“Known Unknowns: Out-of-Distribution Property Prediction in Materials and Molecules” – Oral presentation at NeurIPS Workshop on AI for Accelerated Materials Design 2024; also presented at WiML 2024, MRS Fall Meeting 2024, and Molecular ML Conference 2024.
“Few-Shot Task Learning through Inverse Generative Modeling” – NeurIPS 2024; featured in RSS workshops 2024.
“Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-time Policy Adaptation” – ICML 2023; highlighted as MIT News front-page story.
“Learning to Extrapolate: A Transductive Approach” – ICLR 2023; presented at NeurIPS Workshop on Distribution Shifts 2022.
“Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning” – ICML 2022; also presented at RLDM 2022 and ICLR Elements of Reasoning Workshop 2022.
“PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception” – AAAI 2021; received Best Paper Award and Oral Presentation at NeurIPS Shared Visual Representations Workshop 2020.
Co-authored “Human-Like Scene Interpretation by a Guided Counterstream Processing” published in PNAS 2023.
MSc thesis “Cyclical Bottom-Up Top-Down Neural Networks for Relational Reasoning” proposed a system achieving out-of-distribution and combinatorial generalization in visual relationship detection.