Alert button
Picture for Xiang Zhou

Xiang Zhou

Alert button

Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings

Feb 09, 2024
Yichen Jiang, Xiang Zhou, Mohit Bansal

Viaarxiv icon

Data Factors for Better Compositional Generalization

Nov 08, 2023
Xiang Zhou, Yichen Jiang, Mohit Bansal

Viaarxiv icon

MA-NeRF: Motion-Assisted Neural Radiance Fields for Face Synthesis from Sparse Images

Jun 24, 2023
Weichen Zhang, Xiang Zhou, Yukang Cao, Wensen Feng, Chun Yuan

Figure 1 for MA-NeRF: Motion-Assisted Neural Radiance Fields for Face Synthesis from Sparse Images
Figure 2 for MA-NeRF: Motion-Assisted Neural Radiance Fields for Face Synthesis from Sparse Images
Figure 3 for MA-NeRF: Motion-Assisted Neural Radiance Fields for Face Synthesis from Sparse Images
Figure 4 for MA-NeRF: Motion-Assisted Neural Radiance Fields for Face Synthesis from Sparse Images
Viaarxiv icon

Exploring the Optimal Choice for Generative Processes in Diffusion Models: Ordinary vs Stochastic Differential Equations

Jun 03, 2023
Yu Cao, Jingrun Chen, Yixin Luo, Xiang Zhou

Figure 1 for Exploring the Optimal Choice for Generative Processes in Diffusion Models: Ordinary vs Stochastic Differential Equations
Figure 2 for Exploring the Optimal Choice for Generative Processes in Diffusion Models: Ordinary vs Stochastic Differential Equations
Figure 3 for Exploring the Optimal Choice for Generative Processes in Diffusion Models: Ordinary vs Stochastic Differential Equations
Figure 4 for Exploring the Optimal Choice for Generative Processes in Diffusion Models: Ordinary vs Stochastic Differential Equations
Viaarxiv icon

Decomposed Human Motion Prior for Video Pose Estimation via Adversarial Training

May 31, 2023
Wenshuo Chen, Xiang Zhou, Zhengdi Yu, Zhaoyu Zheng, Weixi Gu, Kai Zhang

Figure 1 for Decomposed Human Motion Prior for Video Pose Estimation via Adversarial Training
Figure 2 for Decomposed Human Motion Prior for Video Pose Estimation via Adversarial Training
Figure 3 for Decomposed Human Motion Prior for Video Pose Estimation via Adversarial Training
Figure 4 for Decomposed Human Motion Prior for Video Pose Estimation via Adversarial Training
Viaarxiv icon

RexUIE: A Recursive Method with Explicit Schema Instructor for Universal Information Extraction

Apr 28, 2023
Chengyuan Liu, Fubang Zhao, Yangyang Kang, Jingyuan Zhang, Xiang Zhou, Changlong Sun, Fei Wu, Kun Kuang

Figure 1 for RexUIE: A Recursive Method with Explicit Schema Instructor for Universal Information Extraction
Figure 2 for RexUIE: A Recursive Method with Explicit Schema Instructor for Universal Information Extraction
Figure 3 for RexUIE: A Recursive Method with Explicit Schema Instructor for Universal Information Extraction
Figure 4 for RexUIE: A Recursive Method with Explicit Schema Instructor for Universal Information Extraction
Viaarxiv icon

ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness

Apr 21, 2023
Archiki Prasad, Swarnadeep Saha, Xiang Zhou, Mohit Bansal

Figure 1 for ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness
Figure 2 for ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness
Figure 3 for ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness
Figure 4 for ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness
Viaarxiv icon

TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings

Apr 20, 2023
Norman P. Jouppi, George Kurian, Sheng Li, Peter Ma, Rahul Nagarajan, Lifeng Nai, Nishant Patil, Suvinay Subramanian, Andy Swing, Brian Towles, Cliff Young, Xiang Zhou, Zongwei Zhou, David Patterson

Figure 1 for TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings
Figure 2 for TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings
Figure 3 for TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings
Figure 4 for TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings
Viaarxiv icon

Scene Style Text Editing

Apr 20, 2023
Tonghua Su, Fuxiang Yang, Xiang Zhou, Donglin Di, Zhongjie Wang, Songze Li

Figure 1 for Scene Style Text Editing
Figure 2 for Scene Style Text Editing
Figure 3 for Scene Style Text Editing
Figure 4 for Scene Style Text Editing
Viaarxiv icon