 Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in
Closed-Source LLMsConference of the European Chapter of the Association for Computational Linguistics (EACL), 2024 |
 Deep Learning Model Reuse in the HuggingFace Community: Challenges,
Benefit and TrendsIEEE International Conference on Software Analysis, Evolution, and Reengineering (SANER), 2024 |
 Enhancing In-context Learning via Linear Probe CalibrationInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2024 |
 B-Cos Aligned Transformers Learn Human-Interpretable FeaturesInternational Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2024 |
 Effects of diversity incentives on sample diversity and downstream model
performance in LLM-based text augmentationAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
 MetaHate: A Dataset for Unifying Efforts on Hate Speech DetectionInternational Conference on Web and Social Media (ICWSM), 2024 |
 DREAM: Debugging and Repairing AutoML PipelinesACM Transactions on Software Engineering and Methodology (TOSEM), 2023 |
 GreenFlow: A Computation Allocation Framework for Building
Environmentally Sound Recommendation SystemInternational Joint Conference on Artificial Intelligence (IJCAI), 2023 |
 Power Hungry Processing: Watts Driving the Cost of AI Deployment?Conference on Fairness, Accountability and Transparency (FAccT), 2023 |
 Survey on AI Ethics: A Socio-technical PerspectiveInternational Conference on Climate Informatics (ICCI), 2023 |
 Data Augmentation for Code Translation with Comparable Corpora and
Multiple ReferencesConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked
AutoencodersIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2023 |
 |
 From Molecules to Materials: Pre-training Large Generalizable Models for
Atomic Property PredictionInternational Conference on Learning Representations (ICLR), 2023 |
 Manifold-Preserving Transformers are Effective for Short-Long Range
EncodingConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 On Bilingual Lexicon Induction with Large Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
