4 papers
Dreaming in Flow: Bidirectional Self-Refinement for Unified Multimodal Models
Ke Hao, Yuanzhi Liang, Tingxi Chen +5
Unified multimodal models can generate images and interpret them, but their two capabilities are usually optimized with separate supervision. We introduce Bidirectional Self-Refine…
Separating Capability from Confidence: Grounded Dual-State Calibration for GRPO-Trained Medical Vision-Language Models
Yangyang Xie, Ke Hao, Jiaqi Liu +2
Medical vision-language models (VLMs) require confidence that reflects both answer correctness and patient-specific visual evidence. Recent GRPO-based methods optimize verbalized c…
Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training
Rui Li, Yuanzhi Liang, Ke Hao +4
Latent reward models can supervise visual diffusion models without decoding intermediate states into pixel space. This makes alignment with human preferences more efficient. Howeve…
Learning to Credit the Right Steps: Objective-aware Process Optimization for Visual Generation
Rui Li, Ke Hao, Yuanzhi Liang +4
Reinforcement learning, particularly Group Relative Policy Optimization (GRPO), has emerged as an effective framework for post-training visual generative models with human preferen…