TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts Paper • 2601.08881 • Published 6 days ago • 8
Bringing Characters to New Stories: Training-Free Theme-Specific Image Generation via Dynamic Visual Prompting Paper • 2501.15641 • Published Jan 26, 2025 • 1
HeadRouter: A Training-free Image Editing Framework for MM-DiTs by Adaptively Routing Attention Heads Paper • 2411.15034 • Published Nov 22, 2024 • 2