From the 1 of 9 linked papers with an AI index.
9 papers
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
Xinhao Li, Yuhan Zhu, Xiangyu Zeng +24
VideoChat3 is a fully open, 4B-parameter video-centric multimodal large language model that combines an efficient Inflated 3D Vision Transformer and adaptive frame resolution with…
FreeRet: MLLMs as Training-Free Retrievers
Yuhan Zhu, Xiangyu Zeng, Chenting Wang +6
Multimodal large language models (MLLMs) are emerging as versatile foundations for mixed-modality retrieval. Yet, they often require heavy post-hoc training to convert them into co…
InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision
Chenting Wang, Yuhan Zhu, Yicheng Xu +6
Large-scale video-text pretraining achieves strong performance but depends on noisy, synthetic captions with limited semantic coverage, often overlooking implicit world knowledge s…
UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation
Zhengrong Yue, Haiyu Zhang, Xiangyu Zeng +7
Tokenizer is a crucial component for both visual understanding and generation. To advance toward the ultimate goal of universal modeling, recent research has focused on developing…
InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling
Yi Wang, Xinhao Li, Ziang Yan +13
This paper aims to improve the performance of video multimodal large language models (MLLM) via long and rich context (LRC) modeling. As a result, we develop a new version of Inter…
VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling
Xinhao Li, Yi Wang, Jiashuo Yu +10
Long-context video modeling is critical for multimodal large language models (MLLMs), enabling them to process movies, online video streams, and so on. Despite its advances, handli…