 |
 EMR-Merging: Tuning-Free High-Performance Model MergingNeural Information Processing Systems (NeurIPS), 2024 |
 Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer ModelsInternational Conference on Learning Representations (ICLR), 2024 |
 Effective In-Context Example Selection through Data CompressionAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
 Keep It Private: Unsupervised Privatization of Online TextNorth American Chapter of the Association for Computational Linguistics (NAACL), 2024 |
 Polarity Calibration for Opinion SummarizationNorth American Chapter of the Association for Computational Linguistics (NAACL), 2024 |
 Monotonic Paraphrasing Improves Generalization of Language Model
PromptingConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 |
 Enhancing Effectiveness and Robustness in a Low-Resource Regime via
Decision-Boundary-aware Data AugmentationInternational Conference on Language Resources and Evaluation (LREC), 2024 |
 Using Shapley interactions to understand how models use structureAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
 Enhancing Transfer Learning with Flexible Nonparametric Posterior
SamplingInternational Conference on Learning Representations (ICLR), 2024 |
 SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model CompressionInternational Conference on Learning Representations (ICLR), 2024 |
 Rebuilding ROME : Resolving Model Collapse during Sequential Model
EditingConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 |
