 SkipSNN: Efficiently Classifying Spike Trains with Event-attentionBigData Congress [Services Society] (BSS), 2024 |
 Improving Machine Translation with Large Language Models: A Preliminary
Study with Cooperative DecodingAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 |
 Transformer-VQ: Linear-Time Transformers via Vector QuantizationInternational Conference on Learning Representations (ICLR), 2023 |
 On "Scientific Debt" in NLP: A Case for More Rigour in Language Model
Pre-Training ResearchAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 |
 Multi-Head State Space Model for Speech RecognitionInterspeech (Interspeech), 2023 |
 Conditional Adapters: Parameter-efficient Transfer Learning with Fast
InferenceNeural Information Processing Systems (NeurIPS), 2023 |
 Unsupervised Protein-Ligand Binding Energy Prediction via Neural Euler's
Rotation EquationNeural Information Processing Systems (NeurIPS), 2023 |
 |
 Fine-Tuning Pre-trained Transformers into Decaying Fast WeightsConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Reprogramming Pretrained Language Models for Antibody Sequence InfillingInternational Conference on Machine Learning (ICML), 2022 |
 Mega: Moving Average Equipped Gated AttentionInternational Conference on Learning Representations (ICLR), 2022 |
 Adapting Pretrained Text-to-Text Models for Long Text SequencesConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Confident Adaptive Language ModelingNeural Information Processing Systems (NeurIPS), 2022 |
 Long Range Language Modeling via Gated State SpacesInternational Conference on Learning Representations (ICLR), 2022 |
 Training Language Models with Memory AugmentationConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Implicit N-grams Induced by RecurrenceNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 Xiaobing Sun Wei Lu |
 Block-Recurrent TransformersNeural Information Processing Systems (NeurIPS), 2022 |
 Mukayese: Turkish NLP Strikes BackFindings (Findings), 2022 |
 SRU++: Pioneering Fast Recurrence with Attention for Speech RecognitionIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021 |
 Iterative Refinement Graph Neural Network for Antibody
Sequence-Structure Co-designInternational Conference on Learning Representations (ICLR), 2021 |
 Finetuning Pretrained Transformers into RNNsConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
