activity
20242026
collaborators

9 papers

cs.CV2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.CV2026

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…

cs.LG2026

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…

cs.LG2025

GeoRecon: Graph-Level Representation Learning for 3D Molecules via Reconstruction-Based Pretraining

Shaoheng Yan, Zian Li, Muhan Zhang

The pretraining-finetuning paradigm has powered major advances in domains such as natural language processing and computer vision, with representative examples including masked lan…