Shoubin Yu

Current egocentric video generation models fail to execute multi-step manipulation tasks realistically, often skipping crucial actions and exhibiting poor physical dynamics.

Ditch the clunky tool-use pipelines: STORM teaches video-language models to reason about space and time using *internalized* latent trajectories, slashing inference costs while boosting accuracy.

Findings position LLMs as effective late-fusion mechanisms for multimodal learning analytics and demonstrate the viability of LLM-as-a-Judge for scalable, human-in-the-loop evaluation.

Achieve state-of-the-art video reasoning by using visual prompting during training to guide reinforcement learning, then distilling this ability into a model that performs grounded reasoning on raw videos without prompts at inference time.