Bin Lin

SPAR introduces a novel framework that rectifies action policies by performing local fine-tuning in a residual space anchored to a pure behavior cloning policy, achieving state-of-the-art performance in offline policy improvement.

The paper demonstrates that enforcing a local conservative finite volume structure is crucial for achieving stable, accurate long-term autoregressive rollouts of plasma transport simulations, outperforming learned neural network approaches.

This paper introduces GEAR, a method for training a vector-quantized tokenizer and an autoregressive generator jointly and end-to-end, resolving the issue of non-differentiable VQ indices.

This paper proposes Twins, a unified continuous token space for multimodal models using ViT and VAE features, and addresses optimization imbalance with a focal regression objective.