 Flora: Low-Rank Adapters Are Secretly Gradient CompressorsInternational Conference on Machine Learning (ICML), 2024 |
 Unlearning Traces the Influential Training Data of Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
 HiFT: A Hierarchical Full Parameter Fine-Tuning StrategyConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 |
 TURNA: A Turkish Encoder-Decoder Language Model for Enhanced
Understanding and GenerationAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
 Lumiere: A Space-Time Diffusion Model for Video GenerationACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia (SIGGRAPH Asia), 2024 |
 WARM: On the Benefits of Weight Averaged Reward ModelsInternational Conference on Machine Learning (ICML), 2024 Alexandre Ramé Nino Vieillard Léonard Hussenot Robert Dadashi Geoffrey Cideron Olivier Bachem Johan Ferret |
 Instruct-Imagen: Image Generation with Multi-modal InstructionComputer Vision and Pattern Recognition (CVPR), 2024 |
 To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine
Translation vs Human TranslationTransactions of the Association for Computational Linguistics (TACL), 2024 |
 Magicoder: Empowering Code Generation with OSS-InstructInternational Conference on Machine Learning (ICML), 2023 |
 Locally Optimal Descent for Dynamic Stepsize SchedulingInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 |
 Diffusion Model Alignment Using Direct Preference OptimizationComputer Vision and Pattern Recognition (CVPR), 2023 |
 Making Harmful Behaviors Unlearnable for Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 |
 Calibrated Seq2seq Models for Efficient and Generalizable Ultra-fine
Entity TypingConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 De-Diffusion Makes Text a Strong Cross-Modal InterfaceComputer Vision and Pattern Recognition (CVPR), 2023 |
 HARE: Explainable Hate Speech Detection with Step-by-Step ReasoningConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
