{"total":31,"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":"2502.15589","title":"LightThinker: Thinking Step-by-Step Compression","created":"2025-02-21","cited_by_count":104,"area":"lr"},{"id":"2506.06122","title":"Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library","created":"2025-06-06","cited_by_count":101,"area":"lr"},{"id":"2504.04823","title":"Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models","created":"2025-04-07","cited_by_count":73,"area":"lr"},{"id":"2408.05646","title":"Eigen Attention: Attention in Low-Rank Space for KV Cache Compression","created":"2024-08-10","cited_by_count":72,"area":"lr"},{"id":"2407.21018","title":"ThinK: Thinner Key Cache by Query-Driven Pruning","created":"2024-07-30","cited_by_count":68,"area":"lr"},{"id":"2402.04236","title":"CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning","created":"2024-02-06","cited_by_count":67,"area":"lr"},{"id":"2506.05345","title":"Inference-Time Hyper-Scaling with KV Cache Compression","created":"2025-06-05","cited_by_count":27,"area":"lr"},{"id":"2502.13575","title":"ETS: Efficient Tree Search for Inference-Time Scaling","created":"2025-02-19","cited_by_count":16,"area":"lr"},{"id":"2510.08525","title":"Which Heads Matter for Reasoning? RL-Guided KV Cache Compression","created":"2025-10-09","cited_by_count":10,"area":"lr"},{"id":"2601.10079","title":"Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts","created":"2026-01-15","cited_by_count":9,"area":"lr"},{"id":"2503.06518","title":"Towards Superior Quantization Accuracy: A Layer-sensitive Approach","created":"2025-03-09","cited_by_count":8,"area":"lr"},{"id":"2606.03928","title":"Value-Aware Stochastic KV Cache Eviction for Reasoning Models","created":"2026-06-02","cited_by_count":8,"area":"lr"},{"id":"2512.12008","title":"Hold Onto That Thought: Assessing KV Cache Compression On Reasoning","created":"2025-12-12","cited_by_count":6,"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":"2605.22269","title":"MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering","created":"2026-05-21","cited_by_count":6,"area":"lr"},{"id":"2606.11164","title":"ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models","created":"2026-06-09","cited_by_count":3,"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":"2606.26472","title":"Epiphany-Aware KV Cache Eviction Without the Attention Matrix","created":"2026-06-25","cited_by_count":2,"area":"lr"},{"id":"2608.00902","title":"Practical Online KV Cache Compaction for LLM Agents: An Empirical Study","created":"2026-08-02","cited_by_count":2,"area":"lr"},{"id":"2608.15797","title":"KV-Rescue: Recovering Reasoning Language Model KV Eviction Loss via Stepwise Interleaving","created":"2026-08-16","cited_by_count":2,"area":"lr"},{"id":"2605.23200","title":"Adaptive Mass-Segmented KV Compression for Long-Context Reasoning","created":"2026-05-22","cited_by_count":1,"area":"lr"},{"id":"2609.03430","title":"Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning","created":"2026-09-03","cited_by_count":1,"area":"lr"},{"id":"2510.05176","title":"PatternKV: Flattening KV Representation Expands Quantization Headroom","created":"2025-10-05","cited_by_count":0,"area":"lr"},{"id":"2602.00748","title":"HyperOffload: Graph-Driven Hierarchical Memory Management for Large Language Models on SuperNode Architectures","created":"2026-01-31","cited_by_count":0,"area":"lr"},{"id":"2604.10898","title":"ZoomR: Memory Efficient Reasoning through Multi-Granularity Key Value Retrieval","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2605.16439","title":"KVCapsule: Efficient Sequential KV Cache Compression for Vision-Language Models with Asymmetric Redundancy","created":"2026-05-14","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":"2609.03494","title":"GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2610.05685","title":"Spend Bytes on Breadth: Precision-Count Trade-offs for Decode-Time KV Compression in Long Chain-of-Thought Reasoning","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.15259","title":"RECAP: Calibrating Low-Bit Reasoning Models on the History They Read","created":"2026-10-11","cited_by_count":0,"area":"lr"}],"next_cursor":null}