Tong Che

Latest

• LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning
• LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation
• Parallelized Spatiotemporal Binding
• EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision
• Bayesian Reparameterization of Reward-Conditioned Reinforcement Learning with Energy-based Models
• Guided Conditional Diffusion for Controllable Traffic Simulation
• Robust and Controllable Object-Centric Learning through Energy-based Models