QQWorld: Quantile-Quantile Matching for World Model Regularization
Abstract
Latent world models enable efficient planning by predicting future states in a compact representation space, but their performance depends critically on the quality of the learned latent distribution. LeWorldModel (LeWM) regularizes its latents toward an isotropic Gaussian using the Epps-Pulley (EP) objective. We show that the corrective gradients of EP rapidly vanish for isolated tail samples, leaving heavy-tailed deviations insufficiently controlled. To address this limitation, we propose QQWorld, which replaces EP with a quantile-quantile matching objective that directly aligns projected latent samples with rank-matched Gaussian quantiles, thereby maintaining effective corrective gradients in the tails. We further develop cross-batch QQ, which enlarges the effective ranking pool using detached samples from previous batches, and characterize its bias-variance trade-off. Across four control environments, QQWorld effectively improves the average planning success rate of LeWM, while consistently yielding better Gaussian alignment and thinner latent tails.
Community
QQWorld improves latent world models with a quantile-quantile matching objective that aligns projected latent samples with rank-matched Gaussian quantiles, boosting planning success.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Unbiased Open World Regularization for Fair Self-Supervised Learning (2026)
- PIT-SUN: A Deployable Empirical Marginal Transform Framework with Expectation-Consistent Recovery for Regression in Recommender Systems (2026)
- Diachronic Sample Integration: Robust Tail-Risk Estimation with Generative Models (2026)
- Distribution-Aware Robust Bilevel Optimization: Quantile-Guided Huber Updates in Two-Timescale Stochastic Approximation (2026)
- GFlowRL: Scaling Distribution-Matching RL to Large Language Models (2026)
- DLR: Zero-Inference-Cost Latent Residuals for Low-Rank Pre-Training (2026)
- BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper