Uploaded February 2023 | Updated September 2026, 2 days ago
Abstract: Deep neural networks have achieved remarkable results in several Computer Vision tasks, but their increasing complexity poses challenges in terms of interpretability. In this talk, I will present my research on explainability in deep learning models, ranging from convolutional neural networks (CNNs) to multi-modal transformers, for tasks ranging from static image analysis to active perception, and demonstrate how it can enhance their human-likeness. I will focus on how interpretability can establish user trust, identify failure modes, provide targeted human feedback, debias models, ground representations, and facilitate compositional reasoning. Lastly, I will discuss future research directions and how they align with the goals of the PRIOR team at AI2. Ultimately, my talk aims to underscore the importance of interpretability in AI and its potential to advance the development of trustworthy, robust, and human-like machine learning models.
Bio: Ramprasaath is a Sr. Machine Learning Scientist at Artera AI. Prior to this, he was a Sr. Research Scientist at Salesforce. He holds a PhD in Computer Science from the Georgia Institute of Technology, where he was
advised by Devi Parikh and Dhruv Batra. His research lies at the intersection of computer vision, explainable AI and multi-modal pretraining. Specifically, his research focuses on building algorithms that provide explanations for decisions emanating from deep networks in order to build user trust, incorporate domain knowledge into AI, and correct for unwanted biases learned by deep AI models. Previously, he has held visiting positions at Brown, Oxford, Virginia Tech, Facebook, Samsung, Tesla and Microsoft. He obtained his Bachelor's degree in Electrical and Electronics Engineering and his Master's degree in Physics from Birla Institute of Technology and Science, Pilani.
Abstract: Deep neural networks have achieved remarkable results in several Computer Vision tasks, but their increasing complexity poses challenges in terms of interpretability. In this talk, I will present my research on explainability in deep learning models, ranging from convolutional neural networks (CNNs) to multi-modal transformers, for tasks ranging from static image analysis to active perception, and demonstrate how it can enhance their human-likeness. I will focus on how interpretability can establish user trust, identify failure modes, provide targeted human feedback, debias models, ground representations, and facilitate compositional reasoning. Lastly, I will discuss future research directions and how they align with the goals of the PRIOR team at AI2. Ultimately, my talk aims to underscore the importance of interpretability in AI and its potential to advance the development of trustworthy, robust, and human-like machine learning models.
Bio: Ramprasaath is a Sr. Machine Learning Scientist at Artera AI. Prior to this, he was a Sr. Research Scientist at Salesforce. He holds a PhD in Computer Science from the Georgia Institute of Technology, where he was
advised by Devi Parikh and Dhruv Batra. His research lies at the intersection of computer vision, explainable AI and multi-modal pretraining. Specifically, his research focuses on building algorithms that provide explanations for decisions emanating from deep networks in order to build user trust, incorporate domain knowledge into AI, and correct for unwanted biases learned by deep AI models. Previously, he has held visiting positions at Brown, Oxford, Virginia Tech, Facebook, Samsung, Tesla and Microsoft. He obtained his Bachelor's degree in Electrical and Electronics Engineering and his Master's degree in Physics from Birla Institute of Technology and Science, Pilani.
