Backend
The Flip Test: Video World Models Fail to Learn the World State
arXiv cs.RO0 views
arXiv:2611.19822v1 Announce Type: cross Abstract: Video world models promise to predict the future of a scene from its present. Do current models keep this promise? We probe this question counterfactually. When a small change to the present flips the future, such as a box resting a few millimeters before or past a table edge, a model that tracks the state of the world must flip its prediction too. We build FlipTest, a three-level hierarchy of increasingly strict tests over 1,680 initial frames from 10 simulated and 15 real-world tasks. At the base, visual minimal pairs, two nearly identical frames whose true futures differ, test whether predictions change across the boundary; matched controls go further and test whether they change only where the future does; and dense sweeps, the strictest level, locate exactly where they change. All 11 video world models we evaluate fall short. The best averages 18.3% pair accuracy over real and simulated scenes, below the 25% of random guessing. Models flip as often on steps that leave the future unchanged as on steps that change it, and their response stays flat across the sweeps. On the same frames, a vision-language model is selective and traces a near S-shaped curve near the boundary, and a coding agent that measures the image comes close to the true boundary. This implies that the deciding information is in the frame, and video models just miss it. We therefore urge the community to rethink world modeling as pure video prediction. Next-frame prediction must do more than draw plausible pixels; it must also identify the causal states that control future dynamics.
Source:https://arxiv.org/abs/2611.19822PreviousFree AI Tools for Sports, Health & Leisure Businesses: Gyms, Yoga Studios, Pilates, Trainers, Clubs and Swim Schools on No BudgetNextReactBench-AD: Do Driving VLAs and World-Action Models React to Imminent Hazards in Their Path?
Related posts
I checked 149 Philippine city websites for their land use plan. I could confirm 18.
0dev.to
Is the chain moving? A block-age check before you send, in JavaScript
0dev.to
# 5 Security Mistakes Developers Make When Using AI Coding Assistants
0dev.to
Building an SMS feature for US businesses? 22 states have their own texting law. Here are the sending hours.
0dev.to
Feeding GPUs in Another Cloud Without Moving the Dataset Twice: Data Gravity for Cross-Cloud Training
0dev.to
Expose a Local MCP Server Safely With Access Tokens
0dev.to