# Post-Training VLMs for Video Mistake Detection

arXiv: https://arxiv.org/abs/2608.28406 · HTML: https://mlsanity.com/paper/2608.28406/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Builds on (most cited first, 25 of 25)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [Learning Memory-guided Normality for Anomaly Detection](https://mlsanity.com/paper/2003.13228/) (2020)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision](https://mlsanity.com/paper/2007.04687/) (2020)
- [Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning](https://mlsanity.com/paper/2101.10030/) (2021)
- [HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World](https://mlsanity.com/paper/2309.17024/) (2023)
- [Oops! Predicting Unintentional Action in Video](https://mlsanity.com/paper/1911.11206/) (2019)
- [DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO](https://mlsanity.com/paper/2506.07464/) (2025)
- [CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities](https://mlsanity.com/paper/2312.14556/) (2023)
- [PREGO: online mistake detection in PRocedural EGOcentric videos](https://mlsanity.com/paper/2404.01933/) (2024)
- [Seeing the Arrow of Time in Large Multimodal Models](https://mlsanity.com/paper/2506.03340/) (2025)
- [Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos](https://mlsanity.com/paper/2406.01486/) (2024)
- [VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice](https://mlsanity.com/paper/2601.05175/) (2026)
- [EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT](https://mlsanity.com/paper/2510.23569/) (2025)
- [Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks](https://mlsanity.com/paper/2503.22405/) (2025)
- [Self-supervised Learning for Unintentional Action Prediction](https://mlsanity.com/paper/2209.12074/) (2022)
- [Procedural Mistake Detection via Action Effect Modeling](https://mlsanity.com/paper/2512.03474/) (2025)
- [Leveraging Self-Supervised Training for Unintentional Action Recognition](https://mlsanity.com/paper/2209.11870/) (2022)

## Built on by (most cited first, 1 of 1)

- [Hand-Aware Transition Modeling for Bimanual Procedural Anomaly Detection](https://mlsanity.com/paper/2609.21207/) (2026)

## Abstract (arXiv)

Human mistakes are inevitable when following instructions, yet they can lead to severe consequences. As such, there has been an increased interest in developing methods for detecting mistakes in videos, with current methods mostly focusing on closed-set protocols. While successful in controlled settings, the closed-set assumption limits their wider applicability, as any changes to the task require collecting new data and re-training models. Instead, we argue that mistake detection methods should learn the general concept of a mistake, rather than overfitting to step-specific details. To reflect this, we introduce the Mistake Detection Video Question Answering (MD-VQA) protocol and accompanying benchmark. MD-VQA tests whether methods can discern if a step was executed correctly with respect to its description, for both seen and unseen actions. To address this important challenge, we propose the first video-language-model post-training technique for mistake detection. Our method uses a tailored reward function to encourage the model to identify discrepancies between an instruction and the corresponding video. Extensive evaluations demonstrate that this approach outperforms zero-shot, supervised fine-tuning, and post-training baselines. Notably, our method generalizes especially well to unseen procedures, for instance, with an improvement of up to 11.6% over the best-performing baseline on EP-VQA, paving the way toward general mistake detection. We release our code and benchmark at https://github.com/FedeSpu/mstk.