Yan Li

5 papers Mohamed bin Zayed University of Artificial Intelligence

• CausalVerse: Benchmarking Causal Representation Learning with Configurable High-Fidelity Simulations
• Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization
• SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought
• Towards Self-Refinement of Vision-Language Models with Triangular Consistency
• When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding