Guowei Xu

5

Papers

347

Total Citations

Papers (5)

LLaVA-CoT: Let Vision Language Models Reason Step-by-Step

Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction

metaTextGrad: Automatically optimizing language model optimizers

NeurIPS 2025arXiv

S-INF: Towards Realistic Indoor Scene Synthesis via Scene Implicit Neural Field

ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization