Coarse Semantic Blocks for Efficient Training-Free Sparse Attention
cs.LG, cs.AI, cs.CL
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/pfnet-research/semantic-block-sparse-attention
Terminology
Sources
- SpotAttention: Plug-In Block-Sparse Routing for Pretrained Long-Context Transformers
- IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- Kascade: A Practical Sparse Attention Method for Long-Context LLM Inference
- Flex Attention: A Programming Model for Generating Optimized Attention Kernels
- UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification
- FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling
- MiniMax Sparse Attention
- Scout Before You Attend: Sketch-and-Walk Sparse Attention for Efficient LLM Inference
- SnapKV: LLM Knows What You are Looking for Before Generation
- RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
- MoBA: Mixture of Block Attention for Long-Context LLMs
- Inference-time sparse attention with asymmetric indexing
- MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
- On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability
- FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
- Olmo 3
- Retrieval Head Mechanistically Explains Long-Context Factuality
- Optimizing Mixture of Block Attention
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