7 papers
VGR: Visual Grounded Reasoning
Jiacong Wang, Zijian Kang, Haochen Wang +8
In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which inherently suffers from language bias…
UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?
Yuanxin Liu, Rui Zhu, Shuhuai Ren +4
With the rapid growth of video generative models (VGMs), it is essential to develop reliable and comprehensive automatic metrics for AI-generated videos (AIGVs). Existing methods e…
The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer
Weixian Lei, Jiacong Wang, Haochen Wang +4
This paper introduces SAIL, a single transformer unified multimodal large language model (MLLM) that integrates raw pixel encoding and language decoding within a singular architect…
Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
Xin Xiao, Bohong Wu, Jiacong Wang +3
Existing image-text modality alignment in Vision Language Models (VLMs) treats each text token equally in an autoregressive manner. Despite being simple and effective, this method…
Unveiling the Tapestry of Consistency in Large Vision-Language Models
Yuan Zhang, Fei Xiao, Tao Huang +7
Large vision-language models (LVLMs) have recently achieved rapid progress, exhibiting great perception and reasoning abilities concerning visual information. However, when faced w…
World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering
Jiacong Wang, Bohong Wu, Haiyong Jiang +4
Recent advances in Vision-Language Models (VLMs) and the scarcity of high-quality multi-modal alignment data have inspired numerous researches on synthetic VLM data generation. The…