Differential Transformer V2
•
47
None defined yet.
Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization
AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding
Official BizGenEval leaderboard on Hugging Face.
ASR Leaderboard for low resource languages
This is a leaderboard for magebench
Official Playground of Microsoft VibeVoice-ASR
High-fidelity 3D Generation from images
Generate 3D hand motion predictions from images