Yuxin Peng

Superficial reasoning in video temporal grounding can be transformed into high-quality, time-aware insights with the right optimization framework.

You can now automatically transform structurally flawed photos into aesthetically pleasing images, thanks to a new framework that plans and executes edits based on photographic principles.

MLLMs are better at understanding videos than directly grounding text queries within them, and a self-correction training loop can close the gap.