Zhenyu Zhao

Injecting explicit Plücker-ray geometry and local feature sampling into foundation vision backbones drives egocentric 3D hand-object interaction error down to sub-3cm precision.

Agents can now switch models and environments without losing their identity or memory, revolutionizing how we think about long-lived AI systems.

Over 1,100 submissions reveal groundbreaking advancements in sports video understanding, with new methods pushing the boundaries of action prediction and localization.

Reconstructing 3D scenes from images obscured by smoke and extreme darkness is now significantly more achievable, thanks to insights gleaned from the NTIRE 2026 challenge.

Forget scaling laws: this humanoid robot model crushes benchmarks using 10x less data by cleverly pre-training on human videos and then fine-tuning on robot-specific movements.