CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified
Multiplet Upcycling

CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling

28 September 2024

Xiaoye Qu

Yu Cheng

Papers citing "CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling"

7 / 7 papers shown

Title
From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration Mingyang Song Xiaoye Qu Jiawei Zhou Yu-Xi Cheng VLM 59 1 0 17 Mar 2025
A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications Siyuan Mu Sen Lin MoE 129 1 0 10 Mar 2025
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment Chenghao Fan Zhenyi Lu Sichen Liu Xiaoye Qu Wei Wei Chengfeng Gu Yu-Xi Cheng MoE 136 0 0 24 Feb 2025
BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs Sheng Zhang Yanbo Xu Naoto Usuyama Hanwen Xu J. Bagga ... Carlo Bifulco M. Lungren Tristan Naumann Sheng Wang Hoifung Poon LM&MA MedIm 154 205 0 10 Jan 2025
LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training Xiaoye Qu Daize Dong Xuyang Hu Tong Zhu Weigao Sun Yu-Xi Cheng MoE 87 10 0 24 Nov 2024
Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning Xiaoye Qu Jiashuo Sun Wei Wei Yu Cheng MLLM LRM 26 14 0 30 Aug 2024
Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging Zhenyi Lu Chenghao Fan Wei Wei Xiaoye Qu Dangyang Chen Yu Cheng MoMe 42 48 0 17 Jun 2024