3 papers
cs.CV2025
EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture
Xin He, Longhui Wei, Jianbo Ouyang +3
We propose EMMA, an efficient and unified architecture for multimodal understanding, generation and editing. Specifically, EMMA primarily consists of 1) An efficient autoencoder wi…
cs.CV2025
Mixpert: Mitigating Multimodal Learning Conflicts with Efficient Mixture-of-Vision-Experts
Xin He, Xumeng Han, Longhui Wei +2
Multimodal large language models (MLLMs) require a nuanced interpretation of complex image information, typically leveraging a vision encoder to perceive various visual scenarios.…
cs.CV2024
ViMoE: An Empirical Study of Designing Vision Mixture-of-Experts
Xumeng Han, Longhui Wei, Zhiyang Dou +6
Mixture-of-Experts (MoE) models embody the divide-and-conquer concept and are a promising approach for increasing model capacity, demonstrating excellent scalability across multipl…