Publications
Publications & Preprints.
2024
2024
- NeurIPS 2024Gradient Rewiring for Editable Graph Neural Network TrainingIn The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024
- EMNLP 2024In Defense of Structural Sparse Adapters for Concurrent LLM ServingIn Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November 12-16, 2024, 2024
- EMNLP 2024QUEST: Efficient Extreme Multi-Label Text Classification with Large Language Models on Commodity HardwareIn Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November 12-16, 2024, 2024
- EMNLP 2024Taylor Unswift: Secured Weight Release for Large Language Models via Taylor ExpansionIn Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024, Miami, FL, USA, November 12-16, 2024, 2024
- EMNLP 2024KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable ApproachesIn Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November 12-16, 2024, 2024
- ICML 2024
- ICML 2024TVE: Learning Meta-attribution for Transferable Vision ExplainerIn Forty-first International Conference on Machine Learning, 2024
- ICML 2024GNNs Also Deserve Editing, and They Need It More Than OnceIn Forty-first International Conference on Machine Learning, 2024
- ICML 2024Soft Prompt Recovers Compressed LLMs, TransferablyIn Forty-first International Conference on Machine Learning, 21–27 jul 2024
- ICML 2024
2023
2023
- ICML 2023DIVISION: Memory Efficient Training via Dual Activation PrecisionIn International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA, 21–27 jul 2023
- NeurIPS 2023Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language ModelIn Thirty-seventh Conference on Neural Information Processing Systems, 21–27 jul 2023
- KDD-MLGEditable Graph Neural Network for Node ClassificationsIn The 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining on Mining and Learning with Graphs Workshop, 21–27 jul 2023
- NeurIPS 2023Setting the Trap: Capturing and Defeating Backdoor Threats in PLMs through HoneypotsIn Thirty-seventh Conference on Neural Information Processing Systems, 21–27 jul 2023
- NeurIPS 2023One Less Reason for Filter Pruning: Gaining Free Adversarial Robustness with Structured Grouped Kernel PruningIn Thirty-seventh Conference on Neural Information Processing Systems, 21–27 jul 2023
- ICML 2023RSC: Accelerate Graph Neural Networks Training via Randomized Sparse ComputationsIn International Conference on Machine Learning, 21–27 jul 2023
- MLSys 2023Pre-train and Search: Efficient Embedding Table Sharding with Pre-trained Neural Cost ModelsProceedings of Machine Learning and Systems, 21–27 jul 2023
- TMLRDSpar: An Embarrassingly Simple Strategy for Efficient GNN training and inference via Degree-based SparsificationTransactions on Machine Learning Research, 21–27 jul 2023
- TMLRRetiring δDP: New Distribution-Level Metrics for Demographic ParityTransactions on Machine Learning Research, 21–27 jul 2023
- SDMAdaptive label smoothing to regularize large-scale graph trainingIn Proceedings of the 2023 SIAM International Conference on Data Mining (SDM), 21–27 jul 2023
2022
2022
- NeurIPSDreamshard: Generalizable embedding table placement for recommender systemsAdvances in Neural Information Processing Systems, 21–27 jul 2022
- IJCAITable2graph: Transforming tabular data to unified weighted graphIn Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI, 21–27 jul 2022
- NeurIPSA Comprehensive Study on Large-Scale Graph Training: Benchmarking and RethinkingIn Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 21–27 jul 2022
2021
2021
- ICLRAn information fusion approach to learning with instance-dependent label noiseIn International Conference on Learning Representations, 21–27 jul 2021
- ICLREXACT: Scalable graph neural networks training via extreme activation compressionIn International Conference on Learning Representations, 21–27 jul 2021
- WWWMitigating gender bias in captioning systemsIn Proceedings of the Web Conference 2021, 21–27 jul 2021
- ICCVDivAug: Plug-in automated data augmentation with explicit diversity maximizationIn Proceedings of the IEEE/CVF International Conference on Computer Vision, 21–27 jul 2021
2020
2020
- RecSys DemoAutorec: An automated recommender systemIn Proceedings of the 14th ACM Conference on Recommender Systems, 21–27 jul 2020
- NeurIPSDetecting interactions from neural networks via topological analysisAdvances in Neural Information Processing Systems, 21–27 jul 2020
\(*\) equal contribution.