Publications

  1. Gupta, N., Lin, K., Roth, D., Singh, S., & Gardner, M., "Neural module networks for reasoning over text," Proceedings of the International Conference on Learning Representations (ICLR), 2020.
  2. Subramanian, S., Bogin, B., Gupta, N., Wolfson, T., Singh, S., Berant, J., & Gardner, M., "Obtaining faithful interpretations from compositional neural networks," Proceedings of the Association for Computational Linguistics (ACL), 2020.
  3. Wang, K., Ning, Q., & Roth, D., "Learnability with indirect supervision signals," Advances in Neural Information Processing Systems (NeurIPS), 2020.
  4. Dan, S., Zhou, M., & Roth, D., "Generalization in instruction following systems," Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), 2021.
  5. Ivanov, R., Carpenter, T., Weimer, J., Alur, R., Pappas, G., & Lee, I., "Verisig 2.0: Verification of neural network controllers using Taylor model preconditioning," Proceedings of the International Conference on Computer Aided Verification (CAV), 2021.
  6. Kantaros, Y., Carpenter, T., Sridhar, K., Lee, I., & Weimer, J., "Real-time detectors for adversarial digital and physical inputs to perception systems," Proceedings of the 12th ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS), 2021.
  7. Kolotouros, N., Pavlakos, G., Jayaraman, D., & Daniilidis, K., "Probabilistic modeling for 3D human pose estimation," Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021.
  8. Mendez, J., & Eaton, E., "Lifelong learning of compositional structures," Proceedings of the International Conference on Learning Representations (ICLR), 2021.
  9. Mendez, J., Wang, B., & Eaton, E., "Lifelong policy gradient learning of factored policies for faster training without forgetting," Advances in Neural Information Processing Systems (NeurIPS), 2021.
  10. Park, S., Li, S., Lee, I., & Bastani, O., "PAC confidence predictions for deep neural network classifiers," Proceedings of the International Conference on Learning Representations (ICLR), 2021.
  11. Dan, S., & Roth, D., "On the effects of transformer size on in- and out-of-domain calibration," Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-Findings), 2021.
  12. Ma, Y. J., Jayaraman, D., & Bastani, O., "Conservative offline distributional reinforcement learning," Advances in Neural Information Processing Systems (NeurIPS), 2021.
  13. Jothimurugan, K., Bansal, S., Bastani, O., & Alur, R., "Compositional reinforcement learning from logical specifications," Advances in Neural Information Processing Systems (NeurIPS), 2021.
  14. Yang, Y., Inala, J. P., Bastani, O., Pu, Y., Solar-Lezama, A., & Rinard, M., "Program synthesis guided reinforcement learning for partially observed environments," Advances in Neural Information Processing Systems (NeurIPS), 2021.
  15. Caprio, M., "Refined Pinsker's and reverse Pinsker's inequalities for probability distributions of different dimensions," IEEE Access, 10, 2022.
  16. Chatzipantazis, E., Pertigkiozoglou, S., Dobriban, E., & Daniilidis, K., "SE(3)-equivariant attention networks for shape reconstruction in function space," arXiv preprint arXiv:2204.02394, 2022. (Accepted at International Conference on Learning Representations (ICLR), 2023).
  17. Chen, S., Crammer, K., He, H., Roth, D., & Su, W., "Weighted training for cross-task learning," Proceedings of the International Conference on Learning Representations (ICLR), 2022.
  18. Dan, S., Bastani, O., & Roth, D., "Understanding robust generalization in learning regular languages," Proceedings of the International Conference on Machine Learning (ICML), 2022.
  19. Dutta, S., Sridhar, K., Weimer, J., Lee, I., & Parish-Morris, J., "Exploring with sticky mittens: Reinforcement learning with expert interventions via option templates," Proceedings of the Conference on Robot Learning (CoRL), 2022.
  20. Georgakis, G., Schmeckpeper, K., Wanchoo, K., Dan, S., Miltsakaki, E., Roth, D., & Daniilidis, K., "Cross-modal map learning for vision and language navigation," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  21. Gummadi, M., Kent, D., Mendez, J., & Eaton, E., "SHELS: Exclusive feature sets for novelty detection and continual learning without class boundaries," Proceedings of the Conference on Lifelong Learning Agents (CoLLAs), 2022.
  22. Hussing, M., Mendez, J., Gummadi, M., & Eaton, E., "CompoSuite: A compositional reinforcement learning benchmark," Proceedings of the Conference on Lifelong Learning Agents (CoLLAs), 2022.
  23. Jang, S., Park, S., Lee, I., & Bastani, O., "Sequential covariate shift detection using classifier two-sample tests," Proceedings of the International Conference on Machine Learning (ICML), 2022.
  24. Jothimurugan, K., Bansal, S., Bastani, O., & Alur, R., "Specification-guided learning of Nash equilibria with high social welfare," Proceedings of the International Conference on Computer Aided Verification (CAV), 2022.
  25. Kaur, R., Jha, S., Roy, A., Park, S., Dobriban, E., Sokolsky, O., & Lee, I., "iDECODe: In-distribution equivariance for conformal out-of-distribution detection," Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2022.
  26. Lin, V., Weimer, J., & Lee, I., "Narrowing the gap: Towards analyzable and realistic simulators for safety analysis of neural network control systems," Workshop on Trustworthy Artificial Intelligence, ECML/PKDD, 2022.
  27. Ma, Y. J., Shen, A., Jayaraman, D., & Bastani, O., "Conservative and adaptive penalty for model-based safe reinforcement learning," Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2022.
  28. Ma, Y. J., Yan, J., Jayaraman, D., & Bastani, O., "Offline goal-conditioned reinforcement learning via f-advantage regression," Advances in Neural Information Processing Systems (NeurIPS), 2022.
  29. Mendez, J., van Seijen, H., & Eaton, E., "Modular lifelong reinforcement learning via neural composition," Proceedings of the International Conference on Learning Representations (ICLR), 2022.
  30. Park, S., Dobriban, E., Lee, I., & Bastani, O., "PAC prediction sets for meta-learning," Advances in Neural Information Processing Systems (NeurIPS), 2022.
  31. Park, S., Dobriban, E., Lee, I., & Bastani, O., "PAC prediction sets under covariate shift," Proceedings of the International Conference on Learning Representations (ICLR), 2022.
  32. Si, W., Li, S., Park, S., Lee, I., & Bastani, O., "Angelic patches for improving third-party object detector performance," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  33. Xu, Y., Lei, J., Dobriban, E., & Daniilidis, K., "Unified Fourier-based kernel and nonlinearity design for equivariant networks on homogeneous spaces," Proceedings of the International Conference on Machine Learning (ICML), 24596–24614, 2022.
  34. Yang, Y., Dutta, S., & Lee, I., "Interpretable detection of distribution shifts in learning-enabled cyber-physical systems," Proceedings of the International Conference on Cyber-Physical Systems (ICCPS), 2022.
  35. Caprio, M., & Mukherjee, S., "Ergodic theorems for dynamic imprecise probability kinematics," International Journal of Approximate Reasoning, 152, 325–343, 2023.
  36. Chatzipantazis, E., Pertigkiozoglou, S., Dobriban, E., & Daniilidis, K., "Learning augmentation distributions using transformed risk minimization," Transactions on Machine Learning Research (TMLR), 2023.
  37. Hussing, M., Mendez, J. A., Singrodia, A., Kent, C., & Eaton, E., "Robotic manipulation datasets for offline compositional reinforcement learning," arXiv preprint arXiv:2307.07091, 2023.
  38. Ji, X., Choi, H., Sokolsky, O., & Lee, I., "Incremental anomaly detection with guarantee in the Internet of Medical Things," Proceedings of the ACM/IEEE Conference on Internet of Things Design and Implementation, 2023.
  39. Kaur, R., Sridhar, K., Park, S., Yang, Y., Jha, S., Roy, A., Sokolsky, O., & Lee, I., "CODiT: Conformal out-of-distribution detection in time-series data for cyber-physical systems," Proceedings of the 14th ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS), 2023.
  40. Kaur, R., Jha, S., Roy, A., Sokolsky, O., & Lee, I., "Predicting out-of-distribution performance of deep neural networks using model conformance," Proceedings of the IEEE International Conference on Assured Autonomy (ICAA), 2023.
  41. Lee, D., Moniri, B., Huang, X., Dobriban, E., & Hassani, H., "Demystifying disagreement-on-the-line in high dimensions," Proceedings of the International Conference on Machine Learning (ICML), 2023.
  42. Mendez, J., & Eaton, E., "How to reuse and compose knowledge for a lifetime of tasks: A survey on continual learning and functional composition," Transactions on Machine Learning Research (TMLR), 2023.
  43. Mell, S., Bastani, F., Zdancewic, S., & Bastani, O., "Synthesizing trajectory queries from examples," Proceedings of the International Conference on Computer Aided Verification (CAV), 2023.
  44. Sridhar, K., Dutta, S., Weimer, J., & Lee, I., "Guaranteed conformance of neurosymbolic models to natural constraints," Proceedings of the Conference on Learning for Dynamics and Control (L4DC), 2023.
  45. Wang, K., He, H., Nguyen, T. D., Kumar, P., & Roth, D., "On regularization and inference with label constraints," Proceedings of the International Conference on Machine Learning (ICML), 2023.
  46. Yang, Y., Dan, S., Roth, D., & Lee, I., "In and out-of-domain text adversarial robustness via label smoothing," Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), 2023.
  47. Yang, Y., Cho, S., Covello, M., Knox, A., Bastani, O., Weimer, J., Dobriban, E., Schultz, R., Lee, I., & Parish-Morris, J., "Automatically predicting perceived conversation quality in a pediatric sample enriched for autism," Proceedings of INTERSPEECH, 4603–4607, 2023.
  48. Gupta, V., Pandya, P., Kataria, T., Gupta, V., & Roth, D., "Evaluating concurrent robustness of language models across diverse challenge sets," Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024.
  49. Mathur, S. V., Bafna, J. S., Kartik, K., Khandelwal, H., Shrivastava, M., Gupta, V., Bansal, M., & Roth, D., "Knowledge-aware reasoning over multimodal semi-structured tables," Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-Findings), 2024.
  50. Mukhopadhyay, S., Qidwai, A., Garimella, A., Ramu, P., Gupta, V., & Roth, D., "Unraveling the truth: Do LLMs really understand charts? A deep dive into consistency and robustness," Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-Findings), 2024.
  51. Singh, S., Chaurasia, P., Varun, Y., Pandya, P., Gupta, V., & Roth, D., "FlowVQA: Mapping multimodal logic in visual question answering with flowcharts," Findings of the Association for Computational Linguistics (ACL-Findings), 2024.
  52. Srivastava, P., Malik, M., Gupta, V., Ganu, T., & Roth, D., "Evaluating LLMs' mathematical reasoning in financial document question answering," Findings of the Association for Computational Linguistics (ACL-Findings), 2024.
  53. Yang, Y., Dan, S., Li, S., Roth, D., & Lee, I., "MrGuard: A multilingual reasoning guardrail for universal LLM safety," Transactions on Machine Learning Research (TMLR), 2024. [Submitted]
  54. Yang, Y., Dan, S., Roth, D., & Lee, I., "Benchmarking LLM guardrails in handling multilingual toxicity," Transactions on Machine Learning Research (TMLR), 2024. [Submitted]
  55. Yang, Y., Dan, S., Roth, D., & Lee, I., "On the calibration of multilingual question answering LLMs," TrustNLP Workshop at NAACL 2024; Transactions on Machine Learning Research (TMLR), 2024. [Submitted]
  56. Abhyankar, N., Gupta, V., Roth, D., & Reddy, C. K., "H-STAR: LLM-driven hybrid SQL-text adaptive reasoning on tables," Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL), 2025.
  57. Deng, I., Dixit, K., Gupta, V., & Roth, D., "Enhancing temporal understanding in LLMs for semi-structured tables," Findings of the North American Chapter of the Association for Computational Linguistics (NAACL-Findings), 2025.
  58. Ji, X., Richardson, J., Raglin, A., Sokolsky, O., & Lee, I., "TAG: Text-enriched anomaly detection on hierarchical graphs with uncertainty quantification," ARL Technical Report, 2025. [Submitted]
  59. Jiang, W., Lei, B., Ashton, K., & Daniilidis, K., "Multimodal LLM guided exploration and active mapping using Fisher information," Proceedings of the International Conference on Computer Vision (ICCV), 2025.
  60. Kulkarni, A., Dixit, K., Srikumar, V., Roth, D., & Gupta, V., "LLM-symbolic integration for robust temporal tabular reasoning," Findings of the Association for Computational Linguistics (ACL-Findings), 2025.
  61. Lin, V., & Lee, I., "Monitor and recover: A paradigm for future research on distribution shift in learning-enabled cyber-physical systems," Proceedings of the International Conference on Cyber-Physical Systems (ICCPS), 2025.
  62. Lin, V., Jang, K. J., Si, W., & Lee, I., "Pattern-guided diffusion models," Advances in Neural Information Processing Systems (NeurIPS), 2025. [Under Review]
  63. Lin, V., Kaur, R., Yang, Y., Dutta, S., Kantaros, Y., Roy, A., Jha, S., Sokolsky, O., & Lee, I., "Safety monitoring for learning-enabled cyber-physical systems in out-of-distribution scenarios," Proceedings of the 16th ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS), 2025.
  64. Lu, P., Caprio, M., Eaton, E., & Lee, I., "IBCL: Zero-shot model generation under stability-plasticity trade-offs," Transactions on Machine Learning Research (TMLR), 2025. [Submitted]
  65. Lu, P., Cleaveland, M., Sokolsky, O., Lee, I., & Ruchkin, I., "Repairing neural network-based control policies with safety preservation," Research Directions: Cyber-Physical Systems, 2025. [Submitted]
  66. Lu, P., Sokolsky, O., Lee, I., & Ruchkin, I., "Accelerating neural policy repair with preservation via stability-plasticity interpolation," Proceedings of the 16th ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS), 2025.
  67. Pandya, P., Gupta, V., Talwar, A., Kataria, T., Roth, D., & Gupta, V., "NTSEBENCH: Cognitive reasoning benchmark for vision language models," Findings of the North American Chapter of the Association for Computational Linguistics (NAACL-Findings), 2025.
  68. Qidwai, A., Mukhopadhyay, S., Khatiwada, P., Roth, D., & Gupta, V., "PRAISE: Enhancing product descriptions with LLM-driven structured insights," Proceedings of the Association for Computational Linguistics (ACL), 2025.
  69. Shankarampeta, A., Mahajan, H., Kataria, T., Roth, D., & Gupta, V., "TRANSIENTTABLES: Evaluating LLMs' reasoning on temporally evolving semi-structured tables," Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL), 2025.
  70. Sridhar, K., Dutta, S., Jayaraman, D., & Lee, I., "REGENT: A retrieval-augmented generalist agent that can act in-context in new environments," Proceedings of the International Conference on Learning Representations (ICLR), 2025. [Oral]
  71. Sridhar, K., Dutta, S., Jayaraman, D., & Lee, I., "RICL: Adding in-context adaptability to pre-trained vision-language-action models," Proceedings of the Conference on Robot Learning (CoRL), 2025.
  72. Zhang, B., Li, S., & Bastani, O., "Conformal structured prediction," Proceedings of the International Conference on Learning Representations (ICLR), 2025.
  73. Dutta, S., Caprio, M., Lin, V., Cleaveland, M., Jang, K. J., Ruchkin, I., Sokolsky, O., & Lee, I., "Distributionally robust statistical verification with imprecise neural networks," Proceedings of the International Conference on Hybrid Systems: Computation and Control (HSCC), 2025.
  74. Feng, Y., Zhou, B., Lin, W., & Roth, D., "BIRD: A trustworthy Bayesian inference framework for large language models," Proceedings of the International Conference on Learning Representations (ICLR), 2025.
  75. Khincha, S., Kataria, T., Anand, A., Roth, D., & Gupta, V., "Leveraging LLM for synchronizing information across multilingual tables," Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL), 2025.
  76. Mukhopadhyay, S., Rajgaria, A., Khatiwada, P., Shrivastava, M., Roth, D., & Gupta, V., "MAPWise: Evaluating vision-language models for advanced map queries," Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL), 2025.
  77. Dan, S., Han, X., & Roth, D., "Compositional data and task augmentation for instruction following," In submission, 2025.
  78. Dan, S., Bastani, O., & Roth, D., "Few-shot novel concept learning for semantic parsing," In submission, 2025.
  79. Gupta, N., Singh, S., Gardner, M., & Roth, D., "Paired examples as indirect supervision in latent decision models," In submission, 2025.
  80. He, H., et al., "Foreseeing the benefits of incidental supervision," In submission, 2025.
  81. He, H., et al., "Weighted training for cross-task learning," In submission, 2025.
  82. Huang, X., Xu, K., Lee, D., Hassani, H., Bastani, H., & Dobriban, E., "Optimal heterogeneous collaborative linear regression and contextual bandits," In submission, 2025.