publications
Below are recent and selected ones. For a complete list, please refer to the vitae
2024
- Sci. Adv.
- ICMLDySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic SystemsIn Proc. of ICML, 2024
- NAACLA Systematic Comparison of Syllogistic Reasoning in Humans and Language ModelsIn Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics, 2024
- AAAIV2Meow: Meowing to the Visual Beat via Video-to-Music GenerationIn Proceedings of the AAAI Conference on Artificial Intelligence, 2024
- JAMESWeatherBench 2: A Benchmark for the Next Generation of Data-Driven Global Weather ModelsJournal of Advances in Modeling Earth Systems, 2024
- NAACLThe Impact of Depth on Compositional Generalization in Transformer Language ModelsIn Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024
2023
- NeurIPSNeural Ideal Large Eddy Simulation: Modeling Turbulence with Neural Stochastic Differential EquationsIn Advances in Neural Information Processing Systems, 2023
- NeurIPSDebias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion ModelsIn Advances in Neural Information Processing Systems, 2023
- ICMLUser-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical SystemsIn ICML, 2023
- ICMLPre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your computeIn ICML, 2023
- ACLFiDO: Fusion-in-Decoder optimized for stronger performance and faster inferenceIn Findings of ACL, 2023
- ICLREvolve Smoothly, Fit Consistently: Learning Smooth Latent Dynamics For Advection-Dominated SystemsIn ICLR, 2023
2022
- PAMIDrinking from a firehose: Continual learning with web-scale natural languageIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- EMNLPEvaluating the Impact of Model Scale for Compositional Generalization in Semantic ParsingIn EMNLP, 2022
- COLINGGenerate-and-Retrieve: use your predictions to improve retrieval for semantic parsingIn COLING, 2022
- NeurIPS
- ICLRMention Memory: incorporating textual knowledge into Transformers through entity mention attentionIn ICLR, 2022
- ICLR
- AISTAS
2021
- EMNLPSystematic Generalization on gSCAN: what is nearly solved and what is next?In Proc. of EMNLP, 2021
- EMNLP
- ICMLRandomized Entity-wise Factorization for Multi-Agent Reinforcement LearningIn Proc. of Intl. Conf. on Machine Learning (ICML), 2021
- AISTATS
- ICDARCoMSum and SIBERT: A Dataset and Neural Model for Query-Based Multi-Document SummarizationIn Proceedings of Intl. Conf. on Document Analysis and Recognition, 2021
- EACLDOCENT: Learning Self-Supervised Entity Representations from Large Document CollectionsIn Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, Apr 2021
- NAACLReadTwice: Reading Very Large Documents with MemoriesIn Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun 2021
2020
- IJCV
- EMNLPLearning to Represent Image and Text with Denotation GraphIn Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov 2020
- ACLBabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby StepsIn Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020, Nov 2020
- CVPRFew-Shot Learning via Embedding Adaptation With Set-to-Set FunctionsIn The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2020
- AISTATS
2019
- ICMLActor-Attention-Critic for Multi-Agent Reinforcement LearningIn Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, Jun 2019
2016
- CVPR
2013
- NeurIPSSimilarity Component AnalysisIn Proc. of Annual Conference on Neural Information Processing Systems (NIPS), Jun 2013
2012
- CVPRGeodesic Flow Kernel for Unsupervised Domain AdaptationIn Proceedings of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Jun 2012
2010
- NeurIPSUnsupervised Kernel Dimension ReductionIn Proceedings of Neural Information Processing (NIPS), Jun 2010
2007
- NeurIPSLarge margin hidden Markov models for automatic speech recognitionIn Advances in Neural Information Processing Systems 19, Jun 2007
2003
- NAACL-HLTShallow Parsing with Conditional Random FieldsIn Proceedings of Human Language Technology-NAACL 2003, Jun 2003