PAPER·July 21, 2026Accelerating Text-to-Video Generation with Calibrated Sparse AttentionApple Machine Learning Research
TECH·June 1, 2026MiniMax M3: Open-weight model with a million-token context challenges proprietary leadersTHE DECODER
TECH·May 29, 2026Complete Breakdown of the Gemini 3.5 Pro, Claude Lab, and Xiaomi MiMO 2.5 UpdatesGeeky Gadgets
PAPER·May 28, 2026OSP-Next: Efficient High-Quality Video Generation with Sparse Sequence Parallelism, HiF8 Quantization, and Reinforcement LearningHugging Face Papers
PAPER·May 22, 2026Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training StepsHugging Face Papers
PAPER·May 19, 2026CompactAttention: Accelerating Chunked Prefill with Block-Union KV SelectionHugging Face Papers
TECH·May 17, 2026Nous Research Proposes Lighthouse Attention: A Training-Only Selection-Based Hierarchical Attention That Delivers 1.4–1.7× Pretraining Speedup at Long ContextMarkTechPost
PAPER·May 11, 2026MISA: Mixture of Indexer Sparse Attention for Long-Context LLM InferenceHugging Face Papers
PAPER·May 9, 2026EmambaIR: Efficient Visual State Space Model for Event-guided Image ReconstructionarXiv
TECH·April 25, 2026DeepSeek AI Releases DeepSeek-V4: Compressed Sparse Attention and Heavily Compressed Attention Enable One-Million-Token ContextsMarkTechPost
PAPER·April 10, 2026Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs InferenceHugging Face Papers
