Differential Transformer V2
• 51
None defined yet.
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
Covering Human Action Space for Computer Use: Data Synthesis and Benchmark
Official BizGenEval leaderboard on Hugging Face.
ASR Leaderboard for low resource languages
This is a leaderboard for magebench
OmniParser, turn your LLM into GUI agent
High-fidelity 3D Generation from images
Official Playground of Microsoft VibeVoice-ASR