SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation Paper • 2505.19151 • Published May 25 • 2
Running 3.12k 3.12k The Ultra-Scale Playbook 🌌 The ultimate guide to training LLM on large GPU Clusters
Kimi-VL-A3B Collection Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking • 7 items • Updated Jul 1 • 75
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Paper • 2502.14786 • Published Feb 20 • 146
SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines Paper • 2502.14739 • Published Feb 20 • 106