-
Learning to Grow Pretrained Models for Efficient Transformer Training
International Conference on Learning Representations (ICLR), 2023, Spotlight Presentation (Notably 25%)
This paper propose to accelerate transformer training by re-using pretrained models via a learnable, linear and sparse model growth operator.
[Paper]
[Code]
-
Equivariant Hypergraph Diffusion Neural Operators
International Conference on Learning Representations (ICLR), 2023
This work proposes a new hypergraph neural network architecture, which provably represents any continuous equivariant hypergraph diffusion operators.
[Paper]
[Code]
![]()
-
Is Attention All That NeRF Needs?
International Conference on Learning Representations (ICLR), 2023
We present Generalizable NeRF Transformer (GNT), a pure, unified transformer-based architecture that efficiently reconstructs Neural Radiance Fields (NeRFs) on the fly.
[Project Page]
[Paper]
[Code]
![]()
-
NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes
International Conference on Learning Representations (ICLR), 2023
We propose a novel collaborative contrastive loss for NeRF to segment objects in complex real-world scenes, without any annotation.
[Project Page]
[Paper]
[Code]
![]()
-
PINAT: A Permutation INvariance Augmented Transformer for NAS Predictor
AAAI Conference on Artificial Intelligence (AAAI), 2023
We propose a transformer-like NAS predictor consisting of partial permutation invariance augmentation model to characterize the sub-model structure.
[Paper]
[Code]
-
Signal Processing for Implicit Neural Representations
Advances in Neural Information Processing Systems (NeurIPS), 2022
We propose a theoretically grounded signal processing framework for Implicit Neural Representations (INR), which analytically manipulates INRs on the weight space through differential operators.
[Project Page]
[Paper]
[Code]
![]()
-
Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again
Advances in Neural Information Processing Systems (NeurIPS), 2022
We derive a topology-aware isometric initialization and a Dirichlet Energy guided achitectural rewiring technique that boost vanilla-GCNs to be the state-of-the-art.
[Paper]
[Code]
![]()
-
Unified Implicit Neural Stylization
European Conference on Computer Vision (ECCV), 2022
This work explores stylizing an implicit neural representation, using a generalized approach that can apply to various 2D and 3D representations.
[Project Page]
[Paper]
[Code]
![]()
-
SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image
European Conference on Computer Vision (ECCV), 2022
We present Single View NeRF (SinNeRF) consisting of thoughtfully designed semantic and geometry regularizations to train neural radiance field using only a single view.
[Project Page]
[Paper]
[Code]
![]()
-
Neural Implicit Dictionary Learning via Mixture-of-Expert Training
International Conference on Machine Learning (ICML), 2022
We present Neural Implicit Dictionary (NID) that learns and represents implicit neural representation as a sparse mixture of expert networks.
[Paper]
[Code]
![]()
-
Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022
We present the first fair and reproducible benchmark dedicated to assessing the "tricks" of training deep GNNs.
[Paper]
[Code]
![]()
-
Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Augmentations
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
We propose Aug-NeRF which augments NeRF with worst-case perturbations in three distinct levels with physical grounds.
[Paper]
[Code]
![]()
-
CADTransformer: Panoptic Symbol Spotting Transformer for CAD Drawings
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022, Oral Presentation
We present CADTransformer, a transformer based framework, to tackle the panoptic symbol spotting task for computer-aided design drawings.
[Paper]
[Code]
![]()
-
Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice
International Conference on Learning Representations (ICLR), 2022
We prove that self-attention is no more than low-pass filter, and propose two simple yet effective methods to counteract excessive smoothening.
[Paper]
[Code]
![]()
-
Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems
Advances in Neural Information Processing Systems (NeurIPS), 2021
We presents the Delayed Propagation Transformer (DePT) that specializes in the global modeling of CPS while taking into account the immutable constraints from the physical world.
[Paper]
[Code]
![]()
-
SoGCN: Second-Order Graph Convolutional Networks
arXiv preprint, 2021
We prove that second-order graph convolution is the maximally localized kernel with full representation power.
[Paper]
[Code]
![]()
-
TightCap: 3D Human Shape Capture with Clothing Tightness Field
ACM Transactions on Graphics (TOG), 2021
We propose a data-driven approach to capture both the human shape and dressed garments with only a single 3D human scan, by predicting clothing tightness.
[Project Page]
[Paper]
[Code]
![]()
Keep thy heart with all diligence; for out of it are the issues of life.
My exploration in computer science began by twelve years old, when my father bought me a C language programming book. And I spent my leisure time developing database software during high school. I did my undergraduate at ShanghaiTech University, where I was fortunate to work with Prof. Jingyi Yu on 3D human digitalization and cryogenic protein imaging, and studied algebra from Prof. Manolis C. Tsakiris. I also worked with Prof. Jianbo Shi on graph neural network and spectral graph theory in summer 2020. Now I'm focusing on learning, vision, imaging, as well as their mathematical principles. It is always hard to be a starter, hereby I would express my sincere gratitude to those who guided me walk through the novice village of academia.
