Papers

• EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments (2025)
  Minsoo Kim et al.
  5.94
• OmniCache: Multidimensional Hierarchical Feature Caching For Diffusion Models (2026)
  Zhaoyuan He et al.
  4.33
• ForgettingOT: Certified Speculative Batching from Sinkhorn's Projective Forgetting (2026)
  Xinyang Wen
  4.33
• When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers (2026)
  Yushi Sun et al.
  1.94
• WaveFilter: Enhancing the Long-Context Capability of Diffusion LLMs via Wavelet-Guided KV Cache Filtering (2026)
  Jinnan Yang et al.
  1.89
• Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching (2026)
  Qianli Ma et al.
  1.89
• Wan-Streamer v0.2: Higher Resolution, Same Latency (2026)
  Lianghua Huang et al.
  1.89
• KVpop -- Key-Value Cache Compression with Predictive Online Pruning (2026)
  Lukas Hauzenberger et al.
  1.89
• OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators (2026)
  Hongyu Liu et al.
  1.89
• ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing (2026)
  Yongqi An et al.
  1.83
• LearnedCache: eBPF-Integrated Perceptron-Based Eviction Policies for the Linux Page Cache (2026)
  Zejia Qi
  1.83
• GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs (2026)
  Junjie Peng et al.
  1.83
• KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs (2026)
  Chuangtao Chen et al.
  1.78
• RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reuse (2026)
  Yingsheng Geng et al.
  1.72
• KV Cache Optimization Strategies for Scalable and Efficient LLM Inference (2026)
  Yichun Xu et al.
  1.72
• Joint Encoding of KV-Cache Blocks for Scalable LLM Serving (2026)
  Joseph Kampeas and Emir Haleva
  1.61
• Crystal-KV: Efficient KV Cache Management for Chain-of-Thought LLMs via Answer-First Principle (2026)
  Zihan Wang et al.
  1.61
• Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction (2026)
  Jang-Hyun Kim et al.
  1.61
• Randomization Boosts KV Caching, Learning Balances Query Load: A Joint Perspective (2026)
  Fangzhou Wu et al.
  1.61
• KVReviver: Reversible KV Cache Compression with Sketch-Based Token Reconstruction (2025)
  Aomufei Yuan et al.
  1.56
• PackKV: Reducing KV Cache Memory Footprint through LLM-Aware Lossy Compression (2025)
  Bo Jiang et al.
  1.56
• Value-Guided KV Compression for LLMs via Approximated CUR Decomposition (2025)
  Ayan Sengupta et al.
  1.39