Alert button
Picture for Shiyue Zhang

Shiyue Zhang

Alert button

Particle-based Variational Inference with Generalized Wasserstein Gradient Flow

Oct 25, 2023
Ziheng Cheng, Shiyue Zhang, Longlin Yu, Cheng Zhang

Figure 1 for Particle-based Variational Inference with Generalized Wasserstein Gradient Flow
Figure 2 for Particle-based Variational Inference with Generalized Wasserstein Gradient Flow
Figure 3 for Particle-based Variational Inference with Generalized Wasserstein Gradient Flow
Figure 4 for Particle-based Variational Inference with Generalized Wasserstein Gradient Flow
Viaarxiv icon

DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment

Aug 22, 2023
Xujie Zhang, Binbin Yang, Michael C. Kampffmeyer, Wenqing Zhang, Shiyue Zhang, Guansong Lu, Liang Lin, Hang Xu, Xiaodan Liang

Figure 1 for DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment
Figure 2 for DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment
Figure 3 for DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment
Figure 4 for DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment
Viaarxiv icon

MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies

May 26, 2023
Shiyue Zhang, Shijie Wu, Ozan Irsoy, Steven Lu, Mohit Bansal, Mark Dredze, David Rosenberg

Figure 1 for MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies
Figure 2 for MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies
Figure 3 for MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies
Figure 4 for MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies
Viaarxiv icon

HistAlign: Improving Context Dependency in Language Generation by Aligning with History

May 08, 2023
David Wan, Shiyue Zhang, Mohit Bansal

Figure 1 for HistAlign: Improving Context Dependency in Language Generation by Aligning with History
Figure 2 for HistAlign: Improving Context Dependency in Language Generation by Aligning with History
Figure 3 for HistAlign: Improving Context Dependency in Language Generation by Aligning with History
Figure 4 for HistAlign: Improving Context Dependency in Language Generation by Aligning with History
Viaarxiv icon

Evaluating the Factual Consistency of Large Language Models Through Summarization

Nov 15, 2022
Derek Tam, Anisha Mascarenhas, Shiyue Zhang, Sarah Kwan, Mohit Bansal, Colin Raffel

Figure 1 for Evaluating the Factual Consistency of Large Language Models Through Summarization
Figure 2 for Evaluating the Factual Consistency of Large Language Models Through Summarization
Figure 3 for Evaluating the Factual Consistency of Large Language Models Through Summarization
Figure 4 for Evaluating the Factual Consistency of Large Language Models Through Summarization
Viaarxiv icon

Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees

Sep 21, 2022
Swarnadeep Saha, Shiyue Zhang, Peter Hase, Mohit Bansal

Figure 1 for Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees
Figure 2 for Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees
Figure 3 for Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees
Figure 4 for Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees
Viaarxiv icon

Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization

Sep 08, 2022
Shiyue Zhang, David Wan, Mohit Bansal

Figure 1 for Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization
Figure 2 for Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization
Figure 3 for Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization
Figure 4 for Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization
Viaarxiv icon

SETSum: Summarization and Visualization of Student Evaluations of Teaching

Jul 08, 2022
Yinuo Hu, Shiyue Zhang, Viji Sathy, A. T. Panter, Mohit Bansal

Figure 1 for SETSum: Summarization and Visualization of Student Evaluations of Teaching
Figure 2 for SETSum: Summarization and Visualization of Student Evaluations of Teaching
Figure 3 for SETSum: Summarization and Visualization of Student Evaluations of Teaching
Figure 4 for SETSum: Summarization and Visualization of Student Evaluations of Teaching
Viaarxiv icon

Masked Part-Of-Speech Model: Does Modeling Long Context Help Unsupervised POS-tagging?

Jun 30, 2022
Xiang Zhou, Shiyue Zhang, Mohit Bansal

Figure 1 for Masked Part-Of-Speech Model: Does Modeling Long Context Help Unsupervised POS-tagging?
Figure 2 for Masked Part-Of-Speech Model: Does Modeling Long Context Help Unsupervised POS-tagging?
Figure 3 for Masked Part-Of-Speech Model: Does Modeling Long Context Help Unsupervised POS-tagging?
Figure 4 for Masked Part-Of-Speech Model: Does Modeling Long Context Help Unsupervised POS-tagging?
Viaarxiv icon

How Robust is Neural Machine Translation to Language Imbalance in Multilingual Tokenizer Training?

Apr 29, 2022
Shiyue Zhang, Vishrav Chaudhary, Naman Goyal, James Cross, Guillaume Wenzek, Mohit Bansal, Francisco Guzman

Figure 1 for How Robust is Neural Machine Translation to Language Imbalance in Multilingual Tokenizer Training?
Figure 2 for How Robust is Neural Machine Translation to Language Imbalance in Multilingual Tokenizer Training?
Figure 3 for How Robust is Neural Machine Translation to Language Imbalance in Multilingual Tokenizer Training?
Figure 4 for How Robust is Neural Machine Translation to Language Imbalance in Multilingual Tokenizer Training?
Viaarxiv icon