| 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 Learning with Human Videos06665 The Essential Role of Causality in Foundation World Models for Embodied AI] || Alex X. Lee T Gupta, W Gong, C Ma, N Pawlowski, A Hilmkil et al. || This paper explores the use importance of human demonstration videos to improve causality in foundation world models for embodied AI, predicting that these models will simplify the performance introduction of reinforcement learning agents, which is highly relevant for augmenting datasets in roboticsnew robots into everyday life.

| data-sort-value="2024-01-07" | 2024 || [https://arxiv.org/pdfabs/Real-world_robot_applications_of_foundation_models2306.pdf Real-world Robot Applications of Foundation 06561 Learning World Models: A Reviewwith Identifiable Factorization] || K KawaharazukaY Liu, B Huang, Z Zhu, T Matsushima H Tian et al. || This paper provides an overview of the practical application of foundation models in real-a world roboticsmodel with identifiable blocks, including ensuring the integration removal of specific components within existing robot systemsredundancies.

| data-sort-value="2024-01-08" | 2024 || [https://arxiv.org/pdfabs/Is_sora_a_world_simulator2311.pdf Is SORA a 09064 Imagine the Unseen World Simulator? : A Comprehensive Survey on General Benchmark for Systematic Generalization in Visual World Models and Beyond] || Z Zhu, X Wang, W Zhao, C MinY Kim, N DengG Singh, M Dou J Park et al. || This paper surveys the applications of world systematic generalization in vision models in various fields, including robotics, and discusses the potential of the SORA framework as a world simulatormodels.

| 2024 data-sort-value="2020-01-01" | 2020 || [https://arxiv.org/abs/24012003.00001 Large Language Models 08934 NeRF: Representing Scenes as Neural Radiance Fields for Robotics: Opportunities, Challenges, and PerspectivesView Synthesis] || J Wang, Z Wu, Y Li, H Jiang, P Shu, E Shi, H Hu Ben Mildenhall et al. || This paper discusses the opportunitieshigh-fidelity views of complex 3D scenes, challenges, and perspectives of using large language models instrumental in creating synthetic data for robotics, focusing on model transparency, robustness, safety, and real-world applicabilityrelevant for generating diverse visual environments for training robots.

| 2024 data-sort-value="2018-01-01" | 2018 || [https://arxiv.org/abs/24011803.00002 3D-VLA: A 3D Vision-Language-Action Generative 10122 World ModelModels] || H Zhen, X Qiu, P Chen, J Yang, X Yan, Y Du et al. David Ha and Jürgen Schmidhuber || This paper presents 3D-VLA, agent builds a generative compact model of the world model that combines vision, language, and action uses it to guide robot control plan and achieve goal objectivesdream, improving its performance in real environments. This aligns well with the interest in universal simulators.

| 2024 || [https://arxiv.org/abs/2401.00003 A Survey on Robotics with Foundation Models: Toward Embodied AI] || Z Xu, K Wu, J Wen, J Li, N Liu, Z Che, J Tang || This survey explores the integration of foundation models in robotics, addressing safety and interpretation challenges in realdata-sort-value="2017-world scenarios, particularly in densely populated environments.|01-01" | 2024 2017 || [https://arxiv.org/abs/24011612.00004 The Essential Role of Causality in Foundation World Models for Embodied AI07828 Learning from Simulated and Unsupervised Images through Adversarial Training] || T Gupta, W Gong, C Ma, N Pawlowski, A Hilmkil Ashish Shrivastava et al. || This paper emphasizes technique that refines simulated images to make them more realistic using adversarial training, enhancing the importance quality of causality in foundation world models synthetic data for embodied AI, predicting that these training robotics models will simplify the introduction of new robots into everyday life.