Hugging Face's logo
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
VCLab-PolyU  updated a Space 15 days ago
VCLab-HKPU/README
VCLab-PolyU  published a Space 15 days ago
VCLab-HKPU/README
VCLab-PolyU  updated a collection 15 days ago
Benchmarks and Datasets
View all activity

Papers

ANTS: Adaptive Negative Textual Space Shaping for OOD Detection via Test-Time MLLM Understanding and Reasoning

View all Papers

VCLab-HKPU 's collections 6

Image/Video Restoration, Enhancement and Quality Assessment
This collection hosts VCLab's leading research in visual restoration, enhancement, and quality assessment, especially in real-world scenarios.
Image and Video Synthesis and Generation
This collection features VCLab's significant efforts in accelerating, distilling, and improving the image/video synthesis and generation models.
Architecture and Training Paradigms
This collection showcases VCLab's investigations on new architectures of vision transformers, LLMs, VLMs and their training paradigms.
Multimodal Perception, Understanding and Reasoning
VCLab's research in MLLM-based visual perception, understanding and reasoning, enhancing the multi-tasking capabilities of MLLMs.
3D Perception, Reconstruction and Generation
This collection gathers VCLab's research to sense, reconstruct, synthesize, and edit high-fidelity 3D worlds.
Benchmarks and Datasets
This comprehensive collection hosts PolyU VCLab's contributions to the evaluation benchmarks and training datasets for visual computing.
Image/Video Restoration, Enhancement and Quality Assessment
This collection hosts VCLab's leading research in visual restoration, enhancement, and quality assessment, especially in real-world scenarios.
Multimodal Perception, Understanding and Reasoning
VCLab's research in MLLM-based visual perception, understanding and reasoning, enhancing the multi-tasking capabilities of MLLMs.
Image and Video Synthesis and Generation
This collection features VCLab's significant efforts in accelerating, distilling, and improving the image/video synthesis and generation models.
3D Perception, Reconstruction and Generation
This collection gathers VCLab's research to sense, reconstruct, synthesize, and edit high-fidelity 3D worlds.
Architecture and Training Paradigms
This collection showcases VCLab's investigations on new architectures of vision transformers, LLMs, VLMs and their training paradigms.
Benchmarks and Datasets
This comprehensive collection hosts PolyU VCLab's contributions to the evaluation benchmarks and training datasets for visual computing.