Published 'RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers' at ICML 2025
Published 'Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator' at ICML 2025 (Spotlight, acceptance rate 2.6%)
Published 'Diffusion Bridge Implicit Models' at ICLR 2025 (co-first author)
Published 'Consistency Diffusion Bridge Models' at NeurIPS 2024 (co-first author)
Published 'Noise Contrastive Alignment of Language Models with Explicit Rewards' at NeurIPS 2024
Published 'Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models' at ICLR 2023
Co-authored technical report 'Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models' (arXiv:2405.04233, 2024)
arXiv preprint 'Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion' (2025)