End to End
"End-to-end" systems aim to streamline complex processes by integrating multiple stages into a single, unified model, eliminating the need for intermediate steps and potentially improving efficiency and performance. Current research focuses on applying this approach across diverse fields, utilizing architectures like transformers, reinforcement learning, and spiking neural networks to tackle challenges in autonomous driving, robotics, speech processing, and natural language processing. This approach offers significant potential for improving the accuracy, speed, and robustness of various applications, while also simplifying development and deployment.
Papers
Benchmarking Jetson Edge Devices with an End-to-end Video-based Anomaly Detection System
Hoang Viet Pham, Thinh Gia Tran, Chuong Dinh Le, An Dinh Le, Hien Bich Vo
Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
Xuefei Ning, Zinan Lin, Zixuan Zhou, Zifu Wang, Huazhong Yang, Yu Wang
Personalization for BERT-based Discriminative Speech Recognition Rescoring
Jari Kolehmainen, Yile Gu, Aditya Gourav, Prashanth Gurunath Shivakumar, Ankur Gandhe, Ariya Rastrow, Ivan Bulyko
Automated Deception Detection from Videos: Using End-to-End Learning Based High-Level Features and Classification Approaches
Laslo Dinges, Marc-André Fiedler, Ayoub Al-Hamadi, Thorsten Hempel, Ahmed Abdelrahman, Joachim Weimann, Dmitri Bershadskyy