ChenWu98

cycle-diffusion

[ICCV 2023] A latent space for stochastic diffusion models

unified-generative-zoo

[ICCV 2023] https://arxiv.org/abs/2210.05559

generative-visual-prompt

[NeurIPS 2022] (Amortized) distributional control for pre-trained generative models

Point-Then-Operate

Code for the ACL 2019 paper ``A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer``

cliport-batchify

A batched version of CLIPort: What and Where Pathways for Robotic Manipulation

Coupled-VAE

Code for the ACL 2020 paper ``On the Encoder-Decoder Incompatibility in Variational Text Modeling and Beyond``

cmu-vision.github.io

DeepSeek-VL

DeepSeek-VL: Towards Real-World Vision-Language Understanding

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

prismatic-vlms

A flexible and efficient codebase for training visually-conditioned language models (VLMs)

visualwebarena

VisualWebArena is a benchmark for multimodal agents.