Joy, Tom
- What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
2024/07/14 by Jain, Samyak, Lubana, Ekdeep Singh, Oksuz, Kemal +4 · 10 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Sample-dependent Adaptive Temperature Scaling for Improved Calibration
2022/07/13 by Tom Joy, Joy, Tom, Francesco Pinto +7 · 2 citations
Computer Science · Materials Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning and Data Classification #Machine Learning in Materials Science
- Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration
2023/07/03 by Oksuz, Kemal, Joy, Tom, Dokania, Puneet K. · 3 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
- Capturing Label Characteristics in VAEs
2020/06/17 by Tom Joy, Joy, Tom, Sebastian M. Schmon +6 · 2 citations
Computer Science · #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Human Pose and Action Recognition #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Healthcare
- MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection
2023/09/26 by Kemal Öksüz, Oksuz, Kemal, Selim Kuzucu +5 · 2 citations
Medicine · Computer Science · #COVID-19 diagnosis using AI #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications
- Learning Multimodal VAEs through Mutual Supervision
2021/06/23 by Joy, Tom, Shi, Yuge, Torr, Philip H. S. +3 · 1 citation
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)