{"total":199,"rows":[{"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":"2406.20094","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","created":"2024-06-28","cited_by_count":417,"area":"synth"},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364,"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":"2309.10668","title":"Language Modeling Is Compression","created":"2023-09-19","cited_by_count":225,"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":"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":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"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":"2409.03420","title":"mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding","created":"2024-09-05","cited_by_count":114,"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":"2410.19258","title":"Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning","created":"2024-10-25","cited_by_count":97,"area":"lr"},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"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":"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":"2406.01326","title":"TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","created":"2024-06-03","cited_by_count":71,"area":null},{"id":"2308.14352","title":"EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices","created":"2023-08-28","cited_by_count":69,"area":"moe"},{"id":"2512.18470","title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","created":"2025-12-20","cited_by_count":59,"area":"agents"},{"id":"2407.09709","title":"GOFA: A Generative One-For-All Model for Joint Graph Language Modeling","created":"2024-07-12","cited_by_count":57,"area":null},{"id":"2509.25911","title":"Mem-{\\alpha}: Learning Memory Construction via Reinforcement Learning","created":"2025-09-30","cited_by_count":55,"area":"lr"},{"id":"2502.00592","title":"M+: Extending MemoryLLM with Scalable Long-Term Memory","created":"2025-02-01","cited_by_count":54,"area":null},{"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":"2406.14528","title":"DeciMamba: Exploring the Length Extrapolation Potential of Mamba","created":"2024-06-20","cited_by_count":49,"area":"ssm"},{"id":"2404.12096","title":"LongEmbed: Extending Embedding Models for Long Context Retrieval","created":"2024-04-18","cited_by_count":48,"area":null},{"id":"2404.01077","title":"Efficient Prompting Methods for Large Language Models: A Survey","created":"2024-04-01","cited_by_count":47,"area":null},{"id":"2312.03414","title":"Compressed Context Memory For Online Language Model Interaction","created":"2023-12-06","cited_by_count":43,"area":null},{"id":"2310.18859","title":"SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models","created":"2023-10-29","cited_by_count":38,"area":"moe"},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"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":"2410.03227","title":"ALR$^2$: A Retrieve-then-Reason Framework for Long-context Question Answering","created":"2024-10-04","cited_by_count":26,"area":"lr"},{"id":"2411.05877","title":"Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass","created":"2024-11-08","cited_by_count":26,"area":null},{"id":"2503.23895","title":"Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement","created":"2025-03-31","cited_by_count":25,"area":"rag"},{"id":"2507.20198","title":"A Survey of Token Compression for Efficient Multimodal Large Language Models","created":"2025-07-27","cited_by_count":25,"area":"mllm"},{"id":"2602.06358","title":"SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass","created":"2026-02-06","cited_by_count":25,"area":null},{"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":"2503.08727","title":"Training Plug-n-Play Knowledge Modules with Deep Context Distillation","created":"2025-03-11","cited_by_count":24,"area":null},{"id":"2601.04786","title":"AgentOCR: Reimagining Agent History via Optical Self-Compression","created":"2026-01-08","cited_by_count":22,"area":"agents"},{"id":"2410.00487","title":"Self-Updatable Large Language Models by Integrating Context into Model Parameters","created":"2024-10-01","cited_by_count":21,"area":null},{"id":"2502.00791","title":"Vision-centric Token Compression in Large Language Model","created":"2025-02-02","cited_by_count":21,"area":"inference"},{"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":"2501.16075","title":"PISCO: Pretty Simple Compression for Retrieval-Augmented Generation","created":"2025-01-27","cited_by_count":20,"area":"rag"},{"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":"2407.08892","title":"Characterizing Prompt Compression Methods for Long Context Inference","created":"2024-07-11","cited_by_count":18,"area":"inference"},{"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},{"id":"2511.15244","title":"Context Cascade Compression: Exploring the Upper Limits of Text Compression","created":"2025-11-19","cited_by_count":17,"area":null},{"id":"2404.07979","title":"LLoCO: Learning Long Contexts Offline","created":"2024-04-11","cited_by_count":16,"area":"inference"},{"id":"2410.10450","title":"KBLaM: Knowledge Base augmented Language Model","created":"2024-10-14","cited_by_count":16,"area":null},{"id":"2510.08907","title":"Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors","created":"2025-10-10","cited_by_count":14,"area":"inference"},{"id":"2409.06679","title":"E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning","created":"2024-09-10","cited_by_count":13,"area":"lr"},{"id":"2410.05078","title":"Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data","created":"2024-10-07","cited_by_count":13,"area":null},{"id":"2602.01719","title":"COMI: Coarse-to-fine Context Compression via Marginal Information Gain","created":"2026-02-02","cited_by_count":13,"area":"inference"},{"id":"2602.21221","title":"Latent Context Compilation: Distilling Long Context into Compact Portable Memory","created":"2026-01-31","cited_by_count":13,"area":null},{"id":"2501.12959","title":"Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference","created":"2025-01-22","cited_by_count":12,"area":"inference"},{"id":"2603.15634","title":"NextMem: Towards Latent Factual Memory for LLM-based Agents","created":"2026-02-26","cited_by_count":12,"area":"agents"},{"id":"2405.14660","title":"Implicit In-context Learning","created":"2024-05-23","cited_by_count":11,"area":null},{"id":"2410.03156","title":"MELODI: Exploring Memory Compression for Long Contexts","created":"2024-10-04","cited_by_count":11,"area":null},{"id":"2410.08391","title":"KV Prediction for Improved Time to First Token","created":"2024-10-10","cited_by_count":11,"area":"inference"},{"id":"2507.08799","title":"KV Cache Steering for Controlling Frozen LLMs","created":"2025-07-11","cited_by_count":11,"area":"inference"},{"id":"2511.18659","title":"CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning","created":"2025-11-24","cited_by_count":11,"area":"lr"},{"id":"2505.17051","title":"Embedding-to-Prefix: Parameter-Efficient Personalization for Pre-Trained Large Language Models","created":"2025-05-16","cited_by_count":10,"area":null},{"id":"2507.05633","title":"SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression","created":"2025-07-08","cited_by_count":10,"area":"rag"},{"id":"2510.27688","title":"Continuous Autoregressive Language Models","created":"2025-10-31","cited_by_count":10,"area":null},{"id":"2608.06503","title":"Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability","created":"2026-08-06","cited_by_count":10,"area":"inference"},{"id":"2509.15763","title":"UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression","created":"2025-09-19","cited_by_count":9,"area":"inference"},{"id":"2510.17364","title":"Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs","created":"2025-10-20","cited_by_count":9,"area":null},{"id":"2603.13875","title":"GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent","created":"2026-03-14","cited_by_count":9,"area":null},{"id":"2604.02985","title":"Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference","created":"2026-04-03","cited_by_count":9,"area":"rag"},{"id":"2501.14743","title":"KVDirect: Distributed Disaggregated LLM Inference","created":"2024-12-13","cited_by_count":8,"area":"inference"},{"id":"2505.00019","title":"An Empirical Study on Prompt Compression for Large Language Models","created":"2025-04-24","cited_by_count":8,"area":"inference"},{"id":"2506.04344","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","created":"2025-06-04","cited_by_count":8,"area":null},{"id":"2512.04550","title":"AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees","created":"2025-12-04","cited_by_count":8,"area":"inference"},{"id":"2601.07226","title":"Lost in the Noise: How Reasoning Models Fail with Contextual Distractors","created":"2026-01-12","cited_by_count":8,"area":"lr"},{"id":"2401.07793","title":"Flexibly Scaling Large Language Models Contexts Through Extensible Tokenization","created":"2024-01-15","cited_by_count":7,"area":"rag"},{"id":"2408.14906","title":"Writing in the Margins: Better Inference Pattern for Long Context Retrieval","created":"2024-08-27","cited_by_count":7,"area":null},{"id":"2410.15116","title":"Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models","created":"2024-10-19","cited_by_count":7,"area":null},{"id":"2505.15774","title":"Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information Retention","created":"2025-05-21","cited_by_count":7,"area":"inference"},{"id":"2510.20797","title":"No Mean Feat: Simple, Strong Baselines for Context Compression","created":"2025-10-23","cited_by_count":7,"area":"inference"},{"id":"2408.15518","title":"Squid: Long Context as a New Modality for Energy-Efficient On-Device Language Models","created":"2024-08-28","cited_by_count":6,"area":null},{"id":"2605.23071","title":"The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management","created":"2026-05-21","cited_by_count":6,"area":null},{"id":"2409.01495","title":"The Compressor-Retriever Architecture for Language Model OS","created":"2024-09-02","cited_by_count":5,"area":null},{"id":"2506.01084","title":"zip2zip: Inference-Time Adaptive Tokenization via Online Compression","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2506.11638","title":"LoRA-Gen: Specializing Large Language Model via Online LoRA Generation","created":"2025-06-13","cited_by_count":5,"area":null},{"id":"2509.19228","title":"CompLLM: Compression for Long Context Q&A","created":"2025-09-23","cited_by_count":5,"area":"inference"},{"id":"2510.04476","title":"Compressed Convolutional Attention: Efficient Attention in a Compressed Latent Space","created":"2025-10-06","cited_by_count":5,"area":"moe"},{"id":"2412.13437","title":"Deploying Foundation Model Powered Agent Services: A Survey","created":"2024-12-18","cited_by_count":4,"area":"agents"},{"id":"2501.06730","title":"Better Prompt Compression Without Multi-Layer Perceptrons","created":"2025-01-12","cited_by_count":4,"area":"inference"},{"id":"2504.07109","title":"OSCAR: Online Soft Compression And Reranking","created":"2025-03-17","cited_by_count":4,"area":"rag"},{"id":"2506.00307","title":"Lossless Token Sequence Compression via Meta-Tokens","created":"2025-05-30","cited_by_count":4,"area":"inference"},{"id":"2508.12285","title":"\"My productivity is boosted, but ...\" Demystifying Users' Perception on AI Coding Assistants","created":"2025-08-17","cited_by_count":4,"area":null},{"id":"2603.25340","title":"Large Language Model as Token Compressor and Decompressor","created":"2026-03-26","cited_by_count":4,"area":null},{"id":"2605.00444","title":"Scaling Video Understanding via Compact Latent Multi-Agent Collaboration","created":"2026-05-01","cited_by_count":4,"area":"mllm"},{"id":"2605.15156","title":"MeMo: Memory as a Model","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2606.07878","title":"Still: Amortized KV Cache Compaction in a Single Forward Pass","created":"2026-06-05","cited_by_count":4,"area":"inference"},{"id":"2606.09659","title":"End-to-End Context Compression at Scale","created":"2026-06-08","cited_by_count":4,"area":"inference"},{"id":"2309.17061","title":"SCALE: Synergized Collaboration of Asymmetric Language Translation Engines","created":"2023-09-29","cited_by_count":3,"area":null}],"next_cursor":"100"}