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

arXiv: https://arxiv.org/abs/2507.20939 · HTML: https://mlsanity.com/paper/2507.20939/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 28 Jul 2025.

## Builds on (most cited first, 24 of 24)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension](https://mlsanity.com/paper/2307.16125/) (2023)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [CLIP2Video: Mastering Video-Text Retrieval via Image CLIP](https://mlsanity.com/paper/2106.11097/) (2021)
- [Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?](https://mlsanity.com/paper/2505.21374/) (2025)
- [video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models](https://mlsanity.com/paper/2406.15704/) (2024)
- [Audio-Visual LLM for Video Understanding](https://mlsanity.com/paper/2312.06720/) (2023)
- [EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning](https://mlsanity.com/paper/2312.06722/) (2023)
- [A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation](https://mlsanity.com/paper/2104.13030/) (2021)
- [Kwai Keye-VL Technical Report](https://mlsanity.com/paper/2507.01949/) (2025)
- [On Semantic Similarity in Video Retrieval](https://mlsanity.com/paper/2103.10095/) (2021)
- [VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning](https://mlsanity.com/paper/2504.07956/) (2025)
- [EgoPlan-Bench2: A Benchmark for Multimodal Large Language Model Planning in Real-World Scenarios](https://mlsanity.com/paper/2412.04447/) (2024)
- [Pre-trained Language Model based Ranking in Baidu Search](https://mlsanity.com/paper/2105.11108/) (2021)
- [video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model](https://mlsanity.com/paper/2502.11775/) (2025)

## Built on by (most cited first, 30 of 41)

- [Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning](https://mlsanity.com/paper/2508.04416/) (2025)
- [TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs](https://mlsanity.com/paper/2512.14698/) (2025)
- [Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation](https://mlsanity.com/paper/2602.02994/) (2026)
- [LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning](https://mlsanity.com/paper/2509.24786/) (2025)
- [AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration](https://mlsanity.com/paper/2510.10395/) (2025)
- [Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools](https://mlsanity.com/paper/2510.08480/) (2025)
- [Streaming Video Instruction Tuning](https://mlsanity.com/paper/2512.21334/) (2025)
- [LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs](https://mlsanity.com/paper/2603.19217/) (2026)
- [OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models](https://mlsanity.com/paper/2511.14582/) (2025)
- [AdaTooler-V: Adaptive Tool-Use for Images and Videos](https://mlsanity.com/paper/2512.16918/) (2025)
- [Active Perception Agent for Omnimodal Audio-Video Understanding](https://mlsanity.com/paper/2512.23646/) (2025)
- [OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention](https://mlsanity.com/paper/2602.05847/) (2026)
- [TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions](https://mlsanity.com/paper/2602.08711/) (2026)
- [Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO](https://mlsanity.com/paper/2511.16669/) (2025)
- [Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions](https://mlsanity.com/paper/2602.13013/) (2026)
- [Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models](https://mlsanity.com/paper/2510.05034/) (2025)
- [ChronusOmni: Improving Time Awareness of Omni Large Language Models](https://mlsanity.com/paper/2512.09841/) (2025)
- [D-ORCA: Dialogue-Centric Optimization for Robust Audio-Visual Captioning](https://mlsanity.com/paper/2602.07960/) (2026)
- [OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video](https://mlsanity.com/paper/2604.11102/) (2026)
- [OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models](https://mlsanity.com/paper/2605.12056/) (2026)
- [Stage-adaptive Token Selection for Efficient Omni-modal LLMs](https://mlsanity.com/paper/2605.20035/) (2026)
- [Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning](https://mlsanity.com/paper/2607.01667/) (2026)
- [OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models](https://mlsanity.com/paper/2608.03812/) (2026)
- [ViDiC: Video Difference Captioning](https://mlsanity.com/paper/2512.03405/) (2025)
- [OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning](https://mlsanity.com/paper/2606.08572/) (2026)
- [AVSCap: Orchestrating Audio-Visual Synergy for Omni-modal Video Captioning](https://mlsanity.com/paper/2607.12820/) (2026)
- [HiVid-Narrator: Hierarchical Video Narrative Generation with Scene-Primed ASR-anchored Compression](https://mlsanity.com/paper/2601.07366/) (2026)
- [Allocation Before Ranking: Decoupled Token Compression for OmniLLMs](https://mlsanity.com/paper/2608.01665/) (2026)
- [Decoupling Perception from Reasoning for Hallucination-Resistant Video Understanding](https://mlsanity.com/paper/2511.18463/) (2025)
- [StoryTR: Narrative-Centric Video Temporal Retrieval with Theory of Mind Reasoning](https://mlsanity.com/paper/2604.23198/) (2026)

## Abstract (arXiv)

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.