AI.info
Jing Zhang
Explore Jing Zhang on AI.info.
- Ancient-Bench: A Comprehensive Multi-millennial, Multi-medium, and Multi-script Benchmark for Ancient Chinese Artifact Text Recognition
- Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval
- JOintGS: Joint Optimization of Cameras, Bodies and 3D Gaussians for In-the-Wild Monocular Reconstruction
- PTQ4ARVG: Post-Training Quantization for AutoRegressive Visual Generation Models
- Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts
- Degradation-Aware Metric Prompting for Hyperspectral Image Restoration
- SARMAE: Masked Autoencoder for SAR Representation Learning
- GeoBridge: A Semantic-Anchored Multi-View Foundation Model Bridging Images and Text for Geo-Localization
- UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes
- GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenes
- Prune4Web: DOM Tree Pruning Programming for Web Agent
- Thinking in 360°: Humanoid Visual Search in the Wild
- Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI
- Rectified SpaAttn: Revisiting Attention Sparsity for Efficient Video Generation
- AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention
- DCMM-Transformer: Degree-Corrected Mixed-Membership Attention for Medical Imaging
- World Simulation with Video Foundation Models for Physical AI
- Residual Diffusion Bridge Model for Image Restoration
- PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model