arXiv AI

Better World Models Can Lead to Better Post-Training Performance

arXiv AI
Sep 10

WorldAgen: Unified State-Action Prediction with Test-Time World Model Training

WorldAgen is a unified framework that jointly learns world modeling and action prediction using a shared Transformer backbone with two specialized heads. It introduces a Mixed Unidirectional Attention Mask to separate the world model and agent model, and enables Test-Time Training (TTT) by sampling exploratory actions and updating the world model with real state transitions. Experiments on CALVIN and LIBERO show that WorldAgen matches or surpasses state‑of‑the‑art methods, especially when TTT is applied to a few samples.

By Chi Wan, Kangrui Wang, Yuan Si, Pingyue Zhang, Manling Li
arXiv AI
Sep 3

AGI Maze Prediction Datasets: A Compact Benchmark for Learning World Dynamics with Transformers

The paper introduces the AGI Maze Prediction Datasets and Benchmark, a lightweight, procedurally generated grid‑world testbed for evaluating predictive models, particularly Transformers, on tasks such as per‑step transition prediction, fixed‑horizon state prediction, and sequential textual‑observation prediction. It compares byte‑level Transformer baselines with two memory‑augmented architectures, showing that a pseudo‑video spatial‑memory Transformer achieves perfect validation accuracy on selected tasks and improves sequential text‑trace prediction, while a generic auxiliary latent‑memory Transformer does not consistently help. The study highlights that structured, task‑aligned working memory can be more effective than merely increasing latent capacity, and positions the benchmark as a compact setting for testing architectures that couple textual interfaces to learned structured state.

By Alexey Potapov
Hugging Face Trending Papers
Sep 2

AGI Maze Prediction Datasets: A Compact Benchmark for Learning World Dynamics with Transformers

The paper introduces the AGI Maze Prediction Datasets and Benchmark, a lightweight testbed for evaluating how Transformers and other models learn world dynamics. The benchmark, built from procedurally generated grid worlds, includes per‑step transition prediction, fixed‑horizon state prediction, and sequential textual‑observation prediction, with source‑maze‑disjoint training and validation splits to test transferable action‑conditioned dynamics. Experiments show that a pseudo‑video spatial‑memory Transformer, which initializes and updates a two‑dimensional latent workspace from the input map and action history, achieves perfect validation accuracy on selected tasks and improves sequential text‑trace prediction, outperforming byte‑level and unstructured‑memory baselines and suggesting that structured, task‑aligned working memory is more effective than additional latent capacity alone.

arXiv AI
Sep 4

Toward Physically Grounded JEPA World Models for Goal-Conditioned Robotic Planning

The paper presents an end‑to‑end JEPA world model that enhances latent prediction with inverse dynamics and state alignment to improve goal‑conditioned robotic planning. By preventing latent collapse and grounding representations in physical configuration, the model achieves top success rates on tasks such as TwoRoom, PushT, and OGBench‑Cube, outperforming the baseline LeWorldModel. Ablation studies confirm that state alignment consistently boosts planning success over inverse dynamics alone across all four benchmark tasks.

By Muyuan Liu (GENISOM AI, Beijing, China), Yue Huang (GENISOM AI, Beijing, China), Zheng Liang (GENISOM AI, Beijing, China), Xiang Gao (GENISOM AI, Beijing, China)
arXiv Machine Learning
Aug 27

JEPA-x: Cross-Predictive Physics Grounding for Forecastable Latent Dynamics

JEPA-x is a cross‑predictive physics grounding method that aligns visual latent dynamics with privileged physical trajectories. By treating visual observations and physical states as two views of the same action‑conditioned trajectory and sharing a predictor, it forces the model to learn a common transition rule for both modalities. The physical branch is only used during training, so deployment incurs no extra cost, and the approach significantly reduces rollout drift and boosts control success across a multi‑task suite.

By Kehan Wen, Ziming Li, Siyuan Luo, Fan Shi
arXiv AI
Jul 7

HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models

arXiv:2607. 04265v1 Announce Type: cross Abstract: World-action (WA) models can generate long-horizon action chunks for general-purpose robotic manipulation, but they remain vulnerable to calibration, perception, and contact-dynamics errors in real-world precision tasks, often failing in the final few millimeters of alignment or insertion.

By Angen Ye, Weijie Ke, Xiaofeng Wang, Xinze Chen, Chaojun Ni, Guosheng Zhao, Boyuan Wang, Zheng Zhu, Junjie Xie, Dapeng Zhang