-
Carnegie Mellon University
- Pittsburgh, PA
-
12:14
- 8h ahead - https://chenwu.io/
- https://scholar.google.com/citations?hl=en&user=WFKit_4AAAAJ&view_op=list_works&sortby=pubdate
Highlights
- Pro
-
agent-attack Public
[Arxiv 2024] Dissecting Adversarial Robustness of Multimodal LM Agents
-
visualwebarena Public
Forked from web-arena-x/visualwebarenaVisualWebArena is a benchmark for multimodal agents.
-
simpletransformers Public
Forked from ThilinaRajapakse/simpletransformersTransformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
Python Apache License 2.0 UpdatedOct 8, 2024 -
chameleon Public
Forked from facebookresearch/chameleonRepository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
Python Other UpdatedAug 20, 2024 -
prismatic-vlms Public
Forked from TRI-ML/prismatic-vlmsA flexible and efficient codebase for training visually-conditioned language models (VLMs)
Python MIT License UpdatedAug 9, 2024 -
Point-Then-Operate Public
Code for the ACL 2019 paper ``A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer``
-
cambrian Public
Forked from cambrian-mllm/cambrianCambrian-1 is a family of multimodal LLMs with a vision-centric design.
Python Apache License 2.0 UpdatedJul 2, 2024 -
-
LLaVA Public
Forked from haotian-liu/LLaVA[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Python Apache License 2.0 UpdatedJul 1, 2024 -
DeepSeek-VL Public
Forked from deepseek-ai/DeepSeek-VLDeepSeek-VL: Towards Real-World Vision-Language Understanding
-
cliport-batchify Public
Forked from cliport/cliportA batched version of CLIPort: What and Where Pathways for Robotic Manipulation
-
cycle-diffusion Public
[ICCV 2023] A latent space for stochastic diffusion models
-
generative-visual-prompt Public
[NeurIPS 2022] (Amortized) distributional control for pre-trained generative models
-
unified-generative-zoo Public
[ICCV 2023] https://arxiv.org/abs/2210.05559
-
Coupled-VAE Public
Code for the ACL 2020 paper ``On the Encoder-Decoder Incompatibility in Variational Text Modeling and Beyond``