The risk of KV cache compression
cs.LG
Submitted: 2026-07-01
Updated: 2026-11-11
Project page: https://longbench2.github.io
Terminology
Sources
- PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
- Compression Barriers for Autoregressive Transformers
- Streaming Attention Approximation via Discrepancy Theory
- Qwen3 Technical Report
- SubGen: Token Generation in Sublinear Time and Memory
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis