Video-IFBench: Evaluating Instruction Following of Multimodal LLMs in Video Understanding Scenarios Paper • 2608.25529 • Published 3 days ago • 16
Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning Paper • 2605.21487 • Published May 20 • 23
HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising Paper • 2603.08703 • Published Mar 9 • 32
Architecture Decoupling Is Not All You Need For Unified Multimodal Model Paper • 2511.22663 • Published Nov 27, 2025 • 29