{"total":17,"rows":[{"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":"2307.15337","title":"Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation","created":"2023-07-28","cited_by_count":105,"area":"lr"},{"id":"2412.03213","title":"ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression","created":"2024-12-04","cited_by_count":65,"area":"lr"},{"id":"2502.14837","title":"Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs","created":"2025-02-20","cited_by_count":27,"area":"lr"},{"id":"2506.21710","title":"FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering","created":"2025-06-26","cited_by_count":20,"area":"lr"},{"id":"2512.00504","title":"G-KV: Decoding-Time KV Cache Eviction with Global Attention","created":"2025-11-29","cited_by_count":7,"area":"lr"},{"id":"2602.01469","title":"P-EAGLE: Parallel-Drafting EAGLE with Scalable Training","created":"2026-02-01","cited_by_count":6,"area":"lr"},{"id":"2508.18736","title":"Rethinking Caching for LLM Serving Systems: Beyond Traditional Heuristics","created":"2025-08-26","cited_by_count":2,"area":"lr"},{"id":"2602.13595","title":"The Quantization Trap: Breaking Linear Scaling Laws in Multi-Hop Reasoning","created":"2026-02-14","cited_by_count":2,"area":"lr"},{"id":"2606.03092","title":"The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs","created":"2026-06-02","cited_by_count":2,"area":"lr"},{"id":"2602.11530","title":"PASCAL: A Phase-Aware Scheduling Algorithm for Serving Reasoning-based Large Language Models","created":"2026-02-12","cited_by_count":1,"area":"lr"},{"id":"2309.15531","title":"Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models","created":"2023-09-27","cited_by_count":0,"area":"lr"},{"id":"2510.05176","title":"PatternKV: Flattening KV Representation Expands Quantization Headroom","created":"2025-10-05","cited_by_count":0,"area":"lr"},{"id":"2603.27960","title":"Towards Efficient Large Vision-Language Models: A Comprehensive Survey on Inference Strategies","created":"2026-03-30","cited_by_count":0,"area":"lr"},{"id":"2608.24063","title":"VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference","created":"2026-08-25","cited_by_count":0,"area":"lr"},{"id":"2609.25442","title":"WeightBridge: An Efficient Weight Transfer Library for Reinforcement Learning","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2610.00437","title":"JevSpawn: Adaptive Agentic Inference through Compositional Action Spaces","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}