Xiangbo Gao

The results show that reliable scenario generation requires verifying realized behavior, not merely executable code, and demonstrate the value of explicit intermediate representations for verifiable and repairable language-driven co-simulation.

Users can alter video prompts on-the-fly, enabling a seamless interactive experience in long-form video generation.

Rule-grounded reasoning can cut average distance errors in driving VLAs by nearly half, fundamentally enhancing their decision-making transparency and reliability.

ACTS achieves full-thinking performance with up to 40% fewer tokens, enabling precise control over reasoning efficiency and accuracy.

Current video editing AIs still struggle to balance visual quality, instruction adherence, and localized edits, as revealed by a new benchmark designed to disentangle these factors.

Current video editing methods still struggle to maintain physical realism when removing objects, often leaving behind telltale signs like lingering shadows that betray the edit.

Control video super-resolution with a few keyframes: SparkVSR lets you guide the process and fix artifacts, unlike black-box VSR models.

Forget tedious prompt engineering: PISCO lets you insert objects into video with just a few keyframes, automatically handling appearance, motion, and scene interaction.

Foundation model-powered robots need more than just physical constraints—think modular safety guardrails that understand context, human intent, and evolving norms.