快手开源模型能看1小时视频，还只用了3B参数
看长视频对AI来说一直是个难题：1小时的视频，逐帧处理算力爆炸，跳帧又容易漏掉关键情节。快手开源的Keye-VL-2.0用了一个巧招——它把DeepSeek的稀疏注意力机制嫁接到自己的多模态架构上，让模型只关注视频里真正重要的帧和长程时序关系，而不是傻看每一帧。结果就是：它能无损处理25.6万token的上下文，相当于1小时视频，而激活的参数只有30亿（总参数量300亿，但MoE架构每次只激活一小部分）。更关键的是，它学会了在看完视频后调用代码、工具和搜索来修正自己的答案——比如你问“视频里那个人最后去了哪家店”，它如果拿不准，会自己去搜地图验证。在TimeLens（时间定位）、Video-MME-v2（长视频理解）等基准上，它超过了同体量的所有模型。这不是你明天就能用的产品，但它意味着：AI看长视频、做复杂推理的门槛正在被拆掉。
📄 原文摘要(英文)
We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding and agentic intelligence. To address the challenges of ultra-long contexts, information redundancy, and prohibitive computational costs inherent in hour-level videos, Keye-VL-2.0 is the first to adapt DeepSeek Sparse Attention (DSA) to GQA-based multimodal architectures, enabling lossless 256K context processing while capturing critical frames and long-range temporal dependencies. This architecture is underpinned by a highly optimized training and inference infrastructure, including scalable video I/O, heterogeneous ViT-LM parallelism, and custom DSA kernels that significantly maximize throughput and minimize computational overhead. Furthermore, to overcome the algorithmic dilemma of catastrophic forgetting during multi-task alignment, we introduce Cross-Modal Multi-Teacher On-Policy Distillation (MOPD) paired with Context-RL and Video-RL. By distilling dense token-level teacher feedback from on-policy rollouts back into the MoE backbone, which activates only 3B parameters, Keye-VL-2.0 natively empowers advanced agent collaboration across Code, Tool, and Search scenarios with multimodal self-correction. Extensive evaluations across video understanding, temporal grounding, reasoning, STEM, and agent benchmarks demonstrate that Keye-VL-2.0-30B-A3B achieves state-of-the-art performance among models of similar scale, particularly excelling in fine-grained temporal localization on TimeLens and long-video comprehension on Video-MME-v2 and LongVideoBench. We release our model checkpoints to accelerate community progress toward scalable and robust multimodal agentic applications.