Video generation is rapidly evolving from single-shot synthesis to complex multi-shot audio-video (MSAV) narratives to meet real-world demands. However, evaluating such frontier models remains a fundamental challenge. Existing benchmarks are limited in scope and data diversity, and rely on rigid evaluation pipelines, preventing systematic and reliable assessment of modern MSAV models. To bridge these gaps, we introduce MSAVBench, the first comprehensive benchmark and adaptive hybrid evaluation framework for multi-shot audio-video generation. Our benchmark spans four key dimensions, video, audio, shot, and reference, covering diverse task settings, varying shot counts of up to 15, and challenging non-realistic scenarios. Our evaluation framework improves robustness through an adaptive self-correction mechanism for shot segmentation, instance-wise rubrics for subjective metrics, and tool-grounded evidence extraction for complex judgments. Furthermore, MSAVBench achieves high alignment with human judgments, reaching a Spearman rank correlation of 91.5%. Our systematic evaluation of 19 state-of-the-art closed- and open-source models shows that current systems still struggle with director-level control and fine-grained audio-visual synchronization, while modular or agentic generation pipelines offer a promising path toward narrowing the gap between open- and closed-source models. The benchmark data and evaluation code are publicly available at https://github.com/ali-vilab/MSAVBench.
UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating
The Hong Kong University of Science and Technology(香港科技大学);The Chinese University of Hong Kong(香港中文大学);Kling Team, Kuaishou Technology(Kling团队,快手科技);Tsinghua University(清华大学);Sun Yat-sen University(中山大学)
CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation
Shanghai Jiao Tong University(上海交通大学);University of Electronic Science and Technology of China(电子科技大学);Zhejiang University(浙江大学);The University of Tokyo(东京大学);Nanyang Technological University(南洋理工大学)
MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control
Peking University(北京大学);Kling Team, Kuaishou Technology(快手团队);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Sun Yat-sen University(中山大学)
Exploiting Temporal Audio-Visual Correlation Embedding for Audio-Driven One-Shot Talking Head Animation
School of Information Engineering, Guangdong University of Technology(广东工业大学信息工程学院);School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机科学与工程学院)
On Aligning Hierarchical Standardized Embedding for Audio-visual Generalized Zero-shot Learning
Southeast University(东南大学);The University of Hong Kong(香港大学);Beijing Institute of Technology(北京理工大学);Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education(新一代人工智能技术及其跨学科应用重点实验室(东南大学),教育部);School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院)
Audio-Visual Generalized Zero-Shot Learning using Pre-Trained Large Multi-Modal Models
University of Tübingen(蒂宾根大学);Tübingen AI Center(蒂宾根人工智能中心);Helmholtz Munich(慕尼黑亥姆霍兹中心);Technical University of Munich(慕尼黑工业大学);Localyzer GmbH(Localyzer有限公司)
S^3D-NeRF: Single-Shot Speech-Driven Neural Radiance Field for High Fidelity Talking Head Synthesis
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Alibaba Group(阿里巴巴集团)
FONT: Flow-guided One-shot Talking Head Generation with Natural Head Motions
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)
Multi-Timescale Motion-Decoupled Spiking Transformer for Audio-Visual Zero-Shot Learning
Harbin Institute of Technology(哈尔滨工业大学);Harbin Institute of Technology Suzhou Research Institute(哈尔滨工业大学苏州研究院);Peking University(北京大学);School of AI for Science(科学人工智能学院);Peng Cheng Laboratory(鹏城实验室)
OPT: One-shot Pose-Controllable Talking Head Generation
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China 2 School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China(1 中国科学院信息工程研究所,北京,中国 2 中国科学院大学网络空间安全学院,北京,中国)
SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification
Department of Computer Science, University of Haifa(海法大学计算机科学系);Independent Researcher(独立研究者);University of Stuttgart, Germany(斯图加特大学,德国);IMPRS-IS, Germany(智能系统国际Max Planck研究学校,德国)
SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM
Department of Computer Science, University at Albany - SUNY(University at Albany - SUNY 计算机科学系);School of Software & Microelectronics, Peking University(北京大学软件与微电子学院);Nanjing University(南京大学);Xiamen University(厦门大学);Department of Mathematics and Statistics, University at Albany - SUNY(University at Albany - SUNY 数学与统计学系)
AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis
University of Chinese Academy of Sciences(中国科学院大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Alibaba Group(阿里巴巴集团);Nanjing University(南京大学)
PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation
School of Computer Science and Electronic Engineering, University of Surrey(计算机科学与电子工程系,塞夫顿大学);Centre for Vision, Speech and Signal Processing, University of Surrey(视觉、语音与信号处理中心,塞夫顿大学);School of Artificial Intelligence and Computer Science, Jiangnan University(人工智能与计算机科学系,江南大学)