Wei Ji
- Counterfactual Evolution of Multimodal Datasets via Visual Programming
- Degradation-Aware Dynamic Schrödinger Bridge for Unpaired Image Restoration
- EvolvedGRPO: Unlocking Reasoning in LVLMs via Progressive Instruction Evolution
- MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs
- On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders
- VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language Models