arXiv AI
Better World Models Can Lead to Better Post-Training Performance
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
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.
arXiv AI
Oct 21
VPFlow: Value-Predictive Planning with Imperfect World Models for Offline Goal Reaching
arXiv:2610.27280v1 Announce Type: cross Abstract: Offline goal-conditioned reinforcement learning enables skill acquisition by reaching any goal from any state without dense rewards. Model-based meth...
arXiv Computer Vision
Sep 30
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling
arXiv:2609.34981v2 Announce Type: replace Abstract: World action models (WAMs) predict the future alongside actions during training. Due to the heavy computation cost of video denoising, whether the...
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.
arXiv Computer Vision
3d ago
Time-to-Goal: Learned Temporal Metrics for Long-Horizon Planning with JEPA World Models
arXiv:2611.05847v1 Announce Type: cross Abstract: Joint-Embedding Predictive Architectures (JEPAs) support planning by comparing predicted latent states with an encoded goal. For this comparison to g...
Hugging Face Trending Papers
Oct 19
VPFlow: Value-Predictive Planning with Imperfect World Models for Offline Goal Reaching
Offline goal-conditioned reinforcement learning enables skill acquisition by reaching any goal from any state without dense rewards. Model-based methods allow for planning by scaling test-time compute...