One Distribution, Two Channels: Coverage-Calibrated KV Retention and Compensation
cs.AR, cs.AI
Submitted: 2026-09-28
Updated: 2026-10-10
Sources
- The Llama 3 Herd of Models
- Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices
- AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset
- Fast Transformer Decoding: One Write-Head is All You Need
- Trust the Mass: Forced Weights in KV-Cache Eviction
- Every Cache Entry Earns Its Place: Global Allocation of Resolution and Coverage for KV Cache Compression
- Error Certificates for KV-Cache Eviction via Randomized Design
- Qwen3 Technical Report
- SWE-smith: Scaling Data for Software Engineering Agents
- ResKV: Reconstructing Omitted Attention Contributions for Fixed-Budget KV Cache Compression
- LKV: End-to-End Learning of Head-wise Budgets and Token Selection for LLM KV Cache Eviction
Related papers
- WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantization
- Golden Ruler: A Numeric Format Catalog with Bit-Exact Conformance Vectors for FP8, BF16, MXFP4, and Microscaling Formats
- RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip Design
- PoisonCap: Efficient Hierarchical Temporal Safety for CHERI
- Provisioning to Runtime Optimization of a 100 MW-Scale AI Cluster
- Bit-Accurate Modeling of GPU Matrix Multiply-Accumulate Units: Demystifying Numerical Discrepancy and Accuracy