All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts Paper • 2609.24058 • Published 20 days ago • 55
MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation Paper • 2604.23789 • Published May 9 • 7
MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation Paper • 2604.23789 • Published May 9 • 7
Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs Paper • 2510.01954 • Published Oct 2, 2025 • 14
Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs Paper • 2510.01954 • Published Oct 2, 2025 • 14