Sanjay Subramanian, Ben Bogin, Nitish Gupta, Tomer Wolfson, Sameer Singh, Jonathan Berant, and Matt Gardner. “Obtaining Faithful Interpretations from Compositional Neural Networks.” ACL 2020.
Evangelos Chatzipantazis, Stefanos Pertigkiozolou, Kostas Daniilidis, and Edgar Dobriban. Learning Augmentation Distributions using Transformed Risk Minimization, submitted to NeurIPS 2021.
Nikolaos Kolotouros, Georgios Pavlakos, Dinesh Jayaraman, Kostas Daniilidis, Probabilistic Modeling for 3D Human Pose Estimation, ICCV 2021.
Yiannis Kantaros, Taylor Carpenter, Kaustubh Sridhar, Yahan Yang, Insup Lee, and James Weimer. Real-Time Detectors for Digital and Physical Adversarial Inputs to Perception Systems. ICCPS 2021.
Jorge Mendez, Eric Eaton. Lifelong learning of compositional structures, ICLR 2021.
Sangdon Park, Shuo Li, Insup Lee, and Osbert Bastani. PAC Confidence Predictions for Deep Neural Network Classifiers. ICLR 2021.
Radoslav Ivanov, Taylor Carpenter, James Weimer, Rajeev Alur, George Pappas and Insup Lee. Verisig 2.0: Verification of Neural Network Controllers Using Taylor Model Preconditioning. CAV 2021.
Soham Dan, Michael Zhou, and Dan Roth. "Generalization in Instruction Following Systems." NAACL-HLT 2021.
Soham Dan, Xinran Han, and Dan Roth. “Compositional Data and Task Augmentation for Instruction Following.” EMNLP-Findings 2021.
Gupta, Nitish, Sameer Singh, Matt Gardner, and Dan Roth. “Paired Examples as Indirect Supervision in Latent Decision Models.” Submitted.
Soham Dan, Osbert Bastani, and Dan Roth. “Few-Shot Novel Concept Learning for Semantic Parsing.” EMNLP-Findings 2021.
Soham Dan, and Dan Roth. “On the Effects of Transformer Size on In- and Out-of-Domain Calibration.” EMNLP-Findings 2021.
Shuxiao Chen, Koby Crammer, Hangfeng He, Dan Roth, Weijie Su. “Weighted Training for Cross-Task Learning.” arXiv:2105.14095, ICLR 2022.
Hangfeng He, Mingyuan Zhang, Qiang Ning, Dan Roth. “Foreseeing the Benefits of Incidental Supervision.” EMNLP 2021.
Philip Huebner, Elior Sulem , Cynthia Fisher, Dan Roth, "BabyBERTa: Learning More Grammar With Small-Scale Child-Directed Language" CoNLL 2021.
Georgios Georgakis, Bernadette Bucher, Karl Schmeckpeper, Siddharth Singh, Kostas Daniilidis, “Learning to Map for Active Semantic Goal Navigation.” arXiv:2106.15648, ICLR 2022
Georgios Georgakis, Bernadette Bucher, Anton Arapin, Karl Schmeckpeper, Nikolai Matni, Kostas Daniilidis, “Uncertainty-driven Planner for Exploration and Navigation.” ICRA 2022.
Seungwon Lee, Sima Behpour, and Eric Eaton. “Sharing less is more: Lifelong learning in deep networks with selective layer transfer.” ICML 2021.
1 AUG 2021 to 31 JUL 2022
Souradeep Dutta, Kaustubh Sridhar, Osbert Bastani, Edgar Dobriban, James Weimer, Insup Lee, Julia Parish-Morris, "Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templates", CoRL 2022. Submitted.
R. Kaur, S. Jha, A. Roy, S. Park, E. Dobriban, O. Sokolsky, I. Lee. iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection. AAAI 2022.
Ramneet Kaur, Kaustubh Sridhar, Sangdon Park, Susmit Jha, Anirban Roy, Oleg Sokolsky, Insup Lee, "CoDiT: Conformal Out-of-Distribution Detection in Time-Series Data", Workshop on PODS at ICML 2022.
Kaustubh Sridhar, Oleg Sokolsky, Insup Lee, James Weimer, “Improving Neural Network Robustness via Persistency of Excitation”, ACC 2022.
Kaustubh Sridhar, Souradeep Dutta, Ramneet Kaur, James Weimer, Oleg Sokolsky, Insup Lee, "Towards Alternative Techniques for Improving Adversarial Robustness: Analysis of Adversarial Training at a Spectrum of Perturbations", arXiv:2206.06496.
Georgios Georgakis, Karl Schmeckpeper, Karan Wanchoo, Sohan Dan, Eleni Miltsakaki, Dan Roth, Kostas Daniilidis, "Cross-modal Map Learning for Vision and Language Navigation." CVPR 2022.
Yinshuang Xu, Jiahui Lei, Edgar Dobriban, Kostas Daniilidis, "Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces." ICML 2022.
Evangelos Chatzipantazis, Stefanos Pertigkiozoglou, Edgar Dobriban and Kostas Daniilidis, "SE(3)-Equivariant Attention Networks for Shape Reconstruction in Function Space", arXiv:2204.02394 2022.
V. Lin, R. Ivanov, J. Weimer, O. Sokolsky, I. Lee, "T4V: Exploring Neural Network Architectures that Improve the Scalability of Neural Network Verification." Henzinger-60; Thomas Henzinger Festschrift - Conference Celebrating his 60th Birthday, 2023.
Soham Dan and Osbert Bastani and Dan Roth, “Understanding Robust Generalization in Learning Regular Languages”, ICML 2022.
Shuo Li, Xiayan Ji, Edgar Dobriban, Oleg Sokolsky, Insup Lee. PAC-Wrap: Semi-Supervised PAC Anomaly Detection. SIGKDD 2022.
Shuo Li, Sangdon Park, Xiayan Ji, Insup Lee, Osbert Bastani, “Towards PAC Multi-Object Detection and Tracking”, Workshop on DFUQ at ICML 2022.
Xiayan Ji, Insup Lee. PAC Guarantee for Detecting Evolving Anomalies in Medical Cyber-physical Systems. ICDM 2022. Submitted.
Sangdon Park, Edgar Dobriban, Insup Lee, Osbert Bastani, "PAC Prediction Sets Under Covariate Shift", ICLR 2022.
Sangdon Park, Edgar Dobriban, Insup Lee, Osbert Bastani, "PAC Prediction Sets for Meta-Learning", arXiv:2207.02440 and ICML Workshop on DFUQ 2022.
Sooyong Jang, Sangdon Park, Insup Lee, Osbert Bastani. "Sequential Covariate Shift Detection Using Classifier Two-Sample Tests." ICML 2022.
Yahan Yang, Ramneet Kaur, Souradeep Dutta, Insup Lee. Interpretable Detection of Distribution Shifts in Learning Enabled Cyber-Physical Systems. ICCPS 2022.
Souradeep Dutta, Yahan Yang, Elena Bernardis, Edgar Dobriban, Insup Lee. Memory Classifiers: Two-stage Classification for Robustness in Machine Learning. NeurIPS 2022. Submitted
Yahan Yang, Soham Dan, Dan Roth, Insup Lee. In and Out-of Domain Text Adversarial Robustness via Label Smoothing. EMNLP 2022. Submitted.
Meghna Gummadi, David Kent, Jorge Mendez, Eric Eaton.. “SHELS: Exclusive feature sets for novelty detection and continual learning without class boundaries.” CoLLAs 2022.
Marcel Hussing, Jorge Mendez, Meghna Gummadi, Eric Eaton. “CompoSuite: A compositional reinforcement learning benchmark.” CoLLAs 2022.
Jorge Mendez, Harm van Seijen, and Eric Eaton. (2022). “Modular lifelong reinforcement learning via neural composition.” ICLR 2022.