{"total":88,"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":"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":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"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":"2401.03462","title":"Long Context Compression with Activation Beacon","created":"2024-01-07","cited_by_count":104,"area":"inference"},{"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":"2410.12388","title":"Prompt Compression for Large Language Models: A Survey","created":"2024-10-16","cited_by_count":67,"area":"inference"},{"id":"2502.00299","title":"ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference","created":"2025-02-01","cited_by_count":60,"area":"inference"},{"id":"2409.01227","title":"Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference","created":"2024-09-02","cited_by_count":53,"area":"inference"},{"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":"2408.03094","title":"500xCompressor: Generalized Prompt Compression for Large Language Models","created":"2024-08-06","cited_by_count":47,"area":"inference"},{"id":"2408.03675","title":"NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time","created":"2024-08-07","cited_by_count":43,"area":"inference"},{"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":"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":"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":"2409.19272","title":"Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios","created":"2024-09-28","cited_by_count":23,"area":"inference"},{"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":"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":"2412.17483","title":"A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression","created":"2024-12-23","cited_by_count":17,"area":"inference"},{"id":"2404.07979","title":"LLoCO: Learning Long Contexts Offline","created":"2024-04-11","cited_by_count":16,"area":"inference"},{"id":"2503.19114","title":"Understanding and Improving Information Preservation in Prompt Compression for LLMs","created":"2025-03-24","cited_by_count":15,"area":"inference"},{"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":"2504.08934","title":"Long Context In-Context Compression by Getting to the Gist of Gisting","created":"2025-04-11","cited_by_count":13,"area":"inference"},{"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":"2404.15420","title":"XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference","created":"2024-04-23","cited_by_count":12,"area":"inference"},{"id":"2407.02043","title":"Concise and Precise Context Compression for Tool-Using Language Models","created":"2024-07-02","cited_by_count":12,"area":"inference"},{"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":"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":"2409.14364","title":"Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models","created":"2024-09-22","cited_by_count":9,"area":"inference"},{"id":"2410.11786","title":"Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability","created":"2024-10-15","cited_by_count":9,"area":"inference"},{"id":"2410.14042","title":"Style-Compress: An LLM-Based Prompt Compression Framework Considering Task-Specific Styles","created":"2024-10-17","cited_by_count":9,"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":"2406.06110","title":"Recurrent Context Compression: Efficiently Expanding the Context Window of LLM","created":"2024-06-10","cited_by_count":8,"area":"inference"},{"id":"2512.04550","title":"AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees","created":"2025-12-04","cited_by_count":8,"area":"inference"},{"id":"2405.12591","title":"Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression","created":"2024-05-21","cited_by_count":7,"area":"inference"},{"id":"2410.04139","title":"From Reading to Compressing: Exploring the Multi-document Reader for Prompt Compression","created":"2024-10-05","cited_by_count":7,"area":"inference"},{"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":"2408.08146","title":"KOALA: Enhancing Speculative Decoding for LLM via Multi-Layer Draft Heads with Adversarial Learning","created":"2024-08-15","cited_by_count":6,"area":"inference"},{"id":"2504.11004","title":"Dynamic Compressing Prompts for Efficient Inference of Large Language Models","created":"2025-04-15","cited_by_count":6,"area":"inference"},{"id":"2508.02053","title":"ProCut: LLM Prompt Compression via Attribution Estimation","created":"2025-08-04","cited_by_count":6,"area":"inference"},{"id":"2604.20920","title":"Simplified Sparse Attention via Gist Tokens","created":"2026-04-22","cited_by_count":6,"area":"inference"},{"id":"2606.04557","title":"Cartridges at Scale: Training Modular KV Caches over Large Document Collections","created":"2026-06-03","cited_by_count":6,"area":"inference"},{"id":"2509.19228","title":"CompLLM: Compression for Long Context Q&A","created":"2025-09-23","cited_by_count":5,"area":"inference"},{"id":"2501.06730","title":"Better Prompt Compression Without Multi-Layer Perceptrons","created":"2025-01-12","cited_by_count":4,"area":"inference"},{"id":"2504.16574","title":"PIS: Linking Importance Sampling and Attention Mechanisms for Efficient Prompt Compression","created":"2025-04-23","cited_by_count":4,"area":"inference"},{"id":"2506.00307","title":"Lossless Token Sequence Compression via Meta-Tokens","created":"2025-05-30","cited_by_count":4,"area":"inference"},{"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":"2405.11299","title":"The CAP Principle for LLM Serving: A Survey of Long-Context Large Language Model Serving","created":"2024-05-18","cited_by_count":3,"area":"inference"},{"id":"2508.17892","title":"ILRe: Intermediate Layer Retrieval for Context Compression in Causal Language Models","created":"2025-08-25","cited_by_count":3,"area":"inference"},{"id":"2511.08128","title":"Sentence-Anchored Gist Compression for Long-Context LLMs","created":"2025-11-11","cited_by_count":3,"area":"inference"},{"id":"2512.14244","title":"From Context to EDUs: Faithful and Structured Context Compression via Elementary Discourse Unit Decomposition","created":"2025-12-16","cited_by_count":3,"area":"inference"},{"id":"2603.19733","title":"PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction","created":"2026-03-20","cited_by_count":3,"area":"inference"},{"id":"2605.09463","title":"Beyond Position Bias: Shifting Context Compression from Position-Driven to Semantic-Driven","created":"2026-05-10","cited_by_count":3,"area":"inference"},{"id":"2603.23527","title":"Compression Method Matters: Benchmark-Dependent Output Dynamics in LLM Prompt Compression","created":"2026-03-06","cited_by_count":2,"area":"inference"},{"id":"2605.04426","title":"Telegraph English: Semantic Prompt Compression via Structured Symbolic Rewriting","created":"2026-05-06","cited_by_count":2,"area":"inference"},{"id":"2609.35621","title":"Cartridges++: KV Cache Compression without Off-Context Derailment","created":"2026-09-28","cited_by_count":2,"area":"inference"},{"id":"2407.19410","title":"AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answering","created":"2024-07-28","cited_by_count":1,"area":"inference"},{"id":"2509.09199","title":"CCF: A Context Compression Framework for Efficient Long-Sequence Language Modeling","created":"2025-09-11","cited_by_count":1,"area":"inference"},{"id":"2511.12281","title":"Cmprsr: Abstractive Token-Level Question-Agnostic Prompt Compressor","created":"2025-11-15","cited_by_count":1,"area":"inference"},{"id":"2512.03643","title":"Optical Context Compression Is Just (Bad) Autoencoding","created":"2025-12-03","cited_by_count":1,"area":"inference"},{"id":"2603.23525","title":"Prompt Compression in Production Task Orchestration: A Pre-Registered Randomized Trial","created":"2026-03-06","cited_by_count":1,"area":"inference"},{"id":"2606.14875","title":"Context Compression Is Not One Thing: Readable Symbolic Re-expression vs. Coherent Summary at Matched Budget","created":"2026-06-12","cited_by_count":1,"area":"inference"},{"id":"2606.18406","title":"CoreMem: Riemannian Retrieval and Fisher-Guided Distillation for Long-Term Memory in Dialogue Agents","created":"2026-06-16","cited_by_count":1,"area":"inference"},{"id":"2607.21231","title":"Progressive Cramming: Reliable Token Compression and What It Reveals","created":"2026-07-23","cited_by_count":1,"area":"inference"},{"id":"2609.01507","title":"LatentPress: Context Compression Beyond Text and Vision","created":"2026-09-01","cited_by_count":1,"area":"inference"},{"id":"2609.11192","title":"FlexComp: One Model for Every Ratio in Context Compression","created":"2026-09-10","cited_by_count":1,"area":"inference"},{"id":"2609.25537","title":"Compressing Long Context into Answer-Aligned Memory Embeddings for LLM Inference","created":"2026-09-22","cited_by_count":1,"area":"inference"},{"id":"2502.13374","title":"Task-agnostic Prompt Compression with Context-aware Sentence Embedding and Reward-guided Task Descriptor","created":"2025-02-19","cited_by_count":0,"area":"inference"},{"id":"2603.04759","title":"Stacked from One: Multi-Scale Self-Injection for Context Window Extension","created":"2026-03-05","cited_by_count":0,"area":"inference"},{"id":"2604.15153","title":"Compressing Sequences in the Latent Embedding Space: $K$-Token Merging for Large Language Models","created":"2026-04-16","cited_by_count":0,"area":"inference"},{"id":"2605.22337","title":"Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache Compression","created":"2026-05-21","cited_by_count":0,"area":"inference"},{"id":"2606.03739","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","created":"2026-06-02","cited_by_count":0,"area":"inference"},{"id":"2607.08399","title":"Prompt Compression via Activation Aggregation","created":"2026-07-09","cited_by_count":0,"area":"inference"},{"id":"2607.25335","title":"Every Time I Hire a Linguist, Inference Costs Go Down: On Linguistic Rules as Effective Prompt Compressors","created":"2026-07-28","cited_by_count":0,"area":"inference"},{"id":"2608.04569","title":"Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression","created":"2026-08-05","cited_by_count":0,"area":"inference"},{"id":"2608.30252","title":"Strong Drafts Need Compact Memories: Long-Context Speculative Decoding with Compressed KV Cache","created":"2026-08-31","cited_by_count":0,"area":"inference"},{"id":"2609.32395","title":"Memory as a cache: Exact context reuse and deletion by construction","created":"2026-09-26","cited_by_count":0,"area":"inference"},{"id":"2609.36526","title":"Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations","created":"2026-09-29","cited_by_count":0,"area":"inference"},{"id":"2610.05885","title":"The Optimization Landscape of Learning Compacted Context Models","created":"2026-10-05","cited_by_count":0,"area":"inference"},{"id":"2610.13605","title":"zip2zip++: Towards Inference-Time Token Compression with Minimal Quality Loss","created":"2026-10-09","cited_by_count":0,"area":"inference"},{"id":"2610.18654","title":"Kwai Summary Attention V2 Technical Report","created":"2026-10-13","cited_by_count":0,"area":"inference"}],"next_cursor":null}