Picture for Lei Li

Lei Li

Carnegie Mellon University

Weak-to-Strong Jailbreaking on Large Language Models

Add code
Feb 05, 2024
Viaarxiv icon

Ada-Retrieval: An Adaptive Multi-Round Retrieval Paradigm for Sequential Recommendations

Add code
Jan 31, 2024
Viaarxiv icon

Red Teaming Visual Language Models

Add code
Jan 23, 2024
Viaarxiv icon

Developing ChatGPT for Biology and Medicine: A Complete Review of Biomedical Question Answering

Add code
Jan 20, 2024
Viaarxiv icon

DarkShot: Lighting Dark Images with Low-Compute and High-Quality

Add code
Jan 10, 2024
Viaarxiv icon

Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations

Add code
Dec 28, 2023
Figure 1 for Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
Figure 2 for Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
Figure 3 for Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
Figure 4 for Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
Viaarxiv icon

SSFlowNet: Semi-supervised Scene Flow Estimation On Point Clouds With Pseudo Label

Add code
Dec 23, 2023
Figure 1 for SSFlowNet: Semi-supervised Scene Flow Estimation On Point Clouds With Pseudo Label
Figure 2 for SSFlowNet: Semi-supervised Scene Flow Estimation On Point Clouds With Pseudo Label
Figure 3 for SSFlowNet: Semi-supervised Scene Flow Estimation On Point Clouds With Pseudo Label
Figure 4 for SSFlowNet: Semi-supervised Scene Flow Estimation On Point Clouds With Pseudo Label
Viaarxiv icon

Silkie: Preference Distillation for Large Visual Language Models

Add code
Dec 17, 2023
Viaarxiv icon

Seam-guided local alignment and stitching for large parallax images

Add code
Nov 30, 2023
Figure 1 for Seam-guided local alignment and stitching for large parallax images
Figure 2 for Seam-guided local alignment and stitching for large parallax images
Figure 3 for Seam-guided local alignment and stitching for large parallax images
Figure 4 for Seam-guided local alignment and stitching for large parallax images
Viaarxiv icon

VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models

Add code
Nov 29, 2023
Figure 1 for VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models
Figure 2 for VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models
Figure 3 for VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models
Figure 4 for VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models
Viaarxiv icon