KV Admission: Learning What to Write for Efficient Long-Context LLM Inference
cs.LG, cs.AI
Submitted: 2025-12-19
Updated: 2026-08-29
Terminology
Sources
- xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction
- MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
- Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?
- RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference
- Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- Unveiling Simplicities of Attention: Adaptive Long-Context Head Identification
- SeerAttention-R: Sparse Attention Adaptation for Long Reasoning
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
- Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression
- The Llama 3 Herd of Models
- Benchmarking Natural Language Understanding Services for building Conversational Agents
- Qwen3 Technical Report
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks