Related papers: Rethinking the adaptive relationship between Encod…

Encoder-decoder models such as FLAN-T5 are finetuned to follow instructions, but often fail when the instructions conflict with memorized continuations ingrained during training. To understand this behavior, we adapt DoLa to FLAN-T5 and…

Adapting large-scale pre-trained generative models in a parameter-efficient manner is gaining traction. Traditional methods like low rank adaptation achieve parameter efficiency by imposing constraints but may not be optimal for tasks…

We propose and evaluate a novel procedure for training multiple Transformers with tied parameters which compresses multiple models into one enabling the dynamic choice of the number of encoder and decoder layers during decoding. In…

Transformer-based architectures have been the subject of research aimed at understanding their overparameterization and the non-uniform importance of their layers. Applying these approaches to Automatic Speech Recognition, we demonstrate…

Multimodal Machine Translation (MMT) aims to improve translation quality by leveraging auxiliary modalities such as images alongside textual input. While recent advances in large-scale pre-trained language and vision models have…

Convolutional layers with 1-D filters are often used as frontend to encode audio signals. Unlike fixed time-frequency representations, they can adapt to the local characteristics of input data. However, 1-D filters on raw audio are hard to…

Advanced neural machine translation (NMT) models generally implement encoder and decoder as multiple layers, which allows systems to model complex functions and capture complicated linguistic structures. However, only the top layers of…

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific…

Fine-tuning is a crucial paradigm for adapting pre-trained large language models to downstream tasks. Recently, methods like Low-Rank Adaptation (LoRA) have been shown to effectively fine-tune LLMs with an extreme reduction in trainable…

We present and discuss several novel applications of deep learning for the physical layer. By interpreting a communications system as an autoencoder, we develop a fundamental new way to think about communications system design as an…

In this paper, we study the use of deep Transformer translation model for the CCMT 2022 Chinese-Thai low-resource machine translation task. We first explore the experiment settings (including the number of BPE merge operations, dropout…

Among parameter-efficient fine-tuning methods, freezing has emerged as a popular strategy for speeding up training, reducing catastrophic forgetting, and improving downstream performance. We investigate the impact of freezing the decoder in…

This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods…

Test-time adaptation (TTA) refers to adjusting the model during the testing phase to cope with changes in sample distribution and enhance the model's adaptability to new environments. In real-world scenarios, models often encounter samples…

Building extraction $-$ needed for inventory management and planning of urban environment $-$ is affected by the misalignment between labels and off-nadir source imagery in training data. Teacher-Student learning of noise-tolerant…

Low-Rank Adaptation (LoRA) has emerged as one of the most widely used parameter-efficient fine-tuning (PEFT) methods for adapting large language models (LLMs) to downstream tasks. While highly effective in single-task settings, it struggles…

Tying the weights of the target word embeddings with the target word classifiers of neural machine translation models leads to faster training and often to better translation quality. Given the success of this parameter sharing, we…

While different neural models often exhibit latent spaces that are alike when exposed to semantically related data, this intrinsic similarity is not always immediately discernible. Towards a better understanding of this phenomenon, our work…

In this paper, we propose a multilingual encoder-decoder architecture capable of obtaining multilingual sentence representations by means of incorporating an intermediate {\em attention bridge} that is shared across all languages. That is,…

Existing approaches to explaining deep learning models in NLP usually suffer from two major drawbacks: (1) the main model and the explaining model are decoupled: an additional probing or surrogate model is used to interpret an existing…