Shiqi Zhang

Generalist world action models can be distilled into task-specific experts without a single online rollout, eliminating the need for costly environment interactions during on-policy post-training.

There is evidence that transitioning from diversity-based to uncertainty-based selection and explicitly reducing redundancy within acquisition batches improve model training, and initial evidence that larger acquisition batch sizes may be increasingly beneficial later in the labelling process.

Achieving a 3.36-fold speedup in action generation, DriftingVLA eliminates the need for iterative refinement while maintaining high performance in robot control tasks.

Physics-constraints generative AI can revolutionize tropical cyclone forecasting by dramatically reducing uncertainty and computational demands.