4DLangVGGT: 4D Language-Visual Geometry Grounded Transformer Paper • 2512.05060 • Published Dec 4, 2025 • 18
FiVE: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models Paper • 2503.13684 • Published Mar 17, 2025 • 1
SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding Paper • 2412.09604 • Published Dec 12, 2024 • 38