Picture for Jiachen Li

Jiachen Li

Uncertainty-Aware Diffusion Guided Refinement of 3D Scenes

Add code
Mar 19, 2025
Viaarxiv icon

Can Large Vision Language Models Read Maps Like a Human?

Add code
Mar 18, 2025
Viaarxiv icon

Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation

Add code
Mar 18, 2025
Viaarxiv icon

VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search

Add code
Mar 13, 2025
Viaarxiv icon

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

Add code
Mar 12, 2025
Viaarxiv icon

Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm

Add code
Mar 07, 2025
Viaarxiv icon

Unleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identification

Add code
Feb 10, 2025
Figure 1 for Unleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identification
Figure 2 for Unleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identification
Figure 3 for Unleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identification
Figure 4 for Unleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identification
Viaarxiv icon

Preference VLM: Leveraging VLMs for Scalable Preference-Based Reinforcement Learning

Add code
Feb 03, 2025
Figure 1 for Preference VLM: Leveraging VLMs for Scalable Preference-Based Reinforcement Learning
Figure 2 for Preference VLM: Leveraging VLMs for Scalable Preference-Based Reinforcement Learning
Figure 3 for Preference VLM: Leveraging VLMs for Scalable Preference-Based Reinforcement Learning
Figure 4 for Preference VLM: Leveraging VLMs for Scalable Preference-Based Reinforcement Learning
Viaarxiv icon

VidFormer: A novel end-to-end framework fused by 3DCNN and Transformer for Video-based Remote Physiological Measurement

Add code
Jan 07, 2025
Figure 1 for VidFormer: A novel end-to-end framework fused by 3DCNN and Transformer for Video-based Remote Physiological Measurement
Figure 2 for VidFormer: A novel end-to-end framework fused by 3DCNN and Transformer for Video-based Remote Physiological Measurement
Figure 3 for VidFormer: A novel end-to-end framework fused by 3DCNN and Transformer for Video-based Remote Physiological Measurement
Figure 4 for VidFormer: A novel end-to-end framework fused by 3DCNN and Transformer for Video-based Remote Physiological Measurement
Viaarxiv icon

Stealthy and Robust Backdoor Attack against 3D Point Clouds through Additional Point Features

Add code
Dec 10, 2024
Viaarxiv icon