VisionXLab
VisionXLab at Shanghai Jiao Tong University, led by Prof. Xue Yang.
Pinned Loading
Repositories
Showing 10 of 36 repositories
- EvoTok Public
Code repo for "EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation"
VisionXLab/EvoTok’s past year of commit activity - FIRM-Reward Public
Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation
VisionXLab/FIRM-Reward’s past year of commit activity - CrossEarth-SAR Public
The official repo of CrossEarth-SAR, a sar-centric and billion-scale geospatial foundation model for cross-domain semantic segmentation
VisionXLab/CrossEarth-SAR’s past year of commit activity - Point2RBox-v3 Public
[ICLR'26] Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization
VisionXLab/Point2RBox-v3’s past year of commit activity - LRS-VQA Public
[ICCV'25] When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning
VisionXLab/LRS-VQA’s past year of commit activity