World Models That Know When They Don't Know: Controllable Video Generation with Calibrated Uncertainty

• URL: http://arxiv.org/abs/2512.05927v1
• Date: Fri, 05 Dec 2025 18:06:18 GMT
• Title: World Models That Know When They Don't Know: Controllable Video Generation with Calibrated Uncertainty
• Authors: Zhiting Mei, Tenny Yin, Micah Baker, Ola Shorinwa, Anirudha Majumdar,
• Abstract summary: 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.
• Score: 9.69325079034745
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in generative video models have led to significant breakthroughs in high-fidelity video synthesis, specifically in controllable video generation where the generated video is conditioned on text and action inputs, e.g., in instruction-guided video editing and world modeling in robotics. Despite these exceptional capabilities, controllable video models often hallucinate - generating future video frames that are misaligned with physical reality - which raises serious concerns in many tasks such as robot policy evaluation and planning. However, state-of-the-art video models lack the ability to assess and express their confidence, impeding hallucination mitigation. To rigorously address this challenge, we propose C3, an uncertainty quantification (UQ) method for training continuous-scale calibrated controllable video models for dense confidence estimation at the subpatch level, precisely localizing the uncertainty in each generated video frame. Our UQ method introduces three core innovations to empower video models to estimate their uncertainty. First, our method develops a novel framework that trains video models for correctness and calibration via strictly proper scoring rules. Second, we estimate the video model's uncertainty in latent space, avoiding training instability and prohibitive training costs associated with pixel-space approaches. Third, we map the dense latent-space uncertainty to interpretable pixel-level uncertainty in the RGB space for intuitive visualization, providing high-resolution uncertainty heatmaps that identify untrustworthy regions. Through extensive experiments on large-scale robot learning datasets (Bridge and DROID) and real-world evaluations, we demonstrate that our method not only provides calibrated uncertainty estimates within the training distribution, but also enables effective out-of-distribution detection.

Related papers

• VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning [42.22791607763693]
  VideoVeritas is a framework for fine-grained perception and fact-based reasoning.<n>Joint Perception Preference and Perception Pretext Reinforcement Learning is used.
  arXiv  Detail & Related papers  (2026-02-09T16:00:01Z)
• VDOT: Efficient Unified Video Creation via Optimal Transport Distillation [70.02065520468726]
  We propose an efficient unified video creation model, named VDOT.<n>We employ a novel computational optimal transport (OT) technique to optimize the discrepancy between the real and fake score distributions.<n>To support training unified video creation models, we propose a fully automated pipeline for video data annotation and filtering.
  arXiv  Detail & Related papers  (2025-12-07T11:31:00Z)
• UniFField: A Generalizable Unified Neural Feature Field for Visual, Semantic, and Spatial Uncertainties in Any Scene [11.224584333257338]
  We present UniFField, a unified uncertainty-aware neural feature field that combines visual, semantic, and geometric features in a single generalizable representation.<n>We evaluate our uncertainty estimations to accurately describe the model prediction errors in scene reconstruction and semantic feature prediction.
  arXiv  Detail & Related papers  (2025-10-08T08:30:26Z)
• How Confident are Video Models? Empowering Video Models to Express their Uncertainty [11.251320289181338]
  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.
  arXiv  Detail & Related papers  (2025-10-02T21:20:41Z)
• BrokenVideos: A Benchmark Dataset for Fine-Grained Artifact Localization in AI-Generated Videos [63.03271511550633]
  BrokenVideos is a benchmark dataset of 3,254 AI-generated videos with meticulously annotated, pixel-level masks highlighting regions of visual corruption.<n>Our experiments show that training state of the art artifact detection models and multi modal large language models (MLLMs) on BrokenVideos significantly improves their ability to localize corrupted regions.
  arXiv  Detail & Related papers  (2025-06-25T03:30:04Z)
• BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation [77.55074597806035]
  GenBuster-200K is a large-scale, high-quality AI-generated video dataset featuring 200K high-resolution video clips.<n>BusterX is a novel AI-generated video detection and explanation framework leveraging multimodal large language model (MLLM) and reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-19T02:06:43Z)
• T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models [88.63040835652902]
  Text to video models are vulnerable to jailbreak attacks, where specially crafted prompts bypass safety mechanisms and lead to the generation of harmful or unsafe content.<n>We propose T2VShield, a comprehensive and model agnostic defense framework designed to protect text to video models from jailbreak threats.<n>Our method systematically analyzes the input, model, and output stages to identify the limitations of existing defenses.
  arXiv  Detail & Related papers  (2025-04-22T01:18:42Z)
• Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding [55.32861154245772]
  Calib3D is a pioneering effort to benchmark and scrutinize the reliability of 3D scene understanding models.<n>We comprehensively evaluate 28 state-of-the-art models across 10 diverse 3D datasets.<n>We introduce DeptS, a novel depth-aware scaling approach aimed at enhancing 3D model calibration.
  arXiv  Detail & Related papers  (2024-03-25T17:59:59Z)
• 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)

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.