Alert button
Picture for Chunyuan Li

Chunyuan Li

Alert button

BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeys

Oct 21, 2023
Yu Gu, Jianwei Yang, Naoto Usuyama, Chunyuan Li, Sheng Zhang, Matthew P. Lungren, Jianfeng Gao, Hoifung Poon

Figure 1 for BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeys
Figure 2 for BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeys
Figure 3 for BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeys
Figure 4 for BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeys
Viaarxiv icon

Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V

Oct 17, 2023
Jianwei Yang, Hao Zhang, Feng Li, Xueyan Zou, Chunyuan Li, Jianfeng Gao

Figure 1 for Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
Figure 2 for Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
Figure 3 for Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
Figure 4 for Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
Viaarxiv icon

Improved Baselines with Visual Instruction Tuning

Oct 05, 2023
Haotian Liu, Chunyuan Li, Yuheng Li, Yong Jae Lee

Viaarxiv icon

MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Oct 03, 2023
Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Galley, Jianfeng Gao

Viaarxiv icon

Aligning Large Multimodal Models with Factually Augmented RLHF

Sep 25, 2023
Zhiqing Sun, Sheng Shen, Shengcao Cao, Haotian Liu, Chunyuan Li, Yikang Shen, Chuang Gan, Liang-Yan Gui, Yu-Xiong Wang, Yiming Yang, Kurt Keutzer, Trevor Darrell

Figure 1 for Aligning Large Multimodal Models with Factually Augmented RLHF
Figure 2 for Aligning Large Multimodal Models with Factually Augmented RLHF
Figure 3 for Aligning Large Multimodal Models with Factually Augmented RLHF
Figure 4 for Aligning Large Multimodal Models with Factually Augmented RLHF
Viaarxiv icon

Multimodal Foundation Models: From Specialists to General-Purpose Assistants

Sep 18, 2023
Chunyuan Li, Zhe Gan, Zhengyuan Yang, Jianwei Yang, Linjie Li, Lijuan Wang, Jianfeng Gao

Figure 1 for Multimodal Foundation Models: From Specialists to General-Purpose Assistants
Figure 2 for Multimodal Foundation Models: From Specialists to General-Purpose Assistants
Figure 3 for Multimodal Foundation Models: From Specialists to General-Purpose Assistants
Figure 4 for Multimodal Foundation Models: From Specialists to General-Purpose Assistants
Viaarxiv icon

An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models

Sep 18, 2023
Yadong Lu, Chunyuan Li, Haotian Liu, Jianwei Yang, Jianfeng Gao, Yelong Shen

Figure 1 for An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models
Figure 2 for An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models
Figure 3 for An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models
Figure 4 for An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models
Viaarxiv icon

Benchmarking and Analyzing Generative Data for Visual Recognition

Jul 25, 2023
Bo Li, Haotian Liu, Liangyu Chen, Yong Jae Lee, Chunyuan Li, Ziwei Liu

Figure 1 for Benchmarking and Analyzing Generative Data for Visual Recognition
Figure 2 for Benchmarking and Analyzing Generative Data for Visual Recognition
Figure 3 for Benchmarking and Analyzing Generative Data for Visual Recognition
Figure 4 for Benchmarking and Analyzing Generative Data for Visual Recognition
Viaarxiv icon

Semantic-SAM: Segment and Recognize Anything at Any Granularity

Jul 10, 2023
Feng Li, Hao Zhang, Peize Sun, Xueyan Zou, Shilong Liu, Jianwei Yang, Chunyuan Li, Lei Zhang, Jianfeng Gao

Figure 1 for Semantic-SAM: Segment and Recognize Anything at Any Granularity
Figure 2 for Semantic-SAM: Segment and Recognize Anything at Any Granularity
Figure 3 for Semantic-SAM: Segment and Recognize Anything at Any Granularity
Figure 4 for Semantic-SAM: Segment and Recognize Anything at Any Granularity
Viaarxiv icon