Chen Wu (吴尘)'s repositories
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``
agent-attack
[Arxiv 2024] Adversarial attacks on multimodal agents
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``
cambrian
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
chameleon
Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
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.