Kwai Keye-VL Technical Report

• URL: http://arxiv.org/abs/2507.01949v1
• Date: Wed, 02 Jul 2025 17:57:28 GMT
• Title: Kwai Keye-VL Technical Report
• Authors: Kwai Keye Team, Biao Yang, Bin Wen, Changyi Liu, Chenglong Chu, Chengru Song, Chongling Rao, Chuan Yi, Da Li, Dunju Zang, Fan Yang, Guorui Zhou, Hao Peng, Haojie Ding, Jiaming Huang, Jiangxia Cao, Jiankang Chen, Jingyun Hua, Jin Ouyang, Kaibing Chen, Kaiyu Jiang, Kaiyu Tang, Kun Gai, Shengnan Zhang, Siyang Mao, Sui Huang, Tianke Zhang, Tingting Gao, Wei Chen, Wei Yuan, Xiangyu Wu, Xiao Hu, Xingyu Lu, Yang Zhou, Yi-Fan Zhang, Yiping Yang, Yulong Chen, Zhenhua Wu, Zhenyu Li, Zhixin Ling, Ziming Li, Dehua Ma, Di Xu, Haixuan Gao, Hang Li, Jiawei Guo, Jing Wang, Lejian Ren, Muhao Wei, Qianqian Wang, Qigen Hu, Shiyao Wang, Tao Yu, Xinchen Luo, Yan Li, Yiming Liang, Yuhang Hu, Zeyi Lu, Zhuoran Yang, Zixing Zhang,
• Abstract summary: We introduce textbfKwai Keye-VL, a multimodal foundation model for short-video understanding.<n>The development of Keye-VL rests on two core pillars: a massive, high-quality dataset with a strong emphasis on video, and an innovative training recipe.<n>To validate our approach, we conduct extensive evaluations, showing that Keye-VL achieves state-of-the-art results on public video benchmarks and remains highly competitive on general image-based tasks.
• Score: 80.53170317017147
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities on static images, they often fall short in comprehending dynamic, information-dense short-form videos, a dominant medium in today's digital landscape. To bridge this gap, we introduce \textbf{Kwai Keye-VL}, an 8-billion-parameter multimodal foundation model engineered for leading-edge performance in short-video understanding while maintaining robust general-purpose vision-language abilities. The development of Keye-VL rests on two core pillars: a massive, high-quality dataset exceeding 600 billion tokens with a strong emphasis on video, and an innovative training recipe. This recipe features a four-stage pre-training process for solid vision-language alignment, followed by a meticulous two-phase post-training process. The first post-training stage enhances foundational capabilities like instruction following, while the second phase focuses on stimulating advanced reasoning. In this second phase, a key innovation is our five-mode ``cold-start'' data mixture, which includes ``thinking'', ``non-thinking'', ``auto-think'', ``think with image'', and high-quality video data. This mixture teaches the model to decide when and how to reason. Subsequent reinforcement learning (RL) and alignment steps further enhance these reasoning capabilities and correct abnormal model behaviors, such as repetitive outputs. To validate our approach, we conduct extensive evaluations, showing that Keye-VL achieves state-of-the-art results on public video benchmarks and remains highly competitive on general image-based tasks (Figure 1). Furthermore, we develop and release the \textbf{KC-MMBench}, a new benchmark tailored for real-world short-video scenarios, where Keye-VL shows a significant advantage.

Related papers

• DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework [26.661935208583756]
  virtual try-on (VVT) technology has garnered considerable academic interest owing to its promising applications in e-commerce advertising and entertainment.<n>We propose DreamVVT, which is inherently capable of leveraging diverse unpaired human-centric data to enhance adaptability in real-world scenarios.<n>In the first stage, we sample representative frames from the input video and utilize a multi-frame try-on model integrated with a vision-language model (VLM), to synthesize high-fidelity and semantically consistent try-on images.<n>In the second stage, skeleton maps together with fine-grained motion and appearance descriptions are
  arXiv  Detail & Related papers  (2025-08-04T18:27:55Z)
• Engagement Prediction of Short Videos with Large Multimodal Models [46.954597097369586]
  We empirically investigate the potential of large multimodal models (LMMs) for video engagement prediction.<n>VideoLLaMA2 processes key video frames, text-based metadata, and background sound, while Qwen2.5-VL utilizes only key video frames and text-based metadata.<n>By ensembling two types of models, our method achieves first place in the ICCV VQualA 2025 EVQA-SnapUGC Challenge on short-form video engagement prediction.
  arXiv  Detail & Related papers  (2025-08-04T15:21:29Z)
• Chain-of-Focus: Adaptive Visual Search and Zooming for Multimodal Reasoning via RL [70.1326027641056]
  Vision language models (VLMs) have achieved impressive performance across a variety of computer vision tasks.<n>We propose a Chain-of-Focus (CoF) method that allows VLMs to perform adaptive focusing and zooming in on key image regions.<n>We present a two-stage training pipeline, including supervised fine-tuning and reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-21T12:18:15Z)
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling [128.24325909395188]
  We introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series that builds upon InternVL 2.0.<n>InternVL 2.5 exhibits competitive performance, rivaling leading commercial models such as GPT-4o and Claude-3.5-Sonnet.<n>We hope this model contributes to the open-source community by setting new standards for developing and applying multimodal AI systems.
  arXiv  Detail & Related papers  (2024-12-06T18:57:08Z)
• Making Every Frame Matter: Continuous Activity Recognition in Streaming Video via Adaptive Video Context Modeling [19.205142489726875]
  Video activity recognition has become increasingly important in robots and embodied AI.<n>We introduce a novel system, CARS, to overcome these issues through adaptive video context modeling.<n>Our CARS runs at speeds $>$30 FPS on typical edge devices and outperforms all baselines by 1.2% to 79.7% in accuracy.
  arXiv  Detail & Related papers  (2024-10-19T05:50:00Z)
• Harnessing Vision-Language Pretrained Models with Temporal-Aware Adaptation for Referring Video Object Segmentation [34.37450315995176]
  Current Referring Video Object (RVOS) methods typically use vision and language models pretrained independently as backbones. We propose a temporal-aware prompt-tuning method, which adapts pretrained representations for pixel-level prediction. Our method performs favorably against state-of-the-art algorithms and exhibits strong generalization abilities.
  arXiv  Detail & Related papers  (2024-05-17T08:14:22Z)
• Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation [79.72299298976525]
  We propose to augment a vision-language pre-training model with a textual pre-trained language model (PLM) via vision-language knowledge distillation (VLKD) Experiments show that the resulting model has strong zero-shot performance on multimodal generation tasks, such as open-ended visual question answering and image captioning. The original textual language understanding and generation ability of the PLM is maintained after VLKD, which makes our model versatile for both multimodal and unimodal tasks.
  arXiv  Detail & Related papers  (2022-03-12T09:33:37Z)
• An Empirical Study of Training End-to-End Vision-and-Language Transformers [50.23532518166621]
  We present METER(textbfMultimodal textbfEnd-to-end textbfTransformtextbfER), through which we investigate how to design and pre-train a fully transformer-based VL model. Specifically, we dissect the model designs along multiple dimensions: vision encoders (e.g., CLIP-ViT, Swin transformer), text encoders (e.g., RoBERTa, DeBERTa), multimodal fusion (e.g., merged attention vs. co-
  arXiv  Detail & Related papers  (2021-11-03T17:55:36Z)
• UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation [76.12027504427708]
  This paper proposes UniVL: a Unified Video and Language pre-training model for both multimodal understanding and generation. It comprises four components, including two single-modal encoders, a cross encoder, and a decoder with the Transformer backbone. We develop two pre-training strategies, stage by stage pre-training (StagedP) and enhanced video representation (EnhancedV) to make the training process of the UniVL more effective.
  arXiv  Detail & Related papers  (2020-02-15T10:03:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.