activity
20242026
most citedLLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

2 citations · 3 across the 9 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2026

Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis

Shuang Chen, Quanxin Shou, Hangting Chen +16

Unified multimodal models provide a natural and promising architecture for understanding diverse and complex real-world knowledge while generating high-quality images. However, the…

cs.CV2026

GEMS: Agent-Native Multimodal Generation with Memory and Skills

Zefeng He, Siyuan Huang, Xiaoye Qu +4

Recent multimodal generation models have achieved remarkable progress on general-purpose generation tasks, yet continue to struggle with complex instructions and specialized downst…

cs.CV2026

ExFusion: Efficient Transformer Training via Multi-Experts Fusion

Jiacheng Ruan, Daize Dong, Xiaoye Qu +5

Mixture-of-Experts (MoE) models substantially improve performance by increasing the capacity of dense architectures. However, directly training MoE models requires considerable com…

cs.CV2025

From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration

Mingyang Song, Xiaoye Qu, Jiawei Zhou +1

Large Vision-Language Models (LVLMs) have achieved significant progress in combining visual comprehension with language generation. Despite this success, the training data of LVLMs…

cs.CV2024

SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information

Jiashuo Sun, Jihai Zhang, Yucheng Zhou +3

Large Vision-Language Models (LVLMs) have become pivotal at the intersection of computer vision and natural language processing. However, the full potential of LVLMs Retrieval-Augm…

cs.CV2024

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

Jihai Zhang, Xiaoye Qu, Tong Zhu +1

Contrastive Language-Image Pre-training (CLIP) has become a cornerstone in multimodal intelligence. However, recent studies discovered that CLIP can only encode one aspect of the f…