# Towards multi-modal forgery representation learning for AI-generated video detection and localization

arXiv: https://arxiv.org/abs/2605.07232 · HTML: https://mlsanity.com/paper/2605.07232/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 17 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Pay Attention to MLPs](https://mlsanity.com/paper/2105.08050/) (2021)
- [FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset](https://mlsanity.com/paper/2108.05080/) (2021)
- [Detecting Multimedia Generated by Large AI Models: A Survey](https://mlsanity.com/paper/2402.00045/) (2024)
- [Preserving Fairness Generalization in Deepfake Detection](https://mlsanity.com/paper/2402.17229/) (2024)
- [A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detection](https://mlsanity.com/paper/2103.11326/) (2021)
- [The PartialSpoof Database and Countermeasures for the Detection of Short Fake Speech Segments Embedded in an Utterance](https://mlsanity.com/paper/2204.05177/) (2022)
- [On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection](https://mlsanity.com/paper/2410.23623/) (2024)
- [UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization](https://mlsanity.com/paper/2308.14395/) (2023)
- [P2SGrad: Refined Gradients for Optimizing Deep Face Models](https://mlsanity.com/paper/1905.02479/) (2019)
- [AV-Deepfake1M++: A Large-Scale Audio-Visual Deepfake Benchmark with Real-World Perturbations](https://mlsanity.com/paper/2507.20579/) (2025)

## Abstract (arXiv)

Recent advances in generative AI have democratized video creation at scale. AI-generated videos, including partially manipulated clips across visual and audio channels, pose escalating risks of semantic distortion and misuse, which motivates the need for reliable detection tools. Most existing AI-generated video detectors remain limited by single- or partial-modality of data modeling and the lack of fine-grained temporal forgery localization. To address these challenges, our primary novelty introduces a core architecture that jointly integrates an LMM semantic branch with a spatio-temporal (ST) visual branch and a multi-scale partial-spoof (PS) audio branch. This multi-modal approach enables simultaneous detection and fine-grained temporal localization of partially manipulated AI-generated video forgeries. Extensive experiments show that this approach outperforms existing state-of-the-art methods.