SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference
cs.CL
Submitted: 2026-06-30
Updated: 2026-11-04
Code: https://github.com/gkamradt/LLMTest_NeedleInAHaystack
Terminology
Sources
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference
- Training Verifiers to Solve Math Word Problems
- Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies
- Understanding the planning of LLM agents: A survey
- Mistral 7B
- The Llama 3 Herd of Models
- Qwen2.5 Technical Report
- SemantiCache: Efficient KV Cache Compression via Semantic Chunking and Clustered Merging
- A Survey on Multi-Turn Interaction Capabilities of Large Language Models
- Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception
- Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data