Picture for Haokun Lin

Haokun Lin

DOGE: Towards Versatile Visual Document Grounding and Referring

Add code
Nov 26, 2024
Viaarxiv icon

Contrastive Learning with Counterfactual Explanations for Radiology Report Generation

Add code
Jul 19, 2024
Figure 1 for Contrastive Learning with Counterfactual Explanations for Radiology Report Generation
Figure 2 for Contrastive Learning with Counterfactual Explanations for Radiology Report Generation
Figure 3 for Contrastive Learning with Counterfactual Explanations for Radiology Report Generation
Figure 4 for Contrastive Learning with Counterfactual Explanations for Radiology Report Generation
Viaarxiv icon

Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs

Add code
Jun 28, 2024
Figure 1 for Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
Figure 2 for Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
Figure 3 for Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
Figure 4 for Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
Viaarxiv icon

Rotation and Permutation for Advanced Outlier Management and Efficient Quantization of LLMs

Add code
Jun 03, 2024
Viaarxiv icon

MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?

Add code
Mar 21, 2024
Viaarxiv icon

MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric

Add code
Mar 12, 2024
Viaarxiv icon

IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact

Add code
Mar 02, 2024
Figure 1 for IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact
Figure 2 for IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact
Figure 3 for IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact
Figure 4 for IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact
Viaarxiv icon

Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining

Add code
Apr 26, 2023
Figure 1 for Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining
Figure 2 for Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining
Figure 3 for Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining
Figure 4 for Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining
Viaarxiv icon

Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation

Add code
Mar 18, 2023
Viaarxiv icon