Long (Tony) Lian
About
I am an EECS PhD student at UC Berkeley, advised by Prof. Adam Yala and Prof. Trevor Darrell. I completed my B.A. in Computer Science at UC Berkeley, where I had the privilege of being supervised by Prof. Stella Yu during my undergraduate studies. My primary research focus involves data-efficient computer vision algorithms that leverage various forms of supervision or even operate without external supervision. I have also gained valuable research experiences as an intern with Baidu’s distributed deep learning team.
Email / Google Scholar / Twitter / LinkedIn / Github![](/assets/profile.jpg)
Recently, an identity attacker has been sending spam emails under my name through anonymous email addresses. Please disregard the spam email if you happen to receive one of them. I have already taken the necessary steps to report this fraudulent activity to the appropriate administrative team. I apologize for any confusion this may cause.
Publications (*: equal contribution)
CrossMAE: Rethinking Patch Dependence for Masked Autoencoders
Paper / Project Page / Code / BibTex / TL;DR
![](/assets/cover_images/2024-01-27-CrossMAE.jpg)
![](/assets/cover_images/2023-11-27-SLD.jpg)
LLM-grounded Video Diffusion Models
International Conference on Learning Representations (ICLR), 2024
Paper / Project Page / Code / BibTex / TL;DR
![](/assets/cover_images/2023-09-29-LVD.png)
LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models
Transactions on Machine Learning Research (TMLR)
Paper / Blog Post / Project Page / Demo / Code / Poster / BibTex / TL;DR
![](/assets/cover_images/2023-05-22-LMD.gif)
Q-Diffusion: Quantizing Diffusion Models
International Conference on Computer Vision (ICCV), 2023
Paper / Project Page / Code / BibTex / TL;DR
![](/assets/cover_images/2023-05-01-QDiffusion.png)
Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Paper / Project Page / Video / Demo Video / Code / Poster / BibTex / TL;DR
![](/assets/cover_images/2023-03-01-RCF-demo2.gif)
Unsupervised Selective Labeling for More Effective Semi-Supervised Learning
European Conference on Computer Vision (ECCV), 2022
![](/assets/cover_images/2022-08-08-USL-animation.png)
Debiased Learning from Naturally Imbalanced Pseudo-Labels
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
![](/assets/cover_images/2022-02-01-DebiasPL-animation.gif)
Unsupervised Visual Attention and Invariance for Reinforcement Learning
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
![](/assets/cover_images/2021-04-07-VAI-animation.gif)
Academic Services
Reviewer for CVPR/ECCV/ICCV/NeurIPS
Side Projects
Stable Diffusion XL Demo WebUI: A gradio-based WebUI that allows playing around with SDXL locally and on Colab for free.
AnimeGAN.js: An implementation of AnimeGAN, which converts photos to anime style online, with tf.js.
Rainbow: An implementation of Rainbow algorithm with PARL reinforcement learning framework.