| 2017 data-sort-value="2024-01-01" | 2024 || [https://arxiv.org/abs/16122402.07828 Learning from Simulated and Unsupervised Images through Adversarial Training05741 Real-world Robot Applications of Foundation Models: A Review] || Ashish Shrivastava K Kawaharazuka, T Matsushima et al. || technique that refines simulated images to make them more realistic using adversarial trainingoverview of the practical application of foundation models in real-world robotics, enhancing including the quality integration of synthetic data for training robotics modelsspecific components within existing robot systems.

| 2018 data-sort-value="2024-01-02" | 2024 || [https://arxiv.org/abs/18032405.10122 03520 Is SORA a World Simulator? A Comprehensive Survey on General World Modelsand Beyond] || David Ha and Jürgen Schmidhuber Z Zhu, X Wang, W Zhao, C Min, N Deng, M Dou et al. || agent builds a compact model surveys the applications of the world models in various fields, including robotics, and uses it to plan and dream, improving its performance in real environments. This aligns well with discusses the potential of the interest in universal simulatorsSORA framework as a world simulator.

| 2020 data-sort-value="2024-01-03" | 2024 || [https://arxiv.org/abs/20032403.08934 NeRF09631 Large Language Models for Robotics: Representing Scenes as Neural Radiance Fields for View SynthesisOpportunities, Challenges, and Perspectives] || Ben Mildenhall J Wang, Z Wu, Y Li, H Jiang, P Shu, E Shi, H Hu et al. || high-fidelity views perspectives of complex 3D scenes, instrumental using large language models in creating synthetic data for robotics, focusing on model transparency, robustness, safety, and relevant for generating diverse visual environments for training robotsreal-world applicability.

| data-sort-value="2024-01-04" | 2024 || [https://arxiv.org/abs/24022403.05741 Real09631 3D-world Robot Applications of Foundation ModelsVLA: A Review3D Vision-Language-Action Generative World Model] || K KawaharazukaH Zhen, X Qiu, P Chen, T Matsushima J Yang, X Yan, Y Du et al. || overview of the practical application of foundation models in realPresents 3D-VLA, a generative world roboticsmodel that combines vision, language, including the integration of specific components within existing and action to guide robot systemscontrol and achieve goal objectives.

| data-sort-value="2024-01-05" | 2024 || [https://arxiv.org/abs/24052402.03520 Is SORA a World Simulator? 02385 A Comprehensive Survey on General World Robotics with Foundation Models and Beyond: Toward Embodied AI] || Z ZhuXu, X WangK Wu, W ZhaoJ Wen, C MinJ Li, N DengLiu, M Dou et al. Z Che, J Tang || surveys the applications integration of world foundation models in various fields, including robotics, addressing safety and discusses the potential of the SORA framework as a interpretation challenges in real-world simulatorscenarios, particularly in densely populated environments.

| data-sort-value="2024-01-06" | 2024 || [https://arxiv.org/abs/24032402.09631 Large Language 06665 The Essential Role of Causality in Foundation World Models for Robotics: Opportunities, Challenges, and PerspectivesEmbodied AI] || J Wang, Z Wu, Y LiT Gupta, H JiangW Gong, P ShuC Ma, E ShiN Pawlowski, H Hu A Hilmkil et al. || perspectives importance of using large language causality in foundation world models in roboticsfor embodied AI, focusing on model transparency, robustness, safety, and real-world applicabilitypredicting that these models will simplify the introduction of new robots into everyday life.

| data-sort-value="2024-01-07" | 2024 || [https://arxiv.org/abs/24032306.09631 3D-VLA: A 3D Vision-Language-Action Generative 06561 Learning World ModelModels with Identifiable Factorization] || H ZhenY Liu, X QiuB Huang, P ChenZ Zhu, J Yang, X Yan, Y Du H Tian et al. || Presents 3D-VLA, a generative world model that combines vision, languagewith identifiable blocks, and action to guide robot control and achieve goal objectivesensuring the removal of redundancies.

| data-sort-value="2024-01-08" | 2024 || [https://arxiv.org/abs/24022311.02385 09064 Imagine the Unseen World: A Survey on Robotics with Foundation Benchmark for Systematic Generalization in Visual World Models: Toward Embodied AI] || Z XuY Kim, K WuG Singh, J Wen, J Li, N Liu, Z Che, J Tang Park et al. || integration of foundation systematic generalization in vision models in robotics, addressing safety and interpretation challenges in real-world scenarios, particularly in densely populated environmentsmodels.

| 2024 data-sort-value="2020-01-01" | 2020 || [https://arxiv.org/abs/24022003.06665 The Essential Role of Causality in Foundation World Models 08934 NeRF: Representing Scenes as Neural Radiance Fields for Embodied AIView Synthesis] || T Gupta, W Gong, C Ma, N Pawlowski, A Hilmkil Ben Mildenhall et al. || importance high-fidelity views of causality complex 3D scenes, instrumental in foundation world models creating synthetic data for embodied AIrobotics, predicting that these models will simplify the introduction of new and relevant for generating diverse visual environments for training robots into everyday life.

| 2024 data-sort-value="2018-01-01" | 2018 || [https://arxiv.org/abs/23061803.06561 Learning 10122 World Models with Identifiable Factorization] || Y Liu, B Huang, Z Zhu, H Tian et al. David Ha and Jürgen Schmidhuber || agent builds a compact model of the world model and uses it to plan and dream, improving its performance in real environments. This aligns well with identifiable blocks, ensuring the removal of redundancies interest in universal simulators.

| 2024 data-sort-value="2017-01-01" | 2017 || [https://arxiv.org/abs/23111612.09064 Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models07828 Learning from Simulated and Unsupervised Images through Adversarial Training] || Y Kim, G Singh, J Park Ashish Shrivastava et al. || systematic generalization in vision models and world technique that refines simulated images to make them more realistic using adversarial training, enhancing the quality of synthetic data for training robotics models.