Alert button
Picture for Trevor Darrell

Trevor Darrell

Alert button

Neural Network Diffusion

Feb 20, 2024
Kai Wang, Zhaopan Xu, Yukun Zhou, Zelin Zang, Trevor Darrell, Zhuang Liu, Yang You

Viaarxiv icon

InstanceDiffusion: Instance-level Control for Image Generation

Feb 05, 2024
Xudong Wang, Trevor Darrell, Sai Saketh Rambhatla, Rohit Girdhar, Ishan Misra

Viaarxiv icon

Rethinking Patch Dependence for Masked Autoencoders

Jan 25, 2024
Letian Fu, Long Lian, Renhao Wang, Baifeng Shi, Xudong Wang, Adam Yala, Trevor Darrell, Alexei A. Efros, Ken Goldberg

Viaarxiv icon

From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations

Jan 03, 2024
Evonne Ng, Javier Romero, Timur Bagautdinov, Shaojie Bai, Trevor Darrell, Angjoo Kanazawa, Alexander Richard

Viaarxiv icon

Unsupervised Universal Image Segmentation

Dec 28, 2023
Dantong Niu, Xudong Wang, Xinyang Han, Long Lian, Roei Herzig, Trevor Darrell

Viaarxiv icon

See, Say, and Segment: Teaching LMMs to Overcome False Premises

Dec 13, 2023
Tsung-Han Wu, Giscard Biamby, David Chan, Lisa Dunlap, Ritwik Gupta, Xudong Wang, Joseph E. Gonzalez, Trevor Darrell

Viaarxiv icon

Describing Differences in Image Sets with Natural Language

Dec 05, 2023
Lisa Dunlap, Yuhui Zhang, Xiaohan Wang, Ruiqi Zhong, Trevor Darrell, Jacob Steinhardt, Joseph E. Gonzalez, Serena Yeung-Levy

Viaarxiv icon

Readout Guidance: Learning Control from Diffusion Features

Dec 04, 2023
Grace Luo, Trevor Darrell, Oliver Wang, Dan B Goldman, Aleksander Holynski

Viaarxiv icon

Recursive Visual Programming

Dec 04, 2023
Jiaxin Ge, Sanjay Subramanian, Baifeng Shi, Roei Herzig, Trevor Darrell

Viaarxiv icon

IMProv: Inpainting-based Multimodal Prompting for Computer Vision Tasks

Dec 04, 2023
Jiarui Xu, Yossi Gandelsman, Amir Bar, Jianwei Yang, Jianfeng Gao, Trevor Darrell, Xiaolong Wang

Figure 1 for IMProv: Inpainting-based Multimodal Prompting for Computer Vision Tasks
Figure 2 for IMProv: Inpainting-based Multimodal Prompting for Computer Vision Tasks
Figure 3 for IMProv: Inpainting-based Multimodal Prompting for Computer Vision Tasks
Figure 4 for IMProv: Inpainting-based Multimodal Prompting for Computer Vision Tasks
Viaarxiv icon