Picture for Kun Zhan

Kun Zhan

TransDiffuser: End-to-end Trajectory Generation with Decorrelated Multi-modal Representation for Autonomous Driving

Add code
May 14, 2025
Viaarxiv icon

PosePilot: Steering Camera Pose for Generative World Models with Self-supervised Depth

Add code
May 03, 2025
Viaarxiv icon

DiVE: Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformer

Add code
Apr 28, 2025
Viaarxiv icon

StyledStreets: Multi-style Street Simulator with Spatial and Temporal Consistency

Add code
Mar 27, 2025
Viaarxiv icon

Graph-Weighted Contrastive Learning for Semi-Supervised Hyperspectral Image Classification

Add code
Mar 19, 2025
Viaarxiv icon

BS-Mamba for Black-Soil Area Detection On the Qinghai-Tibetan Plateau

Add code
Mar 16, 2025
Viaarxiv icon

Finetuning Generative Trajectory Model with Reinforcement Learning from Human Feedback

Add code
Mar 13, 2025
Viaarxiv icon

Hierarchical Consensus Network for Multiview Feature Learning

Add code
Feb 04, 2025
Figure 1 for Hierarchical Consensus Network for Multiview Feature Learning
Figure 2 for Hierarchical Consensus Network for Multiview Feature Learning
Figure 3 for Hierarchical Consensus Network for Multiview Feature Learning
Figure 4 for Hierarchical Consensus Network for Multiview Feature Learning
Viaarxiv icon

BrainGuard: Privacy-Preserving Multisubject Image Reconstructions from Brain Activities

Add code
Jan 24, 2025
Viaarxiv icon

StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models

Add code
Dec 17, 2024
Figure 1 for StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models
Figure 2 for StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models
Figure 3 for StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models
Figure 4 for StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models
Viaarxiv icon