Dacheng Yin

4

Papers

260

Total Citations

Papers (4)

R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization

MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling

MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation

Learning Trajectories are Generalization Indicators