About

Liangyan Gui is a Research Assistant Professor at the Siebel School of Computing and Data Science at the University of Illinois Urbana-Champaign. His research areas include Artificial Intelligence, with recent contributions such as co-authoring a paper on Self-supervised Open-world Hierarchical Entity Segmentation presented at the International Conference on Learning Representations (ICLR) in 2024. Gui has taught courses related to Machine Learning and Efficient & Predictive Vision, indicating his expertise in these fields. His work involves advancing understanding and techniques in AI, contributing to the academic community through research and teaching.

Research topics

• Computer Science
• Artificial Intelligence
• Machine Learning
• Computer vision
• Systems engineering
• Mathematics
• Multimedia
• Physics
• Engineering
• Human–computer interaction
• Psychology

Selected publications

• SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation

  2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2023 · 173 citations

  Senior authorCorresponding
  • Computer Science
  • Computer Science
  • Artificial Intelligence

  In this work, we present a novel framework built to sim-plify 3D asset generation for amateur users. To enable interactive generation, our method supports a variety of input modalities that can be easily provided by a human, in-cluding images, text, partially observed shapes and combinations of these, further allowing to adjust the strength of each input. At the core of our approach is an encoder-decoder, compressing 3D shapes into a compact latent representation, upon which a diffusion model is learned. To enable a variety of multimodal inputs, we employ task-specific encoders with dropout followed by a cross-attention mechanism. Due to its flexibility, our model naturally supports a variety of tasks, outperforming prior works on shape completion, image-based 3D reconstruction, and text-to-3D. Most interestingly, our model can combine all these tasks into one swiss-army-knife tool, enabling the user to perform shape generation using incomplete shapes, images, and textual descriptions at the same time, providing the relative weights for each input and facilitating interactivity. Despite our approach being shape-only, we further show an efficient method to texture the generated shape using large-scale text-to-image models.

  DOI

• InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion

  2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 2023 · 77 citations

  Senior authorCorresponding
  • Computer Science
  • Computer Science
  • Artificial Intelligence

  This paper addresses a novel task of anticipating 3D human-object interactions (HOIs). Most existing research on HOI synthesis lacks comprehensive whole-body interactions with dynamic objects, e.g., often limited to manipulating small or static objects. Our task is significantly more challenging, as it requires modeling dynamic objects with various shapes, capturing whole-body motion, and ensuring physically valid interactions. To this end, we propose InterDiff, a framework comprising two key steps: (i) interaction diffusion, where we leverage a diffusion model to encode the distribution of future human-object interactions; (ii) interaction correction, where we introduce a physics-informed predictor to correct denoised HOIs in a diffusion step. Our key insight is to inject prior knowledge that the interactions under reference with respect to contact points follow a simple pattern and are easily predictable. Experiments on multiple human-object interaction datasets demonstrate the effectiveness of our method for this task, capable of producing realistic, vivid, and remarkably longterm 3D HOI predictions.

  DOI

• Contrastive Mean Teacher for Domain Adaptive Object Detectors

  2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2023 · 107 citations

  • Computer Science
  • Artificial Intelligence
  • Computer Science

  Object detectors often suffer from the domain gap between training (source domain) and real-world applications (target domain). Mean-teacher self-training is a powerful paradigm in unsupervised domain adaptation for object detection, but it struggles with low-quality pseudo-labels. In this work, we identify the intriguing alignment and synergy between mean-teacher self-training and contrastive learning. Motivated by this, we propose Contrastive Mean Teacher (CMT) - a unified, general-purpose framework with the two paradigms naturally integrated to maximize beneficial learning signals. Instead of using pseudo-labels solely for final predictions, our strategy extracts object-level features using pseudo-labels and optimizes them via contrastive learning, without requiring labels in the target domain. When combined with recent mean-teacher self-training methods, CMT leads to new state-of-the-art target-domain performance: 51.9% mAP on Foggy Cityscapes, outperforming the previously best by 2.1% mAP. Notably, CMT can stabilize performance and provide more significant gains as pseudo-label noise increases.

  DOI

Frequent coauthors

• Yu-Xiong Wang

  15 shared

• José M. F. Moura

  8 shared

• Shengcao Cao

  6 shared

• Yunze Man

  University of Illinois Urbana-Champaign

  6 shared

• Yu-Xiong Wang

  Jilin University

  6 shared

• Alexander G. Schwing

  6 shared

• João Paulo Costeira

  3 shared

• Cyril Jazra

  University of Illinois Urbana-Champaign

  3 shared

Labs

• Siebel School of Computing and Data SciencePI

Education

• Ph.D., Computer Science

  University of Illinois at Urbana-Champaign

  2005

• M.S., Computer Science

  University of Illinois at Urbana-Champaign

  2001

• B.S., Computer Science

  University of Science and Technology of China

  1998

Awards & honors

• Celebration of Excellence 2026
• Celebration of Excellence 2025
• Celebration of Excellence 2024
• Celebration of Excellence 2023
• Celebration of Excellence 2022

Similar researchers at University of Illinois Urbana-Champaign

• Jiawei Hanh-146
• Maria T. Grosse Perdekamph-141
• Gan Zhangh-134
• Jeffrey S. Mooreh-130
• Shuming Nieh-128