Yi-Lun Du

Off-policy data, long thought to be incompatible with effective SFT, can be transformed via MCMC sampling to unlock generalization capabilities that rival or exceed on-policy RL.

Experiments show that SyncWorld can accurately simulate action outcomes in previously unseen settings, and that its capability of simulating rollouts enables test-time policy improvement without training.

Visual intelligence could be the key to unlocking AGI, challenging the dominance of language-based models in the quest for general intelligence.

Achieving a staggering 90.4% reduction in robot-motion error, Hydra-0 redefines how we model and control robotic actions across varied environments.

Achieving superior zero-shot generalization, the World Action Planner outperforms leading policy models by leveraging the reasoning power of Vision-Language Models.

Fixed-position models struggle with any-order inference, but new masked diffusion techniques unlock flexible generation capabilities that enhance performance in coding and reasoning tasks.

Exploration as a pretraining axis can boost generative model performance by up to 36%, revolutionizing how we approach end-to-end generation.

A 1000x larger video reasoning dataset reveals early signs of emergent generalization, offering a new foundation for training and evaluating spatiotemporal AI.