{"total":16,"rows":[{"id":"2406.19707","title":"InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management","created":"2024-06-28","cited_by_count":245,"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":"2302.07863","title":"Speculative Decoding with Big Little Decoder","created":"2023-02-15","cited_by_count":164,"area":"inference"},{"id":"2401.03868","title":"FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs","created":"2024-01-08","cited_by_count":64,"area":"inference"},{"id":"2403.11421","title":"FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines","created":"2024-03-18","cited_by_count":49,"area":"inference"},{"id":"2308.08758","title":"Discrete Prompt Compression with Reinforcement Learning","created":"2023-08-17","cited_by_count":42,"area":"inference"},{"id":"2405.16148","title":"Accelerating Transformers with Spectrum-Preserving Token Merging","created":"2024-05-25","cited_by_count":35,"area":"inference"},{"id":"2308.00255","title":"LGViT: Dynamic Early Exiting for Accelerating Vision Transformer","created":"2023-08-01","cited_by_count":31,"area":"inference"},{"id":"2508.02401","title":"CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation","created":"2025-08-04","cited_by_count":9,"area":"inference"},{"id":"2602.02599","title":"RAP: KV-Cache Compression via RoPE-Aligned Pruning","created":"2026-02-01","cited_by_count":3,"area":"inference"},{"id":"2412.11242","title":"TrimLLM: Progressive Layer Dropping for Domain-Specific LLMs","created":"2024-12-15","cited_by_count":2,"area":"inference"},{"id":"2605.15852","title":"GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction","created":"2026-05-15","cited_by_count":2,"area":"inference"},{"id":"2606.24467","title":"CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference","created":"2026-06-23","cited_by_count":2,"area":"inference"},{"id":"2511.19718","title":"Rethinking Vision Transformer Depth via Structural Reparameterization","created":"2025-11-24","cited_by_count":0,"area":"inference"},{"id":"2604.05942","title":"BOSCH: Black-Box Binary Optimization for Short-Context Attention-Head Selection in LLMs","created":"2026-04-07","cited_by_count":0,"area":"inference"},{"id":"2609.17008","title":"FlexEE: Self-Speculative and KV-Compatible Early Exiting for Offloading-Aware LLM Inference","created":"2026-09-15","cited_by_count":0,"area":"inference"}],"next_cursor":null}