| 2017 data-sort-value="2024-01-01" | 2024 || [https://arxiv.org/abs/17032402.06907 Sim05741 Real-to-Real Transfer world Robot Applications of Robotic Control with Dynamics RandomizationFoundation Models: A Review] || Josh Tobin K Kawaharazuka, T Matsushima et al. || This paper discusses how simulated data can be used to train robotic control policies that transfer well to overview of the real world using dynamics randomization. The concept is to bridge the gap between simulation and practical application of foundation models in real-world datarobotics, which is a key aspect including the integration of your interestspecific components within existing robot systems.

| 2017 data-sort-value="2024-01-02" | 2024 || [https://arxiv.org/abs/16122405.07828 Learning from Simulated 03520 Is SORA a World Simulator? A Comprehensive Survey on General World Models and Unsupervised Images through Adversarial TrainingBeyond] || Ashish Shrivastava Z Zhu, X Wang, W Zhao, C Min, N Deng, M Dou et al. || This paper presents SimGANsurveys the applications of world models in various fields, which refines simulated images to make them more realistic using adversarial training. This technique can be used to enhance including robotics, and discusses the quality potential of synthetic data for training robotics modelsthe SORA framework as a world simulator.

| 2018 data-sort-value="2024-01-03" | 2024 || [https://arxiv.org/abshtml/18032401.10122 World 04334v1 Large Language Modelsfor Robotics: Opportunities, Challenges, and Perspectives] || David Ha and Jürgen Schmidhuber J Wang, Z Wu, Y Li, H Jiang, P Shu, E Shi, H Hu et al. || This paper introduces a concept where an agent builds a compact perspectives of using large language models in robotics, focusing on model of the world transparency, robustness, safety, and uses it to plan and dream, improving its performance in the real environment. This aligns well with your interest in universal simulators-world applicability.

| 2020 data-sort-value="2024-01-04" | 2024 || [https://arxiv.org/abs/20032403.08934 NeRF09631 3D-VLA: Representing Scenes as Neural Radiance Fields for View SynthesisA 3D Vision-Language-Action Generative World Model] || Ben Mildenhall H Zhen, X Qiu, P Chen, J Yang, X Yan, Y Du et al. || NeRF (Neural Radiance Fields) generates highPresents 3D-fidelity views of complex 3D scenes VLA, a generative world model that combines vision, language, and action to guide robot control and can be instrumental in creating synthetic data for robotics. It’s relevant for generating diverse visual environments for training robotsachieve goal objectives.

| 2021 data-sort-value="2024-01-05" | 2024 || [https://arxiv.org/abs/21032402.11624 Diverse and Admissible Trajectory Forecasting through Multimodal Context Understanding02385 A Survey on Robotics with Foundation Models: Toward Embodied AI] || Krishna D. Kamath et al. Z Xu, K Wu, J Wen, J Li, N Liu, Z Che, J Tang || This work focuses on predicting diverse future trajectoriesintegration of foundation models in robotics, which is crucial for creating realistic addressing safety and interpretation challenges in real-world scenarios , particularly in robotics simulationsdensely populated environments.

| 2021 data-sort-value="2024-01-06" | 2024 || [https://arxiv.org/abs/19122402.06680 Augmenting Reinforcement 06665 The Essential Role of Causality in Foundation World Models for Embodied AI] || T Gupta, W Gong, C Ma, N Pawlowski, A Hilmkil et al. || importance of causality in foundation world models for embodied AI, predicting that these models will simplify the introduction of new robots into everyday life.|-| data-sort-value="2024-01-07" | 2024 || [https://arxiv.org/abs/2306.06561 Learning World Models with Human VideosIdentifiable Factorization] || Alex X. Lee Y Liu, B Huang, Z Zhu, H Tian et al. || This paper explores a world model with identifiable blocks, ensuring the use removal of human demonstration videos to improve redundancies.|-| data-sort-value="2024-01-08" | 2024 || [https://arxiv.org/abs/2311.09064 Imagine the performance Unseen World: A Benchmark for Systematic Generalization in Visual World Models] || Y Kim, G Singh, J Park et al. || systematic generalization in vision models and world models.|-| data-sort-value="2020-01-01" | 2020 || [https://arxiv.org/abs/2003.08934 NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis] || Ben Mildenhall et al. || high-fidelity views of reinforcement learning agentscomplex 3D scenes, which is highly instrumental in creating synthetic data for robotics, and relevant for augmenting datasets generating diverse visual environments for training robots.|-| data-sort-value="2018-01-01" | 2018 || [https://arxiv.org/abs/1803.10122 World Models] || David Ha and Jürgen Schmidhuber || agent builds a compact model of the world and uses it to plan and dream, improving its performance in real environments. This aligns well with the interest in universal simulators.|-| data-sort-value="2017-01-01" | 2017 || [https://arxiv.org/abs/1612.07828 Learning from Simulated and Unsupervised Images through Adversarial Training] || Ashish Shrivastava et al. || technique that refines simulated images to make them more realistic using adversarial training, enhancing the quality of synthetic data for training roboticsmodels.