“I'd really like to play with Qwen2.5-VL at some point, perhaps for reading data-sheets for microchips. Nicely for some applications, it's also very good at reporting position of what it finds, which many ML tools are pretty mediocre at. https://qwenlm.github.io/blog/qwen2.5-vl/ Not really this application, but QvQ for visual reasoning is also impressive.…”
Apollo: An Exploration of Video Understanding in Large Multimodal Models
Despite the rapid integration of video perception capabilities into Large Multimodal Models (LMMs), the underlying mechanisms driving their video understanding remain poorly understood. Consequently, many design decisions in this domain are made without proper justification or analysis. The high computational cost of training and evaluating such models, coupled with limited open research, hinders the development of video-LMMs. To address this, we present a comprehensive study that helps uncover what effectively drives video understanding in LMMs. We begin by critically examining the primary contributors to the high computational requirements associated with video-LMM research and discover Scaling Consistency, wherein design and training decisions made on smaller models and datasets (up to a critical size) effectively transfer to larger models. Leveraging these insights, we explored many video-specific aspects of video-LMMs, including video sampling, architectures, data composition, training schedules, and more. For example, we demonstrated that fps sampling during training is vastly preferable to uniform frame sampling and which vision encoders are the best for video representation. Guided by these findings, we introduce Apollo, a state-of-the-art family of LMMs that achieve superior performance across different model sizes. Our models can perceive hour-long videos efficiently, with Apollo-3B outperforming most existing $7$B models with an impressive 55.1 on LongVideoBench. Apollo-7B is state-of-the-art compared to 7B LMMs with a 70.9 on MLVU, and 63.3 on Video-MME.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及- Meta releases family of multimodal models that comprehend hour-long video ↗anon373839 · 2024-12-16 · 3 分
- Meta's new Video Understanding Multimodal Model used Qwen model for training ↗BUFU · 2024-12-16 · 7 分
- Apollo: An Exploration of Video Understanding in Large Multimodal Models ↗bookofjoe · 2024-12-24 · 1 分