Related papers: Hierarchical Recurrent Adapters for Efficient Mult…

Automatic parameter tuning methods for planning algorithms, which integrate pipeline approaches with learning-based techniques, are regarded as promising due to their stability and capability to handle highly constrained environments. While…

Large Reasoning Models (LRMs) often suffer from computational inefficiency due to overthinking, where a fixed reasoning budget fails to match the varying complexity of tasks. To address this issue, we propose Adaptive Overclocking, a method…

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…

Self-supervised learning has emerged as a key approach for learning generic representations from speech data. Despite promising results in downstream tasks such as speech recognition, speaker verification, and emotion recognition, a…

Parameter-efficient fine-tuning (PEFT) has emerged as a powerful paradigm for adapting large-scale pre-trained models to downstream tasks with minimal additional parameters. Among PEFT methods, Low-Rank Adaptation (LoRA) stands out for its…

Automatic Speech Recognition (ASR) systems are often optimized to work best for speakers with canonical speech patterns. Unfortunately, these systems perform poorly when tested on atypical speech and heavily accented speech. It has…

Large language models (LMs) are typically adapted to improve performance on new contexts (\eg text prompts that define new tasks or domains) through fine-tuning or prompting. However, there is an accuracy compute tradeoff -- fine-tuning…

The remarkable success of large language models has been driven by dense models trained on massive unlabeled, unstructured corpora. These corpora typically contain text from diverse, heterogeneous sources, but information about the source…

Non-hierarchical sparse attention Transformer-based models, such as Longformer and Big Bird, are popular approaches to working with long documents. There are clear benefits to these approaches compared to the original Transformer in terms…

We propose a novel framework, termed Fourier-Activated Adapter (FAA), for parameter-efficient fine-tuning of large pre-trained language models. By incorporating random Fourier features into lightweight adapter modules, FAA decomposes…

While vision-and-language models significantly advance in many fields, the challenge of continual learning is unsolved. Parameter-efficient modules like adapters and prompts present a promising way to alleviate catastrophic forgetting.…

Adapting pre-trained models with broad capabilities has become standard practice for learning a wide range of downstream tasks. The typical approach of fine-tuning different models for each task is performant, but incurs a substantial…

The pretrain-then-finetune paradigm has been widely used in various unimodal and multimodal tasks. However, finetuning all the parameters of a pre-trained model becomes prohibitive as the model size grows exponentially. To address this…

Incremental learning aims to adapt to new sets of categories over time with minimal computational overhead. Prior work often addresses this task by training efficient task-specific adaptors that modify frozen layer weights or features to…

Long-form speech recognition is an application area of increasing research focus. ASR models based on multi-head attention (MHA) are ill-suited to long-form ASR because of their quadratic complexity in sequence length. We build on recent…

Fine-tuning large language models for different tasks can be costly and inefficient, and even methods that reduce the number of tuned parameters still require full gradient-based optimization. We propose HyperTuning, a novel approach to…

Generating a robust representation of the environment is a crucial ability of learning agents. Deep learning based methods have greatly improved perception systems but still fail in challenging situations. These failures are often not…

State-of-the-art pretrained NLP models contain a hundred million to trillion parameters. Adapters provide a parameter-efficient alternative for the full finetuning in which we can only finetune lightweight neural network layers on top of…

Adapters provide an efficient and lightweight mechanism for adapting trained transformer models to a variety of different tasks. However, they have often been found to be outperformed by other adaptation mechanisms, including low-rank…

The quadratic computational complexity of MultiHead SelfAttention (MHSA) remains a fundamental bottleneck in scaling Large Language Models (LLMs) for longcontext tasks. While sparse and linearized attention mechanisms attempt to mitigate…