Researcher at Thinking Machines Lab | PhD Student at UC Berkeley (EECS) | UC Berkeley 22' (CS) | Research interests: Improved Reasoning on LLMs/VLMs through RL
LLM-groundedDiffusion. LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models (LLM-grounded Diffusion: LMD, TMLR 2024)
481stable-diffusion-xl-demo. A gradio web UI demo for Stable Diffusion XL 1.0, with refiner and MultiGPU support
279AnimeGAN.js. AnimeGAN.js: Photo Animation for Everyone
229LLM-groundedVideoDiffusion. [ICLR 2024] LLM-grounded Video Diffusion Models (LVD): official implementation for the LVD paper
172CrossMAE. Official Implementation of the CrossMAE paper: Rethinking Patch Dependence for Masked Autoencoders
135UnsupervisedSelectiveLabeling. [ECCV 2022] Official Implementation for Unsupervised Selective Labeling for More Effective Semi-Supervised Learning
64igligen. Improved Implementation for Training GLIGEN: Open-Set Grounded Text-to-Image Generation
46RCF-UnsupVideoSeg. [CVPR 2023] Segmenting objects in videos without human annotations 🤯: Official implementation for Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping
40uARM.wasm. An ARM emulator ported to WebAssembly and running Linux in browsers.
35VAI-ReinforcementLearning. [CVPR 2021] Official Implementation of VAI: Unsupervised Visual Attention and Invariance for Reinforcement Learning
27RIDE-Swin-LongTailRecognition. Swin-Transformer-based version of RIDE (ICLR 2021 Spotlight)
12lotus. An interactive utility that breaks the interdependency between deep learning and coding
11longbox. An iOS App which can let you run Windows or Linux on your iOS devices without jailbreak, based on ported version of bochs.
9cubie-5110. Nokia 5110 driver using GPIO on Cubieboard, Cubietruck, and other A10,A13,A20 boards
6beauticam. 一个萌萌的小创意——给你的脸增加猫耳朵(纯web前端, Vue.js)
6spi_flash. spi flash driver in linux user space using gpio.
5colorQuest. An online game based on HTML5/JavaScript.
2jsdos. A emulator which is written in JavaScript to run DOS system.
2uARMSim. uARM Simulation Version
1LiuXueEatChicken. 留学吃鸡知识竞赛H5源码
1Query.jl. Query almost anything in julia
1PARL-Sample. Deep reinforcement learning using baidu PARL(maze,flappy bird and so on)
1pytorch-template. PyTorch deep learning projects made easy.
1sglang. SGLang is a fast serving framework for large language models and vision language models.
1jekyll-sass-converter. A Sass converter for Jekyll.
1