Jiajun Fan

Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards

ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning

SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration

Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models

Variational Supervised Contrastive Learning

Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization

EDiSon: Efficient Design-and-Control Optimization with Reinforcement Learning and Adaptive Design Reuse