How Confident are Video Models? Empowering Video Models to Express their Uncertainty

• URL: http://arxiv.org/abs/2510.02571v1
• Date: Thu, 02 Oct 2025 21:20:41 GMT
• Title: How Confident are Video Models? Empowering Video Models to Express their Uncertainty
• Authors: Zhiting Mei, Ola Shorinwa, Anirudha Majumdar,
• Abstract summary: Generative video models demonstrate impressive text-to-video capabilities, spurring widespread adoption in many real-world applications.<n>However, like large language models (LLMs), video generation models tend to hallucinate, producing plausible videos even when they are factually wrong.<n>This paper represents the first work towards quantifying the uncertainty of video models.
• Score: 11.251320289181338
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative video models demonstrate impressive text-to-video capabilities, spurring widespread adoption in many real-world applications. However, like large language models (LLMs), video generation models tend to hallucinate, producing plausible videos even when they are factually wrong. Although uncertainty quantification (UQ) of LLMs has been extensively studied in prior work, no UQ method for video models exists, raising critical safety concerns. To our knowledge, this paper represents the first work towards quantifying the uncertainty of video models. We present a framework for uncertainty quantification of generative video models, consisting of: (i) a metric for evaluating the calibration of video models based on robust rank correlation estimation with no stringent modeling assumptions; (ii) a black-box UQ method for video models (termed S-QUBED), which leverages latent modeling to rigorously decompose predictive uncertainty into its aleatoric and epistemic components; and (iii) a UQ dataset to facilitate benchmarking calibration in video models. By conditioning the generation task in the latent space, we disentangle uncertainty arising due to vague task specifications from that arising from lack of knowledge. Through extensive experiments on benchmark video datasets, we demonstrate that S-QUBED computes calibrated total uncertainty estimates that are negatively correlated with the task accuracy and effectively computes the aleatoric and epistemic constituents.

Related papers

• World Models That Know When They Don't Know: Controllable Video Generation with Calibrated Uncertainty [9.69325079034745]
  controllable video models often hallucinate, generating future video frames that are misaligned with physical reality.<n>We propose C3, an uncertainty quantification (UQ) method for training continuous-scale calibrated video models for dense confidence estimation.
  arXiv  Detail & Related papers  (2025-12-05T18:06:18Z)
• VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs [64.60035916955837]
  VANE-Bench is a benchmark designed to assess the proficiency of Video-LMMs in detecting anomalies and inconsistencies in videos.<n>Our dataset comprises an array of videos synthetically generated using existing state-of-the-art text-to-video generation models.<n>We evaluate nine existing Video-LMMs, both open and closed sources, on this benchmarking task and find that most of the models encounter difficulties in effectively identifying the subtle anomalies.
  arXiv  Detail & Related papers  (2024-06-14T17:59:01Z)
• Answering from Sure to Uncertain: Uncertainty-Aware Curriculum Learning for Video Question Answering [63.12469700986452]
  We introduce the concept of uncertainty-aware curriculum learning (CL) Here, uncertainty serves as the guiding principle for dynamically adjusting the difficulty. In practice, we seamlessly integrate the VideoQA model into our framework and conduct comprehensive experiments.
  arXiv  Detail & Related papers  (2024-01-03T02:29:34Z)
• Uncertainty-aware Language Modeling for Selective Question Answering [107.47864420630923]
  We present an automatic large language model (LLM) conversion approach that produces uncertainty-aware LLMs. Our approach is model- and data-agnostic, is computationally-efficient, and does not rely on external models or systems.
  arXiv  Detail & Related papers  (2023-11-26T22:47:54Z)
• A Lightweight Video Anomaly Detection Model with Weak Supervision and Adaptive Instance Selection [14.089888316857426]
  This paper focuses on weakly supervised video anomaly detection. We develop a lightweight video anomaly detection model. We show that our model can achieve comparable or even superior AUC score compared to the state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-10-09T01:23:08Z)
• Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning [76.98542249776257]
  Large-scale language models often face the challenge of "hallucination" We introduce an uncertainty-aware in-context learning framework to empower the model to enhance or reject its output in response to uncertainty.
  arXiv  Detail & Related papers  (2023-10-07T12:06:53Z)
• CONVIQT: Contrastive Video Quality Estimator [63.749184706461826]
  Perceptual video quality assessment (VQA) is an integral component of many streaming and video sharing platforms. Here we consider the problem of learning perceptually relevant video quality representations in a self-supervised manner. Our results indicate that compelling representations with perceptual bearing can be obtained using self-supervised learning.
  arXiv  Detail & Related papers  (2022-06-29T15:22:01Z)
• MDN-VO: Estimating Visual Odometry with Confidence [34.8860186009308]
  Visual Odometry (VO) is used in many applications including robotics and autonomous systems. We propose a deep learning-based VO model to estimate 6-DoF poses, as well as a confidence model for these estimates. Our experiments show that the proposed model exceeds state-of-the-art performance in addition to detecting failure cases.
  arXiv  Detail & Related papers  (2021-12-23T19:26:04Z)
• A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction [45.6432265855424]
  We introduce Neural Uncertainty Quantifier (NUQ) - a principled quantification of the model's predictive uncertainty. Our proposed framework trains more effectively compared to the state-of-theart models.
  arXiv  Detail & Related papers  (2021-10-06T00:25:22Z)
• FitVid: Overfitting in Pixel-Level Video Prediction [117.59339756506142]
  We introduce a new architecture, named FitVid, which is capable of severe overfitting on the common benchmarks. FitVid outperforms the current state-of-the-art models across four different video prediction benchmarks on four different metrics.
  arXiv  Detail & Related papers  (2021-06-24T17:20:21Z)

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.