arXiv AI
Correcting a learned physical invariant improves world-model rollouts
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 24
Frozen Flows Forget: Diagnosing and Restoring Lost Motion in a Latent-flow World Model
The paper investigates why latent‑flow world models that use a frozen self‑supervised latent space lose the ability to manipulate motion. It shows that the pretrained flow does not move the manipulated object and that training with latent‑only losses only produces stillness or teleport‑like motion. The authors introduce Decode‑Augmented Rollout Training (DART), which keeps the representation frozen but retrains the flow using decode‑path supervision, restoring temporal motion structure and improving prediction quality, even closing much of the gap to an oracle‑informed reference. The study also notes that pixel error alone can favor frozen predictions.
arXiv Machine Learning
Jul 10
Unlocking Temporal Generalization in Hamiltonian Video Dynamics Models
arXiv:2607. 07763v1 Announce Type: new Abstract: World models are typically trained to predict discrete-time physical dynamics with a fixed step size baked into the model weights, preventing prediction at variable temporal resolutions.
arXiv Machine Learning
Sep 17
Changepoint-Aware World Models: Detecting Dynamics Shifts and Recovering by Forgetting Stale Replay in Model-Based RL
Changepoint-Aware World Models (CAWM) is a DreamerV3 agent that detects abrupt dynamics shifts in a robot’s environment using an online CUSUM test on internal prediction error. Upon detection, CAWM selectively forgets stale replay data while preserving the learned representation, enabling rapid recovery from shifts such as doubled gravity or halved actuator gain. Experiments on simulated locomotion show CAWM recovers faster than passive retraining and outperforms a baseline that respawns a fresh dynamics model, achieving significant return gains in the first 30k post‑shift frames.
Hugging Face Trending Papers
Sep 23
Frozen Flows Forget: Diagnosing and Restoring Lost Motion in a Latent-flow World Model
Latent world models that integrate a flow in a frozen self supervised latent space train stably and cheaply, yet silently lose the property manipulation depends on most: motion. The pretrained flow ne...
arXiv Machine Learning
Jul 31
ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow
arXiv:2607. 28362v1 Announce Type: cross Abstract: We present ShadowDancer, a novel approach to any-action, frame-level control of interactive video world models.
arXiv Machine Learning
Sep 18
Conservation Buys Stability and Factoring Buys Counterfactuals in Physical World Models
The paper demonstrates that learned simulators can fail in two distinct ways when conditions change: long‑horizon drift due to accumulated errors and incorrect responses to interventions on physical parameters. By adding a symplectic integrator to preserve conservative dynamics, rollouts remain stable for up to 100× the training horizon, while encoding physical coupling via explicit linear factorization allows the model to generalize to unseen signs of that coupling. The study shows that stability and counterfactual generalization arise from separate structural choices, enabling designers to impose each property independently.