7 papers
DUET: A Diversity-Quality Duet of Distillation Experts for Two-Step Video Generation
Zian Li, Litong Gong, Borui Liao +6
Diffusion models have enabled high-quality video generation in recent years, but the high cost of iterative sampling hinders their practical deployment. Few-step distillation allev…
Toward Better Geometric Representations for Molecule Generative Models
Shaoheng Yan, Zian Li, Cai Zhou +3
Geometric representation-conditioned molecule generation provides an effective paradigm that decouples molecule representation modeling from structure generation. By decoupling mol…
MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference
Ruijie Zhou, Fanxu Meng, Yufei Xu +4
DeepSeek Sparse Attention (DSA) sets the state of the art for fine-grained inference-time sparse attention by introducing a learned token-wise indexer that scores every prefix toke…
FlashMol: High-Quality Molecule Generation in as Few as Four Steps
Xinyuan Wei, Zian Li, Shaoheng Yan +2
Generating chemically valid 3D molecular conformations is critical for computational drug discovery. Classical diffusion-based models like GeoLDM perform well but require hundreds…
CanvasMAR: Improving Masked Autoregressive Video Prediction With Canvas
Zian Li, Muhan Zhang
Masked autoregressive models (MAR) have emerged as a powerful paradigm for image and video generation, combining the flexibility of masked modeling with the expressiveness of conti…
Rethinking Diffusion Models with Symmetries through Canonicalization with Applications to Molecular Graph Generation
Cai Zhou, Zijie Chen, Zian Li +7
Many generative tasks in chemistry and science involve distributions invariant to group symmetries (e.g., permutation and rotation). A common strategy enforces invariance and equiv…