AI.info

Paul Pu Liang

Explore Paul Pu Liang on AI.info.

• SPADE: Self-Play in Adaptive Synthetic Executable Environments
• OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization
• When One Modality Sabotages the Others: A Diagnostic Lens on Multimodal Reasoning
• EQPO: Equitable Group Relative Policy Optimization for Clinical Reasoning
• PAGE-4D: Disentangled pose and geometry estimation for vggt-4d perception
• World-in-World: World Models in a Closed-Loop World
• HugAgent: Evaluating LLMs in Simulating Human-Like Individual Reasoning on Open-Ended Tasks