Weiyang Liu

28

Papers

731

Total Citations

Papers (28)

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Deep Hyperspherical Learning

NeurIPS 2017arXiv

Ghost on the Shell: An Expressive Representation of General 3D Shapes

Reparameterized LLM Training via Orthogonal Equivalence Transformation

Decoupled Networks

Iterative Learning With Open-Set Noisy Labels

Regularizing Neural Networks via Minimizing Hyperspherical Energy

Orthogonal Over-Parameterized Training

Towards Principled Disentanglement for Domain Generalization

Self-Supervised 3D Face Reconstruction via Conditional Estimation

Pairwise Similarity Learning is SimPLE

One-shot Implicit Animatable Avatars with Model-based Priors

Structural Causal 3D Reconstruction

ChatHuman: Chatting about 3D Humans with Tools

VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models

GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs

SphereFace: Deep Hypersphere Embedding for Face Recognition

Learning towards Minimum Hyperspherical Energy

Coupled Variational Bayes via Optimization Embedding

Neural Similarity Learning

Meta Architecture Search

Locality Sensitive Teaching

Iterative Teaching by Label Synthesis

Nonparametric Teaching for Multiple Learners

Controlling Text-to-Image Diffusion by Orthogonal Finetuning

Large-Margin Softmax Loss for Convolutional Neural Networks

Iterative Machine Teaching

Towards Black-box Iterative Machine Teaching