Tsung-Wei Ke

I am a postdoctoral researcher at CMU, working with Prof. Katerina Fragkiadaki. My research centers at computer vision, machine learning, and embodied perception. I obtain my Ph.D degree in Vision Science from UC Berkeley, advised by Prof. Stella Yu. Before that, I spent two years working with Dr. Tyng-Luh Liu at the Computer Vision Lab in Academia Sinica after graduating from NTU with a Bachelor of Chemical Engineering.

Contact

tsungwek@andrew.cmu.edu

Publications

3D Diffuser Actor: Policy Diffusion with 3D Scene Representations

Tsung-Wei Ke*, Nikolaos Gkanatsios*, and Katerina Fragkiadaki

Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following

Brian Yang, Huangyuan Su, Nikolaos Gkanatsios, Tsung-Wei Ke, Ayush Jain, Jeff Schneider, and Katerina Fragkiadaki

Learning Hierarchical Image Segmentation For Recognition and By Recognition

Tsung-Wei Ke*, Sangwoo Mo*, and Stella Yu
ICLR 2024 spotlight

Test time Adaptation with Diffusion Models

Mihir Prabhudesai*, Tsung-Wei Ke*, Alexander Cong Li, Deepak Pathak and Katerina Fragkiadaki
NeuRIPS 2023

Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformers

Tsung-Wei Ke, Jyh-Jing Hwang, Yunhui Guo, Xudong Wang and Stella X. Yu
CVPR 2022 (oral)

Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning

Tsung-Wei Ke, Jyh-Jing Hwang, and Stella X. Yu
ICLR 2021

Adversarial Structure Matching for Structured Prediction Tasks

Jyh-Jing Hwang, Tsung-Wei Ke, Jianbo Shi and Stella X. Yu
CVPR 2019

Adaptive Affinity Field for Semantic Segmentation

Tsung-Wei Ke*, Jyh-Jing Hwang*, Ziwei Liu and Stella X. Yu (*equal contribution)
ECCV 2018

Mooney Face Classification And Prediction By Learning Across Tone

Tsung-Wei Ke, Stella X. Yu and David Whitney
ICIP 2017 (oral)

Neural MultiGrid

Tsung-Wei Ke, Michael Maire, and Stella X. Yu
arXiv:1611.07661; CVPR 2017