AllFeed, trending, and board
FeedLatest news
TrendingOpen source and releases
BoardBlogs and showcases
TagsBrowse by topic

#sparse-attention

The latest AI and developer news about #sparse-attention, with the original source and a short summary.

AI Briefing

Privacy Policy Terms of Service Contact About Sources RSS Support us

Feed
Trending
Tags
Settings

LLMs Declare Their Own Attention Scope

·2026.09.05 15:00

GLM-5.3 Architecture Visualization Released on HF Viewer

·2026.08.29 05:00

SGLang Achieves Up to 6.24x Speedup in MiniMax-H3 Video Generation Using Cache-DiT and SubBlock

·2026.08.28 09:00

LongCat Sparse model released

·2026.08.02 00:00

Accelerating Text-to-Video Generation via Calibrated Sparse Attention

·2026.07.21 09:00

New Sparse Attention Architecture DWARF Released

·2026.07.21 01:00

LG AI Research 291

·2026.07.16 09:00

Flash-MSA: Accelerating Million-Token Training via Sparse Attention Kernels

·2026.07.13 05:00

MiniMax M3: How Sparse Attention Makes Long-Horizon Agents Practical

·2026.07.08 09:00

Keye-VL-2.0-30B Model Released

·2026.06.18 18:00

MiniMax Sparse Attention for Million-Token Context (GitHub Repo)

·2026.06.15 09:00

MiniMax Unveils MSA for Ultra-Long-Context Processing

·2026.06.12 23:00

MiniMax Launches 1 Million-Token Context Model, Promises M3 Weight Release

·2026.06.03 09:00

MiniMax-M3 Debuts, Surpassing GPT-5.5 and Gemini 3.1 Pro on Key Benchmarks at Just 5-10% of the Cost

·2026.06.02 16:00

MiniMax Unveils M3

·2026.06.01 09:00

MiniMax previews M3 model with new sparse attention mechanism and 15.6x faster long-context response speed

·2026.05.29 09:00

RTPurbo: Converting Full Attention into Sparse

·2026.05.26 00:00

Elastic Cores for ViT Released

·2026.05.13 20:00

Lighthouse Attention Technique

·2026.05.13 00:00

Reading Notes on the DeepSeek-V4 Paper - Roh Jeongseok

·2026.04.29 09:00

Context length expanded to 1 million tokens

·2024.11.15 01:00

DeepSeek-V3.2-Exp Experimental Model Released

·1

#sparse-attention | AI Briefing