Picture for Bin Dong

Bin Dong

Beijing International Center for Mathematical Research, Peking University, Center for Machine Learning Research, Peking University, National Biomedical Imaging Center, Peking University

Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait

Add code
Mar 17, 2025
Viaarxiv icon

AI-Driven Automated Tool for Abdominal CT Body Composition Analysis in Gastrointestinal Cancer Management

Add code
Mar 10, 2025
Viaarxiv icon

GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks

Add code
Feb 20, 2025
Viaarxiv icon

Consistency Diffusion Models for Single-Image 3D Reconstruction with Priors

Add code
Jan 31, 2025
Viaarxiv icon

MoColl: Agent-Based Specific and General Model Collaboration for Image Captioning

Add code
Jan 03, 2025
Figure 1 for MoColl: Agent-Based Specific and General Model Collaboration for Image Captioning
Figure 2 for MoColl: Agent-Based Specific and General Model Collaboration for Image Captioning
Figure 3 for MoColl: Agent-Based Specific and General Model Collaboration for Image Captioning
Figure 4 for MoColl: Agent-Based Specific and General Model Collaboration for Image Captioning
Viaarxiv icon

Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting

Add code
Oct 14, 2024
Figure 1 for Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting
Figure 2 for Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting
Figure 3 for Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting
Figure 4 for Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting
Viaarxiv icon

Herald: A Natural Language Annotated Lean 4 Dataset

Add code
Oct 09, 2024
Viaarxiv icon

PropSAM: A Propagation-Based Model for Segmenting Any 3D Objects in Multi-Modal Medical Images

Add code
Aug 25, 2024
Figure 1 for PropSAM: A Propagation-Based Model for Segmenting Any 3D Objects in Multi-Modal Medical Images
Figure 2 for PropSAM: A Propagation-Based Model for Segmenting Any 3D Objects in Multi-Modal Medical Images
Figure 3 for PropSAM: A Propagation-Based Model for Segmenting Any 3D Objects in Multi-Modal Medical Images
Figure 4 for PropSAM: A Propagation-Based Model for Segmenting Any 3D Objects in Multi-Modal Medical Images
Viaarxiv icon

State-observation augmented diffusion model for nonlinear assimilation

Add code
Jul 31, 2024
Viaarxiv icon

Demonstration Notebook: Finding the Most Suited In-Context Learning Example from Interactions

Add code
Jun 16, 2024
Viaarxiv icon