11 papers
DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts
Jiarui Feng, Hanqing Zeng, Karish Grover +11
Mixture-of-Experts (MoE) models have become a leading approach for decoupling parameter count from computational cost in large language models, yet effectively scaling MoE performa…
ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment
Zhipeng Bian, Jieming Zhu, Qijiong Liu +6
Recent advances in multimodal large language models (MLLMs) and diffusion models (DMs) have opened new possibilities for AI-generated content. Yet, personalized cover image generat…
CART: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling
Minghui Fang, Shengpeng Ji, Jialong Zuo +9
Cross-modal retrieval aims to search for instances, which are semantically related to the query through the interaction of different modal data. Traditional solutions utilize a sin…
MIRA: Empowering One-Touch AI Services on Smartphones with MLLM-based Instruction Recommendation
Zhipeng Bian, Jieming Zhu, Xuyang Xie +3
The rapid advancement of generative AI technologies is driving the integration of diverse AI-powered services into smartphones, transforming how users interact with their devices.…
RecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendation
Sashuai Zhou, Weinan Gan, Qijiong Liu +7
Recent advances in LLM-based recommendation have shown promise, yet their cross-domain generalization is hindered by a fundamental mismatch between language-centric pretraining and…
Learning Multi-Aspect Item Palette: A Semantic Tokenization Framework for Generative Recommendation
Qijiong Liu, Jieming Zhu, Zhaocheng Du +3
Traditional recommendation models often rely on unique item identifiers (IDs) to distinguish between items, which can hinder their ability to effectively leverage item content info…