Human-Level Accuracy, Non-Human Strategies: Revealing Model-Human Divergence in Video Physical Reasoning
cs.CV, stat.AP
Submitted: 2026-09-19
Updated: 2026-09-19
Code: https://github.com/fanhong-li/model-human-divergence
Terminology
Sources
- Understanding intermediate layers using linear classifier probes
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Revisiting Feature Prediction for Learning Visual Representations from Video
- Intuitive physics understanding emerges from self-supervised pretraining on natural videos
- Interpreting Physics in Video World Models
- Building Machines That Learn and Think Like People
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