210 citations · 727 across the 35 of their papers we have counts for
23 papers · 1 filter
Lyapunov Guidance: A Unified Framework for Stabilizing Generative Flows
Jingdong Zhang, Xinze Li, Yize Jiang +3
Flow matching has emerged as an effective framework for learning complex data distributions, but adapting pretrained flow models to new tasks often requires computationally expensi…
Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement
Meihua Dang, Jiaqi Han, Minkai Xu +3
Discrete diffusion models have recently emerged as strong alternatives to autoregressive language models, matching their performance through large-scale training. However, inferenc…
The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges
Sitao Luan, Chenqing Hua, Qincheng Lu +11
Homophily principle, \ie{} nodes with the same labels or similar attributes are more likely to be connected, has been commonly believed to be the main reason for the superiority of…
Equivariant Graph Neural Operator for Modeling 3D Dynamics
Minkai Xu, Jiaqi Han, Aaron Lou +6
Modeling the complex three-dimensional (3D) dynamics of relational systems is an important problem in the natural sciences, with applications ranging from molecular simulations to…
Equivariant Flow Matching with Hybrid Probability Transport
Yuxuan Song, Jingjing Gong, Minkai Xu +5
The generation of 3D molecules requires simultaneously deciding the categorical features~(atom types) and continuous features~(atom coordinates). Deep generative models, especially…
RetroDiff: Retrosynthesis as Multi-stage Distribution Interpolation
Yiming Wang, Yuxuan Song, Yiqun Wang +4
Retrosynthesis poses a key challenge in biopharmaceuticals, aiding chemists in finding appropriate reactant molecules for given product molecules. With reactants and products repre…
Scaling Riemannian Diffusion Models
Aaron Lou, Minkai Xu, Stefano Ermon
Riemannian diffusion models draw inspiration from standard Euclidean space diffusion models to learn distributions on general manifolds. Unfortunately, the additional geometric com…
VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs
Ling Yang, Ye Tian, Minkai Xu +7
GNN-to-MLP distillation aims to utilize knowledge distillation (KD) to learn computationally-efficient multi-layer perceptron (student MLP) on graph data by mimicking the output re…
Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
Xuan Zhang, Limei Wang, Jacob Helwig +60
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating…
Geometric Latent Diffusion Models for 3D Molecule Generation
Minkai Xu, Alexander Powers, Ron Dror +2
Generative models, especially diffusion models (DMs), have achieved promising results for generating feature-rich geometries and advancing foundational science problems such as mol…
MUDiff: Unified Diffusion for Complete Molecule Generation
Chenqing Hua, Sitao Luan, Minkai Xu +4
Molecule generation is a very important practical problem, with uses in drug discovery and material design, and AI methods promise to provide useful solutions. However, existing me…
FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning
Songtao Liu, Zhengkai Tu, Minkai Xu +6
Retrosynthetic planning aims to devise a complete multi-step synthetic route from starting materials to a target molecule. Current strategies use a decoupled approach of single-ste…
GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation
Minkai Xu, Lantao Yu, Yang Song +3
Predicting molecular conformations from molecular graphs is a fundamental problem in cheminformatics and drug discovery. Recently, significant progress has been achieved with machi…
Generative Coarse-Graining of Molecular Conformations
Wujie Wang, Minkai Xu, Chen Cai +5
Coarse-graining (CG) of molecular simulations simplifies the particle representation by grouping selected atoms into pseudo-beads and drastically accelerates simulation. However, s…
Learning Gradient Fields for Molecular Conformation Generation
Chence Shi, Shitong Luo, Minkai Xu +1
We study a fundamental problem in computational chemistry known as molecular conformation generation, trying to predict stable 3D structures from 2D molecular graphs. Existing mach…
An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming
Minkai Xu, Wujie Wang, Shitong Luo +4
Predicting molecular conformations (or 3D structures) from molecular graphs is a fundamental problem in many applications. Most existing approaches are usually divided into two ste…
Learning Neural Generative Dynamics for Molecular Conformation Generation
Minkai Xu, Shitong Luo, Yoshua Bengio +2
We study how to generate molecule conformations (i.e., 3D structures) from a molecular graph. Traditional methods, such as molecular dynamics, sample conformations via computationa…
Towards Generalized Implementation of Wasserstein Distance in GANs
Minkai Xu, Zhiming Zhou, Guansong Lu +3
Wasserstein GANs (WGANs), built upon the Kantorovich-Rubinstein (KR) duality of Wasserstein distance, is one of the most theoretically sound GAN models. However, in practice it doe…
Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator
Yuxuan Song, Qiwei Ye, Minkai Xu +1
Generative Adversarial Networks (GANs) have shown great promise in modeling high dimensional data. The learning objective of GANs usually minimizes some measure discrepancy, \texti…
Infomax Neural Joint Source-Channel Coding via Adversarial Bit Flip
Yuxuan Song, Minkai Xu, Lantao Yu +3
Although Shannon theory states that it is asymptotically optimal to separate the source and channel coding as two independent processes, in many practical communication scenarios t…
Energy-Based Imitation Learning
Minghuan Liu, Tairan He, Minkai Xu +1
We tackle a common scenario in imitation learning (IL), where agents try to recover the optimal policy from expert demonstrations without further access to the expert or environmen…
A Graph to Graphs Framework for Retrosynthesis Prediction
Chence Shi, Minkai Xu, Hongyu Guo +2
A fundamental problem in computational chemistry is to find a set of reactants to synthesize a target molecule, a.k.a. retrosynthesis prediction. Existing state-of-the-art methods…
GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation
Chence Shi, Minkai Xu, Zhaocheng Zhu +3
Molecular graph generation is a fundamental problem for drug discovery and has been attracting growing attention. The problem is challenging since it requires not only generating c…