Li Song

Agent-repair leaderboards are more fragile than we thought: methods that peek at the evaluator's signals to guide internal repair choices can cause drastic reordering when the evaluator changes.

Finally, a method disentangles dynamic egocentric scenes into background, hand, and object components, enabling fine-grained understanding and editing.

Achieve state-of-the-art image super-resolution with a 50x smaller lookup table, unlocking deployment on resource-constrained devices.

Forget training separate models for each compression level; this framework achieves state-of-the-art extreme image compression with flexible bitrate control using a single diffusion-based arbitrary-scale super-resolution model.