paper-with-me

홈 › Papers

Next Embedding Prediction Makes World Models Stronger

2026-03-03 · George Bredis, Nikita Balagansky, Daniil Gavrilov, Ruslan Rakhimov arxiv

Capturing temporal dependencies is critical for model-based reinforcement learning (MBRL) in partially observable, high-dimensional domains. We introduce NE-Dreamer, a decoder-free MBRL agent that leverages a temporal transformer to predict next-step encoder embeddings from latent state sequences, directly optimizing temporal predictive alignment in representation space. This approach enables NE-Dreamer to learn coherent, predictive state representations without reconstruction losses or auxiliary supervision. On the DeepMind Control Suite, NE-Dreamer matches or exceeds the performance of DreamerV3 and leading decoder-free agents. On a challenging subset of DMLab tasks involving memory and spatial reasoning, NE-Dreamer achieves substantial gains. These results establish next-embedding prediction with temporal transformers as an effective, scalable framework for MBRL in complex, partially observable environments.

📄 PDF Abstract BibTeX arXiv:2603.02765

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningSpatial Reasoning

Similar Papers 제목 키워드 기반

Orca: The World is in Your Mind

2026-06-29 · Yihao Wang, Yuheng Ji, Mingyu Cao, Yanqing Shen 외 hf

We introduce Orca, an initial instantiation of a general world foundation model. Orca learns a unified world latent space from multimodal world signals and exposes it through multimodal readout interfaces. Rather than op…

Text Generation

Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners

2026-08-20 · Umberto Cappellazzo, Xubo Liu, Stavros Petridis, Maja Pantic arxiv

Self-supervised learning (SSL) has driven substantial progress in audio representation learning, though existing methods have increasingly relied on elaborate pre-training recipes to reach competitive performance. A mark…

Self-Supervised LearningRepresentation Learning

Next-Embedding Prediction Makes Strong Vision Learners

2025-12-18 · Sihan Xu, Ziqiao Ma, Wenhao Chai, Xuweiyi Chen 외 arxiv

Inspired by the success of generative pretraining in natural language, we ask whether the same principles can yield strong self-supervised visual learners. Instead of training models to output features for downstream use…

Self-Supervised LearningSemantic Segmentation

TransTARec: Time-Adaptive Translating Embedding Model for Next POI Recommendation

2024-04-10 · Yiping Sun

The rapid growth of location acquisition technologies makes Point-of-Interest(POI) recommendation possible due to redundant user check-in records. In this paper, we focus on next POI recommendation in which next POI is b…

Triplet

Cross-Network Social User Embedding with Hybrid Differential Privacy Guarantees

2022-09-04 · Jiaqian Ren, Lei Jiang, Hao Peng, Lingjuan Lyu 외

Integrating multiple online social networks (OSNs) has important implications for many downstream social mining tasks, such as user preference modelling, recommendation, and link prediction. However, it is unfortunately …

AttributeLink PredictionNetwork EmbeddingPrivacy Preserving