Alert button
Picture for Michael Saxon

Michael Saxon

Alert button

Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies

Aug 06, 2023
Liangming Pan, Michael Saxon, Wenda Xu, Deepak Nathani, Xinyi Wang, William Yang Wang

Figure 1 for Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
Figure 2 for Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
Figure 3 for Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
Figure 4 for Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
Viaarxiv icon

Multilingual Conceptual Coverage in Text-to-Image Models

Jun 02, 2023
Michael Saxon, William Yang Wang

Figure 1 for Multilingual Conceptual Coverage in Text-to-Image Models
Figure 2 for Multilingual Conceptual Coverage in Text-to-Image Models
Figure 3 for Multilingual Conceptual Coverage in Text-to-Image Models
Figure 4 for Multilingual Conceptual Coverage in Text-to-Image Models
Viaarxiv icon

Let's Think Frame by Frame: Evaluating Video Chain of Thought with Video Infilling and Prediction

May 23, 2023
Vaishnavi Himakunthala, Andy Ouyang, Daniel Rose, Ryan He, Alex Mei, Yujie Lu, Chinmay Sonar, Michael Saxon, William Yang Wang

Figure 1 for Let's Think Frame by Frame: Evaluating Video Chain of Thought with Video Infilling and Prediction
Figure 2 for Let's Think Frame by Frame: Evaluating Video Chain of Thought with Video Infilling and Prediction
Figure 3 for Let's Think Frame by Frame: Evaluating Video Chain of Thought with Video Infilling and Prediction
Figure 4 for Let's Think Frame by Frame: Evaluating Video Chain of Thought with Video Infilling and Prediction
Viaarxiv icon

Data Augmentation for Diverse Voice Conversion in Noisy Environments

May 18, 2023
Avani Tanna, Michael Saxon, Amr El Abbadi, William Yang Wang

Figure 1 for Data Augmentation for Diverse Voice Conversion in Noisy Environments
Figure 2 for Data Augmentation for Diverse Voice Conversion in Noisy Environments
Figure 3 for Data Augmentation for Diverse Voice Conversion in Noisy Environments
Viaarxiv icon

Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings

May 03, 2023
Daniel Rose, Vaishnavi Himakunthala, Andy Ouyang, Ryan He, Alex Mei, Yujie Lu, Michael Saxon, Chinmay Sonar, Diba Mirza, William Yang Wang

Figure 1 for Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings
Figure 2 for Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings
Figure 3 for Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings
Figure 4 for Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings
Viaarxiv icon

Users are the North Star for AI Transparency

Mar 09, 2023
Alex Mei, Michael Saxon, Shiyu Chang, Zachary C. Lipton, William Yang Wang

Figure 1 for Users are the North Star for AI Transparency
Figure 2 for Users are the North Star for AI Transparency
Figure 3 for Users are the North Star for AI Transparency
Viaarxiv icon

CausalDialogue: Modeling Utterance-level Causality in Conversations

Dec 20, 2022
Yi-Lin Tuan, Alon Albalak, Wenda Xu, Michael Saxon, Connor Pryor, Lise Getoor, William Yang Wang

Figure 1 for CausalDialogue: Modeling Utterance-level Causality in Conversations
Figure 2 for CausalDialogue: Modeling Utterance-level Causality in Conversations
Figure 3 for CausalDialogue: Modeling Utterance-level Causality in Conversations
Figure 4 for CausalDialogue: Modeling Utterance-level Causality in Conversations
Viaarxiv icon

Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis

Oct 10, 2022
Wenda Xu, Yilin Tuan, Yujie Lu, Michael Saxon, Lei Li, William Yang Wang

Figure 1 for Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis
Figure 2 for Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis
Figure 3 for Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis
Figure 4 for Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis
Viaarxiv icon

Causal Balancing for Domain Generalization

Jun 10, 2022
Xinyi Wang, Michael Saxon, Jiachen Li, Hongyang Zhang, Kun Zhang, William Yang Wang

Figure 1 for Causal Balancing for Domain Generalization
Figure 2 for Causal Balancing for Domain Generalization
Figure 3 for Causal Balancing for Domain Generalization
Figure 4 for Causal Balancing for Domain Generalization
Viaarxiv icon

Automatically Identifying Semantic Bias in Crowdsourced Natural Language Inference Datasets

Dec 16, 2021
Michael Saxon, Xinyi Wang, William Yang Wang

Figure 1 for Automatically Identifying Semantic Bias in Crowdsourced Natural Language Inference Datasets
Figure 2 for Automatically Identifying Semantic Bias in Crowdsourced Natural Language Inference Datasets
Figure 3 for Automatically Identifying Semantic Bias in Crowdsourced Natural Language Inference Datasets
Figure 4 for Automatically Identifying Semantic Bias in Crowdsourced Natural Language Inference Datasets
Viaarxiv icon