Published 8 papers (on arXiv), developed 3 models (FlowDCN, NeuralSolverDistillation-SDXL, NeuralSolverDistillation-SD1.5), and maintained several datasets.
Research Experience
Involved in several research projects including but not limited to UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions; Emu3.5: Native Multimodal Models are World Learners.
Background
AI & ML interests
Miscellany
Active on the Hugging Face platform, following and commenting on the latest research developments in relevant fields.