11 papers
From Pixels to Words -- Towards Native One-Vision Models at Scale
Haiwen Diao, Jiahao Wang, Penghao Wu +18
Current vision-language models (VLMs) typically stitch together separate image encoders and language decoders via multi-stage alignment, a modular framework that inevitably fragmen…
LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
Xiang An, Yin Xie, Feilong Tang +27
We introduce LLaVA-OneVision-2 (LLaVA-OV-2), the most capable vision-language model in the LLaVA-OneVision series to date, achieving superior performance across a broad range of mu…
VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding
Haichen He, Jiayi Zhou, Sifeng Shang +3
Real-world long video understanding requires models to perform continuous tracking, information integration and memory retention over massive temporal spans within extreme video du…
OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
Feilong Tang, Xiang An, Yunyao Yan +16
Hypothesis. Artificial general intelligence is, at its core, a compression problem. Effective compression demands resonance: deep learning scales best when its architecture aligns…
VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness
Dian Zheng, Ziqi Huang, Hongbo Liu +9
Video generation has advanced significantly, evolving from producing unrealistic outputs to generating videos that appear visually convincing and temporally coherent. To evaluate t…
LLaVA-Video: Video Instruction Tuning With Synthetic Data
Yuanhan Zhang, Jinming Wu, Wei Li +4
The development of video large multimodal models (LMMs) has been hindered by the difficulty of curating large amounts of high-quality raw data from the web. To address this, we pro…