Wenbing Huang

Reducing Symmetry Increase in Equivariant Neural Networks

Unified Biomolecular Trajectory Generation via Pretrained Variational Bridge

CloDS: Visual-Only Unsupervised Cloth Dynamics Learning in Unknown Conditions

DMFlow: Disordered Materials Generation by Flow Matching

GraphPlan: Graph-enhanced Planning via Thinking LLMs for Embodied Agents

PlanMoGPT: Flow-Enhanced Progressive Planning for Text to Motion Synthesis

Physical Dynamics as Next Geometric Graph Prediction

HBDrug3D: A Dataset and Benchmark for AI-Driven Heterobifunctional Molecule Design

MOF-BFN: Metal-Organic Frameworks Structure Prediction via Bayesian Flow Networks

Learning 3D Anisotropic Noise Distributions Improves Molecular Force Fields

Universally Invariant Learning in Equivariant GNNs

Force-Guided Bridge Matching for Full-Atom Time-Coarsened Dynamics of Peptides

DenoiseVAE: Learning Molecule-Adaptive Noise Distributions for Denoising-based 3D Molecular Pre-training

UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design

Geometric Mixture Models for Electrolyte Conductivity Prediction

Size-Generalizable RNA Structure Evaluation by Exploring Hierarchical Geometries

Think Then React: Towards Unconstrained Action-to-Reaction Motion Generation

Latent Retrieval Augmented Generation of Cross-Domain Protein Binders

UniSim: A Unified Simulator for Time-Coarsened Dynamics of Biomolecules

Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints

Large Language-Geometry Model: When LLM meets Equivariance

Subequivariant Morphology-Behavior Co-Evolution in 3D Environments

Geometric Spatiotemporal Transformer to Simulate Long-Term Physical Dynamics