5 papers
Redundancy Principles for MLLMs Benchmarks
Zicheng Zhang, Xiangyu Zhao, Xinyu Fang +6
With the rapid iteration of Multi-modality Large Language Models (MLLMs) and the evolving demands of the field, the number of benchmarks produced annually has surged into the hundr…
Auto Cherry-Picker: Learning from High-quality Generative Data Driven by Language
Yicheng Chen, Xiangtai Li, Yining Li +4
Diffusion models can generate realistic and diverse images, potentially facilitating data availability for data-intensive perception tasks. However, leveraging these models to boos…
OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference
Xiangyu Zhao, Shengyuan Ding, Zicheng Zhang +10
Recent advancements in open-source multi-modal large language models (MLLMs) have primarily focused on enhancing foundational capabilities, leaving a significant gap in human prefe…
MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
Xinyu Fang, Kangrui Mao, Haodong Duan +4
The advent of large vision-language models (LVLMs) has spurred research into their applications in multi-modal contexts, particularly in video understanding. Traditional VideoQA be…
MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning
Xiangyu Zhao, Xiangtai Li, Haodong Duan +4
Multi-modal large language models (MLLMs) have made significant strides in various visual understanding tasks. However, the majority of these models are constrained to process low-…