2 papers
cs.CV2024
Beyond Filtering: Adaptive Image-Text Quality Enhancement for MLLM Pretraining
Han Huang, Yuqi Huo, Zijia Zhao +6
Multimodal large language models (MLLMs) have made significant strides by integrating visual and textual modalities. A critical factor in training MLLMs is the quality of image-tex…
cs.CV2024
Exploring the Design Space of Visual Context Representation in Video MLLMs
Yifan Du, Yuqi Huo, Kun Zhou +7
Video Multimodal Large Language Models (MLLMs) have shown remarkable capability of understanding the video semantics on various downstream tasks. Despite the advancements, there is…