Yike Liu

LLMs can now "think with visual latents" by generating masks directly from their internal representations, dramatically improving referring comprehension and segmentation.

Real-world GUI agents can achieve over 72% success in complex mobile tasks by leveraging a unique hybrid training approach that integrates real-device execution and adaptive learning from failures.

RL fine-tuning on a massive new mobile GUI dataset closes the sim2real gap, outperforming supervised methods and suggesting a path to more robust vision-language agents.