InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing Paper • 2603.09877 • Published Mar 10 • 48
Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports Paper • 2603.09896 • Published Mar 10 • 27
Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence Paper • 2603.07660 • Published Mar 8 • 86
FlowRL: Matching Reward Distributions for LLM Reasoning Paper • 2509.15207 • Published Sep 18, 2025 • 118
Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform Paper • 2512.08478 • Published Dec 9, 2025 • 77