InstructX: Towards Unified Visual Editing with MLLM Guidance Paper • 2510.08485 • Published Oct 9, 2025 • 18
OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models Paper • 2509.17627 • Published Sep 22, 2025 • 66
HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning Paper • 2509.08519 • Published Sep 10, 2025 • 128