Lean Pool: An AI-Maintained Archive of Formalized Mathematics Paper • 2609.25199 • Published 7 days ago • 27
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 11 days ago • 185 • 6
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 11 days ago • 185
Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training Paper • 2609.14306 • Published 15 days ago • 19
Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090 Paper • 2608.27370 • Published Aug 27 • 40 • 7
Improving the matrix multiplication exponent with modern optimization and AlphaEvolve Paper • 2608.16884 • Published Aug 17 • 20
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning Paper • 2608.09888 • Published Aug 10 • 793
Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration Paper • 2605.17423 • Published May 17 • 31
Seedance 2.0: Advancing Video Generation for World Complexity Paper • 2604.14148 • Published Apr 15 • 171
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning Paper • 2604.12374 • Published Apr 14 • 39