TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning
cs.AI
Submitted: 2026-08-04
Updated: 2026-08-30
Comments: EMNLP2026 Main Conference
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
- Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution
- RULER: What's the Real Context Size of Your Long-Context Language Models?
- KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- SpinQuant: LLM quantization with learned rotations
- KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
- Value-Guided KV Compression for LLMs via Approximated CUR Decomposition
- Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
- Efficient Streaming Language Models with Attention Sinks
- Qwen3 Technical Report
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection