Papers

Filtered to Epps-Pulley objective · clear filter

Browse by term

continual learning 64reinforcement learning 34large language models 17benchmarking 12vision-language models 10generative models 8language models 8video generation 7multimodal models 6natural language processing 6robotics 6world models 6benchmarks 5diffusion models 5on-policy distillation 5policy optimization 5scalability 5self-distillation 5vision-language-action models 5autoregressive models 4computer vision 4diffusion transformers 4LLMs 4multimodal large language models 4verifiable rewards 4attention mechanisms 3embodied intelligence 3image editing 3long-term memory 3multimodal learning 3

Matching papers

QQWorld: Quantile-Quantile Matching for World Model Regularization

23 upvotes · 30 JUL 2026 · Zhoushun Yu, Xiaoyu Hu, Xiangyu Xu

This paper proposes a new regularization technique for world models to improve planning performance by aligning latent samples with quantiles of a Gaussian distribution, which helps control heavy-tailed deviations. Practitioners caring about efficient planning in complex environments may find this approach useful.

world modelslatent distributionsregularizationquantile-quantile matchingEpps-Pulley objective