Real World
Research on "real-world" applications focuses on bridging the gap between simulated and real-world environments, particularly for complex tasks like robotics, autonomous driving, and natural language processing. Current efforts utilize various model architectures, including large language models (LLMs), diffusion models, reinforcement learning (RL), and graph neural networks, to improve robustness, generalization, and efficiency in diverse real-world scenarios. This research is crucial for advancing AI capabilities beyond controlled settings and enabling practical applications in areas such as healthcare, manufacturing, and transportation, while also addressing challenges like data scarcity, safety, and bias.
Papers
Development and Adaptation of Robotic Vision in the Real-World: the Challenge of Door Detection
Michele Antonazzi, Matteo Luperto, N. Alberto Borghese, Nicola Basilico
Reimagining Reality: A Comprehensive Survey of Video Inpainting Techniques
Shreyank N Gowda, Yash Thakre, Shashank Narayana Gowda, Xiaobo Jin
Learning Representations for Clustering via Partial Information Discrimination and Cross-Level Interaction
Hai-Xin Zhang, Dong Huang, Hua-Bao Ling, Guang-Yu Zhang, Wei-jun Sun, Zi-hao Wen
Growing from Exploration: A self-exploring framework for robots based on foundation models
Shoujie Li, Ran Yu, Tong Wu, JunWen Zhong, Xiao-Ping Zhang, Wenbo Ding
Learning 3D Particle-based Simulators from RGB-D Videos
William F. Whitney, Tatiana Lopez-Guevara, Tobias Pfaff, Yulia Rubanova, Thomas Kipf, Kimberly Stachenfeld, Kelsey R. Allen
Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors
Tongkun Guan, Wei Shen, Xue Yang, Xuehui Wang, Xiaokang Yang
Control of a pendulum system: From simulation to reality
Iyer Venkataraman Natarajan
Reality's Canvas, Language's Brush: Crafting 3D Avatars from Monocular Video
Yuchen Rao, Eduardo Perez Pellitero, Benjamin Busam, Yiren Zhou, Jifei Song