arXiv Machine Learning
Jun 16
How Should World Models Be Evaluated? A Decision-Making-Centric Position
arXiv:2606. 15032v1 Announce Type: new Abstract: World models have rapidly become one of the central abstractions in modern AI.
Learning Counterfactual World Models for Embodied Reasoning under Partial Observability
Related stories
arXiv Computer Vision
Aug 25
ReWorld: Representation Learning for World Action Models
arXiv:2606.27504v2 Announce Type: replace Abstract: World Action Models (WAMs) unify future environment prediction with action generation for autonomous driving, yet existing approaches optimize only...
arXiv AI
Jul 7
Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embodied Reasoning
arXiv:2607. 04681v1 Announce Type: cross Abstract: Embodied Chain-of-Thought has emerged as a promising mechanism to enhance robot decision-making and interpretability in black-box Vision-Language Action (VLA) models.
arXiv AI
Jul 14
Towards Predictive, Aligned, and Scalable Robot Learning
arXiv:2607. 11270v1 Announce Type: cross Abstract: Learning, at its core, extends beyond memorization to the ability to reason and solve novel problems by navigating a space of possibilities.
arXiv Machine Learning
Jun 30
How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position
arXiv:2606. 15032v2 Announce Type: replace Abstract: World models have become a central abstraction in modern AI.
arXiv Computation and Language
Sep 1
World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning
The paper introduces a framework that combines world models, which generate concrete visual rollouts of possible futures, with multimodal large language models (MLLMs) that perform abstract reasoning. It proposes a controlled concrete reasoning approach and a new training method called Privileged‑Future On‑Policy Self‑Distillation (PF‑OPSD), which uses ground‑truth future videos as privileged teacher context during training while the student model never sees true futures at test time. Experiments on two human‑verified benchmarks, VRQABench and OpenWorldQA, show that PF‑OPSD improves performance by about 10–11% over baselines and enhances robustness to noisy or conflicting rollouts.
arXiv AI
Sep 10
PAN: A World Model for General, Actionable, and Long-Horizon World Simulation
arXiv:2511.09057v4 Announce Type: replace-cross Abstract: A world model is a cognitive simulator of the real-world environment allowing biological agents to reason about how the world evolves, whethe...
arXiv Machine Learning
Aug 21
Scaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning
arXiv:2608. 19669v1 Announce Type: cross Abstract: Latent reasoning has advanced multimodal reasoning through a two-stage training paradigm: (1) a helper image is encoded into latent tokens to teach visual chain-of-thought during a supervised fine-tuning (SFT) stage, and (2) these latent tokens are further refined with reward feedback during a reinforcement learning (RL) stage.
arXiv AI
2d ago
World Models for Embodied Intelligence: From Plausible to Controllable to Actionable
arXiv:2609.16697v1 Announce Type: cross Abstract: World models connect perception and decision-making in embodied intelligence by maintaining hidden state, anticipating consequences, comparing interv...
arXiv AI
Jun 2
TERRA: Task-Embedded Reasoning and Representation Architecture for Cross-Domain Applications
arXiv:2606. 01520v1 Announce Type: new Abstract: A single action-conditioned latent predictive architecture can in principle be trained on the structured state of a driving scene, a robot workspace, or a financial order book.
arXiv AI
Aug 28
Predicting Consequences and Reinforcing Navigation Policies with Latent World Models
The paper introduces a Latent World Model (LWM) for robot navigation that predicts action‑conditioned latent feature compatibility instead of reconstructing future observations. By exploiting the correlation between spatial proximity and latent feature similarity, the model evaluates action consequences directly in latent space and supports counterfactual training using sampled action sequences. The learned world model can supervise policy learning from unlabeled video and further improve policies via reinforcement learning entirely within the model, eliminating the need for action annotations and additional environment interaction.
arXiv AI
Sep 4
Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models
The paper introduces Imagine-then-Plan (ITP), a framework that lets agents learn by interacting with a learned world model to generate multi-step imagined trajectories. ITP features an adaptive lookahead mechanism that balances ultimate goals with task progress, producing richer signals about future outcomes. Experiments on various benchmarks show that ITP outperforms existing baselines, and analyses suggest the adaptive lookahead improves reasoning for complex tasks.