-
Peking University
- Beijing, China
- feifeiobama.github.io
- in/zhicheng-sun
- @feifeiobama
Highlights
- Pro
Lists (3)
Sort Name ascending (A-Z)
Starred repositories
Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling
Official PyTorch implementation of AdaFlow
This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation
Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope and StableVideoDiffusion by finetuning them using various r…
Demonstrations of Loss of Plasticity and Implementation of Continual Backpropagation
VQ-GAN for Various Data Modality based on Taming Transformers for High-Resolution Image Synthesis
Derivative-Free Guidance in Diffusion Models with Soft Value-Based Decoding. For controlled generation in DNA, RNA, proteins, molecules (+ images)
Official Implementation of "Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining"
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
In 2024, the strongest open-source implementation of asymmetric magvit_v2 supports inference code but excludes VQVAE. It supports the joint encoding of images and videos, accommodating arbitrary vi…
Enforce the output format (JSON Schema, Regex etc) of a language model
Official inference repo for FLUX.1 models
PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838
RewardBench: the first evaluation tool for reward models.
[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)
Utilities intended for use with Llama models.
Repo is required for the code of our research paper on micro-budget training of large scale diffusion model.
"SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow", Yuanzhi Zhu, Xingchao Liu, Qiang Liu
Implementation of rectified flow and some of its followup research / improvements in Pytorch
CosmicMan: A Text-to-Image Foundation Model for Humans (CVPR 2024)
[ECCV 2024] Official implementation of "RangeLDM: Fast Realistic LiDAR Point Cloud Generation"
[TMLR 2024] Official implementation of "NuTime: Numerically Multi-Scaled Embedding for Large-Scale Time-Series Pretraining". (The code is under review by Microsoft)
Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States
[CVPR 2024] Official implementation of CVPR 2024 paper: "Inversion-Free Image Editing with Natural Language"