arXiv AI
CAER: Causal Action Effect Reweighting for World Model Training
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Oct 15
Can World and Action Modeling Benefit Each Other under Unified Causal Training?
World and action modeling are closely related, yet their reciprocal benefits under unified causal training remain unclear. We introduce OneWM, a simple framework for unified causal training that treat...
arXiv Machine Learning
Oct 9
CausalDreamer: Learning Predictive World Models with Latent Disentanglement
CausalDreamer enhances generative world models by freezing the original video tokenizer and re-encoding its latent space into a factored representation that separates controllable versus uncontrollable dynamics and reward-relevant versus reward-irrelevant information. The pretrained dynamics model is fine‑tuned to predict this factored representation, enabling more accurate model‑predictive planning. On the MMBench2 benchmark, CausalDreamer improves normalized scores by 14% on clean tasks and 25% on manipulated variants compared to the baseline, while both models perform poorly on entirely new environments.
arXiv Computer Vision
Oct 16
Can World and Action Modeling Benefit Each Other under Unified Causal Training?
The paper introduces OneWM, a unified causal training framework that treats actions as both conditions for world prediction and targets for policy learning within a shared video-action architecture. Experiments on LIBERO, LIBERO-Plus, and RoboCasa365 show that learning forward dynamics conditioned on specified actions improves policy performance and generalization, while action learning enhances multi‑view world‑prediction fidelity. These findings demonstrate reciprocal benefits between world modeling and action generation under unified causal training.
arXiv AI
Sep 17
CSWAM: Better Causal Semantic Representations for Out-of-Distribution Generalization in World Action Models
The paper introduces CSWAM, a Causal Semantic World Action Model that enhances FastWAM by integrating a causal semantic expert based on V-JEPA 2.1. This expert provides temporally grounded, appearance‑agnostic representations of semantic state changes and motion, leveraging sparse observation history and causal attention to improve action‑only inference. Experiments on simulation and real‑robot tasks show that CSWAM significantly boosts out‑of‑distribution generalization, raising success rates from 10.16% to 45.18% on RoboTwin 2.0 and from 27.5% to 70.0% across real‑robot tasks.
arXiv AI
Sep 2
IMPACT: Attention Is the Interaction Map for Scalable Interaction-Aware World Model Training
arXiv:2609.00161v1 Announce Type: new Abstract: World models have made remarkable progress in action-conditioned future prediction for embodied agents, yet still struggle to model physically plausibl...
arXiv Computer Vision
Sep 24
Latent evolving World Action Model
arXiv:2609.27455v1 Announce Type: new Abstract: World Action Models (WAMs) jointly model action generation and environment dynamics and are mostly built on pretrained Video Diffusion Models (VDMs). I...