ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts

• URL: http://arxiv.org/abs/2507.20939v1
• Date: Mon, 28 Jul 2025 15:52:36 GMT
• Title: ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts
• Authors: Yuying Ge, Yixiao Ge, Chen Li, Teng Wang, Junfu Pu, Yizhuo Li, Lu Qiu, Jin Ma, Lisheng Duan, Xinyu Zuo, Jinwen Luo, Weibo Gu, Zexuan Li, Xiaojing Zhang, Yangyu Tao, Han Hu, Di Wang, Ying Shan,
• Abstract summary: ARC-Hunyuan-Video is a multimodal model that processes visual, audio, and textual signals end-to-end for structured comprehension.<n>Our model is capable of multi-granularity timestamped video captioning and summarization, open-ended video question answering, temporal video grounding, and video reasoning.
• Score: 56.75723197779384
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real-world user-generated short videos, especially those distributed on platforms such as WeChat Channel and TikTok, dominate the mobile internet. However, current large multimodal models lack essential temporally-structured, detailed, and in-depth video comprehension capabilities, which are the cornerstone of effective video search and recommendation, as well as emerging video applications. Understanding real-world shorts is actually challenging due to their complex visual elements, high information density in both visuals and audio, and fast pacing that focuses on emotional expression and viewpoint delivery. This requires advanced reasoning to effectively integrate multimodal information, including visual, audio, and text. In this work, we introduce ARC-Hunyuan-Video, a multimodal model that processes visual, audio, and textual signals from raw video inputs end-to-end for structured comprehension. The model is capable of multi-granularity timestamped video captioning and summarization, open-ended video question answering, temporal video grounding, and video reasoning. Leveraging high-quality data from an automated annotation pipeline, our compact 7B-parameter model is trained through a comprehensive regimen: pre-training, instruction fine-tuning, cold start, reinforcement learning (RL) post-training, and final instruction fine-tuning. Quantitative evaluations on our introduced benchmark ShortVid-Bench and qualitative comparisons demonstrate its strong performance in real-world video comprehension, and it supports zero-shot or fine-tuning with a few samples for diverse downstream applications. The real-world production deployment of our model has yielded tangible and measurable improvements in user engagement and satisfaction, a success supported by its remarkable efficiency, with stress tests indicating an inference time of just 10 seconds for a one-minute video on H20 GPU.

Related papers

• TinyLLaVA-Video: Towards Smaller LMMs for Video Understanding with Group Resampler [10.92767902813594]
  We introduce TinyLLaVA-Video, a lightweight yet powerful video understanding model with approximately 3.6B parameters.<n>The cornerstone of our design is the video-level group resampler, a novel mechanism that significantly reduces and controls the number of visual tokens at the video level.<n>TinyLLaVA-Video demonstrates exceptional efficiency, requiring only one day of training on 8 A100-40G GPUs.
  arXiv  Detail & Related papers  (2025-01-26T13:10:12Z)
• VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling [43.485687038460895]
  Long-context video modeling is critical for multimodal large language models (MLLMs)<n>This paper aims to address this issue from aspects of model architecture, training data, training strategy and evaluation benchmark.<n>We build a powerful video MLLM named VideoChat-Flash, which shows a leading performance on both mainstream long and short video benchmarks.
  arXiv  Detail & Related papers  (2024-12-31T18:01:23Z)
• Whats in a Video: Factorized Autoregressive Decoding for Online Dense Video Captioning [71.94122309290537]
  We propose an efficient, online approach to generate dense captions for videos. Our model uses a novel autoregressive factorized decoding architecture. Our approach shows excellent performance compared to both offline and online methods, and uses 20% less compute.
  arXiv  Detail & Related papers  (2024-11-22T02:46:44Z)
• Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs [56.040198387038025]
  We present a novel prompt-guided visual perception framework (abbreviated as Free Video-LLM) for efficient inference of training-free video LLMs. Our method effectively reduces the number of visual tokens while maintaining high performance across multiple video question-answering benchmarks.
  arXiv  Detail & Related papers  (2024-10-14T12:35:12Z)
• VideoLLM-online: Online Video Large Language Model for Streaming Video [27.073238234038826]
  We propose a novel Learning-In-Video-Stream framework, which enables temporally aligned, long-context, and real-time conversation within a continuous video stream. Our framework supports streaming dialogue in a 5-minute video clip at over 10 FPS on an A100 GPU. It also showcases state-of-the-art performance on public offline video benchmarks, such as recognition, captioning, and forecasting.
  arXiv  Detail & Related papers  (2024-06-17T17:55:32Z)
• Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization [52.63845811751936]
  Video pre-training is challenging due to the modeling of its dynamics video. In this paper, we address such limitations in video pre-training with an efficient video decomposition. Our framework is both capable of comprehending and generating image and video content, as demonstrated by its performance across 13 multimodal benchmarks.
  arXiv  Detail & Related papers  (2024-02-05T16:30:49Z)
• VidCoM: Fast Video Comprehension through Large Language Models with Multimodal Tools [44.78291853329394]
  textbfVidCoM is a fast adaptive framework that leverages Large Language Models (LLMs) to reason about videos using lightweight visual tools. An InsOVER algorithm locates the corresponding video events based on an efficient Hungarian matching between decompositions of linguistic instructions and video events.
  arXiv  Detail & Related papers  (2023-10-16T17:05:56Z)
• InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation [90.71796406228265]
  InternVid is a large-scale video-centric multimodal dataset that enables learning powerful and transferable video-text representations. The InternVid dataset contains over 7 million videos lasting nearly 760K hours, yielding 234M video clips accompanied by detailed descriptions of total 4.1B words.
  arXiv  Detail & Related papers  (2023-07-13T17:58:32Z)
• Let's Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought [62.619076257298204]
  We motivate framing video reasoning as the sequential understanding of a small number of video reasonings. We introduce VIP, an inference-time challenge dataset designed to explore models' reasoning capabilities through video chain-of-thought. We benchmark GPT-4, GPT-3, and VICUNA on VIP, demonstrate the performance gap in complex video reasoning tasks, and encourage future work.
  arXiv  Detail & Related papers  (2023-05-23T10:26:42Z)
• Revisiting the "Video" in Video-Language Understanding [56.15777956496518]
  We propose the atemporal probe (ATP), a new model for video-language analysis. We characterize the limitations and potential of current video-language benchmarks. We show that effectively integrating ATP into full video-level temporal models can improve efficiency and state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2022-06-03T17:57:33Z)

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.