Alert button
Picture for Changshui Zhang

Changshui Zhang

Alert button

CLOMO: Counterfactual Logical Modification with Large Language Models

Nov 30, 2023
Yinya Huang, Ruixin Hong, Hongming Zhang, Wei Shao, Zhicheng Yang, Dong Yu, Changshui Zhang, Xiaodan Liang, Linqi Song

Figure 1 for CLOMO: Counterfactual Logical Modification with Large Language Models
Figure 2 for CLOMO: Counterfactual Logical Modification with Large Language Models
Figure 3 for CLOMO: Counterfactual Logical Modification with Large Language Models
Figure 4 for CLOMO: Counterfactual Logical Modification with Large Language Models
Viaarxiv icon

A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning

Nov 14, 2023
Ruixin Hong, Hongming Zhang, Xinyu Pang, Dong Yu, Changshui Zhang

Viaarxiv icon

From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models

Sep 08, 2023
Changming Xiao, Qi Yang, Feng Zhou, Changshui Zhang

Figure 1 for From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models
Figure 2 for From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models
Figure 3 for From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models
Figure 4 for From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models
Viaarxiv icon

Bipartite Ranking Fairness through a Model Agnostic Ordering Adjustment

Jul 27, 2023
Sen Cui, Weishen Pan, Changshui Zhang, Fei Wang

Figure 1 for Bipartite Ranking Fairness through a Model Agnostic Ordering Adjustment
Figure 2 for Bipartite Ranking Fairness through a Model Agnostic Ordering Adjustment
Figure 3 for Bipartite Ranking Fairness through a Model Agnostic Ordering Adjustment
Figure 4 for Bipartite Ranking Fairness through a Model Agnostic Ordering Adjustment
Viaarxiv icon

Faithful Question Answering with Monte-Carlo Planning

May 04, 2023
Ruixin Hong, Hongming Zhang, Hong Zhao, Dong Yu, Changshui Zhang

Figure 1 for Faithful Question Answering with Monte-Carlo Planning
Figure 2 for Faithful Question Answering with Monte-Carlo Planning
Figure 3 for Faithful Question Answering with Monte-Carlo Planning
Figure 4 for Faithful Question Answering with Monte-Carlo Planning
Viaarxiv icon

Automatically Predict Material Properties with Microscopic Image Example Polymer Compatibility

Mar 22, 2023
Zhilong Liang, Zhenzhi Tan, Ruixin Hong, Wanli Ouyang, Jinying Yuan, Changshui Zhang

Figure 1 for Automatically Predict Material Properties with Microscopic Image Example Polymer Compatibility
Figure 2 for Automatically Predict Material Properties with Microscopic Image Example Polymer Compatibility
Figure 3 for Automatically Predict Material Properties with Microscopic Image Example Polymer Compatibility
Figure 4 for Automatically Predict Material Properties with Microscopic Image Example Polymer Compatibility
Viaarxiv icon

MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure

Oct 22, 2022
Yinya Huang, Hongming Zhang, Ruixin Hong, Xiaodan Liang, Changshui Zhang, Dong Yu

Figure 1 for MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure
Figure 2 for MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure
Figure 3 for MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure
Figure 4 for MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure
Viaarxiv icon

Rethinking Audio-visual Synchronization for Active Speaker Detection

Jun 21, 2022
Abudukelimu Wuerkaixi, You Zhang, Zhiyao Duan, Changshui Zhang

Figure 1 for Rethinking Audio-visual Synchronization for Active Speaker Detection
Figure 2 for Rethinking Audio-visual Synchronization for Active Speaker Detection
Figure 3 for Rethinking Audio-visual Synchronization for Active Speaker Detection
Figure 4 for Rethinking Audio-visual Synchronization for Active Speaker Detection
Viaarxiv icon

Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking

May 31, 2022
Peng Dai, Yiqiang Feng, Renliang Weng, Changshui Zhang

Figure 1 for Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking
Figure 2 for Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking
Figure 3 for Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking
Figure 4 for Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking
Viaarxiv icon

VD-PCR: Improving Visual Dialog with Pronoun Coreference Resolution

May 29, 2022
Xintong Yu, Hongming Zhang, Ruixin Hong, Yangqiu Song, Changshui Zhang

Figure 1 for VD-PCR: Improving Visual Dialog with Pronoun Coreference Resolution
Figure 2 for VD-PCR: Improving Visual Dialog with Pronoun Coreference Resolution
Figure 3 for VD-PCR: Improving Visual Dialog with Pronoun Coreference Resolution
Figure 4 for VD-PCR: Improving Visual Dialog with Pronoun Coreference Resolution
Viaarxiv icon