GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing Paper • 2603.12264 • Published 1 day ago • 14
InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing Paper • 2603.09877 • Published 3 days ago • 39
RISE-Video: Can Video Generators Decode Implicit World Rules? Paper • 2602.05986 • Published Feb 5 • 26
Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform Paper • 2512.08478 • Published Dec 9, 2025 • 77
MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization Paper • 2510.08540 • Published Oct 9, 2025 • 109
Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing Paper • 2504.02826 • Published Apr 3, 2025 • 68