HVision-NKU

Accepted as [NeurIPS 2024] Spotlight Presentation Paper

Official code for the paper: Depth Anything At Any Condition

Official code for "SRFormer: Permuted Self-Attention for Single Image Super-Resolution" (ICCV 2023) and SRFormerV2

Official implementation of ImageCritic (CVPR 2026)

🎬 OraRL — Annotations as Rollouts for efficient, scalable reinforcement learning of unified video MLLMs.

[AAAI 2026]"Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection"

Official code for K-LoRA (CVPR 2025)

[CVPR26] Official code for GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristic

[TCSVT] Official repository of the paper "A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models"

Official Code for 'TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction' (ICCV 2025)

ASID-Caption: Attribute-Structured and Quality-Verified Audiovisual Instruction Dataset and Training Pipeline for Fine-Grained Video Understanding.

Official Code for 'AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction' (ICCV 2025)

[ICCV 2025] Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment

Official implement of ICML2024 Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation

[ICCV 2025] Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction