arXiv Machine Learning
Training Controllable World Models via Action Influence Maximization
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computer Vision
Sep 14
PAVXploreRL: Physical-Action-Visual World Model Reinforcement Learning with Action Exploration
PAVXploreRL introduces a reinforcement learning framework that builds on a pretrained latent world model to explicitly optimize Physical Plausibility, Action Adherence, and Visual Fidelity (PAV) objectives. By combining in‑distribution expert trajectories with noise‑driven out‑of‑distribution action exploration, the method avoids reliance on paired video supervision and improves generalization. Experiments demonstrate a 5.6% average performance gain over pretrained baselines and more reliable policy evaluation with reduced overestimation bias.
Hugging Face Trending Papers
Jul 27
DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning
Generalizable robot manipulation requires policies that can anticipate how visual scenes evolve while executing language instructions. While recent Vision-Language-Action models benefit from large-scale pretraining, their predominantly static pretraining objectives provide limited supervision for physical dynamics and temporal causality, leaving control-relevant knowledge to be learned from downstream robot demonstrations.
arXiv Machine Learning
Jun 10
GHOST: Hierarchical Sub-Goal Policies for Generalizing Robot Manipulation
arXiv:2606. 10025v1 Announce Type: cross Abstract: We present GHOST, a framework for learning visuomotor manipulation policies that generalize beyond the training distribution.
arXiv Computer Vision
Oct 8
Video Prediction Policy 2: Predict Better, Act Better
Video Prediction Policy 2 (VPP2) is a new world action model that improves zero‑shot generalization for both video prediction and action generation. It achieves this by pretraining a large, diverse manipulation video dataset with event‑level supervision, then distilling the model into a single‑step visual planner and adding a mixture‑of‑transformers action module. Experiments show VPP2 outperforms leading baselines on open‑ended video prediction, real‑world zero‑shot manipulation, and several challenging benchmarks.
arXiv AI
Sep 30
Direct Experience World-Model Optimization: Learning the World Beyond Action Imitation
arXiv:2609.37398v1 Announce Type: new Abstract: World-Action Models (WAMs) couple action generation with predictions of how physical interactions unfold. However, current post-deployment learning par...
arXiv Computer Vision
Aug 28
SimWAM: A Simple World Action Model for End-to-End Autonomous Driving
SimWAM is a lightweight World-Action Model that uses future‑video prediction only during training to supervise an action expert, enabling end‑to‑end autonomous driving without costly test‑time future imagination. The architecture co‑trains a pretrained video expert and a lightweight action expert via joint flow matching, while an isolated attention mask keeps action prediction independent of future frames. This design allows the video backbone to be swapped and the action expert scaled independently, achieving 91.5 PDMS on NAVSIM, outperforming state‑of‑the‑art WAM planners with lower latency and zero‑shot transfer to nuScenes.