CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models

arXiv:2605.23699 · cs.CV · Submitted 2026-05-22 · Read on arXiv

cs.CV

Submitted: 2026-05-22

Updated: 2026-10-10

Project page: https://genintel.github.io/CRONOS

Terminology

• Consistency — 3× in this paper · explained in 3 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• World Simulation with Video Foundation Models for Physical AI
• Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
• CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractions
• Qwen3-VL Technical Report
• VideoPhy: Evaluating Physical Commonsense for Video Generation
• VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation
• Physion: Evaluating Physical Prediction from Vision in Humans and Machines
• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
• IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments
• SAM 3D: 3Dfy Anything in Images
• A Physical Coherence Benchmark for Evaluating Video Generation Models via Optical Flow-guided Frame Prediction
• TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation
• "PhyWorldBench": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models
• World Models
• Imagen Video: High Definition Video Generation with Diffusion Models
• Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench
• VBench: Comprehensive Benchmark Suite for Video Generative Models
• How Far is Video Generation from World Model: A Physical Law Perspective
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• WorldModelBench: Judging Video Generation Models As World Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models