7 papers
SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models
Yuchen Wang, Qihui Zhu, Yang Liu +2
Recent multimodal large language models (MLLMs), such as Qwen2.5-VL and InternVL3, generate large numbers of vision tokens for high-resolution inputs, leading to substantial comput…
LaME: Learning to Think in Latent Space for Multimodal Embedding via Information Bottleneck
Peixi Wu, Biao Yang, Feipeng Ma +7
Reasoning-driven universal multimodal embedding has advanced rapidly by introducing Chain-of-Thought (CoT) reasoning into the embedding pipeline. Despite the strong performance acr…
OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing
Zhihong Chen, Xuehai Bai, Yang Shi +9
The performance of unified multimodal models for image generation and editing is fundamentally constrained by the quality and comprehensiveness of their training data. While existi…
Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment
Lubin Gan, Jing Zhang, Linhao Qu +3
The fine-grained classification of brain tumor subtypes from histopathological whole slide images is highly challenging due to subtle morphological variations and the scarcity of a…
EE-MLLM: A Data-Efficient and Compute-Efficient Multimodal Large Language Model
Feipeng Ma, Yizhou Zhou, Zheyu Zhang +7
Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated satisfactory performance across various vision-language tasks. Current approaches for vision and l…
Visual Perception by Large Language Model's Weights
Feipeng Ma, Hongwei Xue, Guangting Wang +7
Existing Multimodal Large Language Models (MLLMs) follow the paradigm that perceives visual information by aligning visual features with the input space of Large Language Models (L…