C
Chang Liu
Researcher at Microsoft
Publications - 88
Citations - 833
Chang Liu is an academic researcher from Microsoft. The author has contributed to research in topics: Computer science & Chemistry. The author has an hindex of 10, co-authored 37 publications receiving 354 citations. Previous affiliations of Chang Liu include Peking University.
Papers
More filters
Journal Article
Latent Causal Invariant Model
TL;DR: A Latent Causal Invariance Model (LaCIM) is proposed which pursues causal prediction and introduces latent variables that are separated into output-causative factors and others that are spuriously correlated to the output via confounders to model the underlying causal factors.
Posted Content
Accelerated First-order Methods on the Wasserstein Space for Bayesian Inference.
TL;DR: Two inference methods by simulating the gradient flow on $\mathcal{P}_2$ via updating particles, and an acceleration method that speeds up all such particle-simulation-based inference methods are developed, to analyze the approximation flexibility of such methods.
Proceedings Article
Variational annealing of GANs: A Langevin perspective
Chenyang Tao,Shuyang Dai,Liqun Chen,Ke Bai,Junya Chen,Chang Liu,Ruiyi Zhang,Georgiy V. Bobashev,Lawrence Carin Duke +8 more
TL;DR: This work elucidates the theoretical roots of some of the empirical attempts to stabilize and improve GAN training with the introduction of likelihoods, highlights new insights from variational theory of diffusion processes to derive a likelihood-based regularizing scheme for GANTraining, and presents a novel approach to train GANs with an unnormalized distribution instead of empirical samples.
Proceedings ArticleDOI
Learning to Respond with Stickers: A Framework of Unifying Multi-Modality in Multi-Turn Dialog
TL;DR: Zhang et al. as mentioned in this paper proposed a sticker response selector (SRS) model, which employs a convolutional based sticker image encoder and a self-attention based multi-turn dialog encoder to obtain the representation of stickers and utterances.
Journal Article
Direct Molecular Conformation Generation
Jinhua Zhu,Yingce Xia,Chang Liu,Lijun Wu,Shufang Xie,Tong Wang,Yusong Wang,Wengang Zhou,Tao Qin,Houqiang Li,Tie-Yan Liu +10 more
TL;DR: This work proposes a method that directly predicts the coordinates of atoms, the loss function is invariant to roto-translation of coordinates and permutation of symmetric atoms, and the newly proposed model adaptively aggregates the bond and atom information and iteratively refines the coordinate of the generated conformation.