Saurabh Gupta

Robots can now achieve precise physical interactions with objects without relying on task-specific rewards, thanks to a novel approach that decouples contact from keypoint tracking.

False proximity in biomedical embeddings can mislead causal reasoning, but a new method boosts discrimination accuracy by over 2.30x while slashing query latency by 133x.

Finally, a video generation model lets you puppeteer objects and their reactions independently, all while freely moving the camera.