hidden representation

On the Scaling Laws of Geographical Representation in Language Models COLING 2024 ReFT: Representation Finetuning for Language Models NeurIPS 2024 The Representation Landscape of Few-Shot Learning and Fine-Tuning in Large Language Models NeurIPS 2024 Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis EMNLP 2024 Who's asking? User personas and the mechanics of latent misalignment NeurIPS 2024 A Neural Time Alignment Module for End-to-End Automatic Speech Recognition Interspeech 2023 Connecting Pre-trained Language Model and Downstream Task via Properties of Representation NeurIPS 2023 MixRep: Hidden Representation Mixup for Low-Resource Speech Recognition Interspeech 2023 Self-Distillation for Further Pre-training of Transformers ICLR 2023 Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations ACL 2023 Understanding Transformer Memorization Recall Through Idioms EACL 2023 Exploiting Hidden Representations from a DNN-based Speech Recogniser for Speech Intelligibility Prediction in Hearing-impaired Listeners Interspeech 2022 Feature Learning in L_2-regularized DNNs: Attraction/Repulsion and Sparsity NeurIPS 2022 KALA: Knowledge-Augmented Language Model Adaptation NAACL 2022 On the Pitfalls of Analyzing Individual Neurons in Language Models ICLR 2022 VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers CVPR 2022 Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks NAACL 2021 Dynamic Topic Tracker for KB-to-Text Generation COLING 2020 Towards Transparent and Explainable Attention Models ACL 2020 Uncertainty-Aware Semantic Augmentation for Neural Machine Translation EMNLP 2020 Unsupervised Evaluation for Question Answering with Transformers EMNLP 2020 Putting Words in Context: LSTM Language Models and Lexical Ambiguity ACL 2019 State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations ICML 2019 Understanding and Improving Hidden Representations for Neural Machine Translation NAACL 2019 Visualizing the PHATE of Neural Networks NeurIPS 2019