407.18121","title":"Efficient Inference of Vision Instruction-Following Models with Elastic Cache","created":"2024-07-25","cited_by_count":24,"area":"mllm"},{"id":"2310.02409","title":"Dodo: Dynamic Contextual Compression for Decoder-only LMs","created":"2023-10-03","cited_by_count":23,"area":null},{"id":"2404.09173","title":"TransformerFAM: Feedback attention is working memory","created":"2024-04-14","cited_by_count":22,"area":null},{"id":"2408.13233","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","created":"2024-08-23","cited_by_count":22,"area":null},{"id":"2409.13035","title":"TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning","created":"2024-09-19","cited_by_count":22,"area":"lr"},{"id":"2502.14245","title":"Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering","created":"2025-02-20","cited_by_count":22,"area":"rag"},{"id":"2409.14866","title":"PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs","created":"2024-09-23","cited_by_count":21,"area":"safety"},{"id":"2502.00791","title":"Vision-centric Token Compression in Large Language Model","created":"2025-02-02","cited_by_count":21,"area":"inference"},{"id":"2502.17601","title":"Representation Engineering for Large-Language Models: Survey and Research Challenges","created":"2025-02-24","cited_by_count":21,"area":"mechinterp"},{"id":"2505.12215","title":"GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment","created":"2025-05-18","cited_by_count":21,"area":"inference"},{"id":"2406.14848","title":"Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models","created":"2024-06-21","cited_by_count":20,"area":null},{"id":"2502.12176","title":"Ten Challenging Problems in Federated Foundation Models","created":"2025-02-14","cited_by_count":20,"area":"safety"},{"id":"2404.13556","title":"ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval","created":"2024-04-21","cited_by_count":19,"area":null},{"id":"2407.15504","title":"Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models","created":"2024-07-22","cited_by_count":19,"area":"inference"},{"id":"2503.10337","title":"KV-Distill: Nearly Lossless Learnable Context Compression for LLMs","created":"2025-03-13","cited_by_count":19,"area":"inference"},{"id":"2503.10720","title":"AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation","created":"2025-03-13","cited_by_count":19,"area":"rag"},{"id":"2512.03324","title":"Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs","created":"2025-12-03","cited_by_count":19,"area":"inference"},{"id":"2305.11170","title":"Efficient Prompting via Dynamic In-Context Learning","created":"2023-05-18","cited_by_count":18,"area":null},{"id":"2402.09949","title":"Multi-word Tokenization for Sequence Compression","created":"2024-02-15","cited_by_count":17,"area":null},{"id":"2406.02547","title":"Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning","created":"2024-06-04","cited_by_count":17,"area":null}],"next_cursor":"100"}