Picture for He Li

He Li

TextInPlace: Indoor Visual Place Recognition in Repetitive Structures with Scene Text Spotting and Verification

Add code
Mar 09, 2025
Viaarxiv icon

Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model

Add code
Mar 06, 2025
Viaarxiv icon

EmoAssist: Emotional Assistant for Visual Impairment Community

Add code
Feb 13, 2025
Viaarxiv icon

Physics-informed deep learning for infectious disease forecasting

Add code
Jan 16, 2025
Figure 1 for Physics-informed deep learning for infectious disease forecasting
Figure 2 for Physics-informed deep learning for infectious disease forecasting
Figure 3 for Physics-informed deep learning for infectious disease forecasting
Figure 4 for Physics-informed deep learning for infectious disease forecasting
Viaarxiv icon

Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning

Add code
Nov 17, 2024
Figure 1 for Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning
Figure 2 for Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning
Figure 3 for Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning
Figure 4 for Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning
Viaarxiv icon

Multi-Uncertainty Aware Autonomous Cooperative Planning

Add code
Nov 01, 2024
Figure 1 for Multi-Uncertainty Aware Autonomous Cooperative Planning
Figure 2 for Multi-Uncertainty Aware Autonomous Cooperative Planning
Figure 3 for Multi-Uncertainty Aware Autonomous Cooperative Planning
Figure 4 for Multi-Uncertainty Aware Autonomous Cooperative Planning
Viaarxiv icon

Continuous Approximations for Improving Quantization Aware Training of LLMs

Add code
Oct 06, 2024
Viaarxiv icon

Evaluation of OpenAI o1: Opportunities and Challenges of AGI

Add code
Sep 27, 2024
Figure 1 for Evaluation of OpenAI o1: Opportunities and Challenges of AGI
Figure 2 for Evaluation of OpenAI o1: Opportunities and Challenges of AGI
Figure 3 for Evaluation of OpenAI o1: Opportunities and Challenges of AGI
Figure 4 for Evaluation of OpenAI o1: Opportunities and Challenges of AGI
Viaarxiv icon

CipherDM: Secure Three-Party Inference for Diffusion Model Sampling

Add code
Sep 09, 2024
Figure 1 for CipherDM: Secure Three-Party Inference for Diffusion Model Sampling
Figure 2 for CipherDM: Secure Three-Party Inference for Diffusion Model Sampling
Figure 3 for CipherDM: Secure Three-Party Inference for Diffusion Model Sampling
Figure 4 for CipherDM: Secure Three-Party Inference for Diffusion Model Sampling
Viaarxiv icon

Look Within, Why LLMs Hallucinate: A Causal Perspective

Add code
Jul 14, 2024
Viaarxiv icon