相关论文: TAIL: Task-specific Adapters for Imitation Learnin…

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…

Adapting large pretrained models to new tasks efficiently and continually is crucial for real-world deployment but remains challenging due to catastrophic forgetting and the high cost of retraining. While parameter-efficient tuning methods…

Low-rank adaptations (LoRAs) have revolutionized the finetuning of large foundation models, enabling efficient adaptation even with limited computational resources. The resulting proliferation of LoRAs presents exciting opportunities for…

Although instruction tuning is widely used to adjust behavior in Large Language Models (LLMs), extensive empirical evidence and research indicates that it is primarily a process where the model fits to specific task formats, rather than…

Low-Rank Adaptation (LoRA) is a standard tool for parameter-efficient finetuning of large models. While it induces a small memory footprint, its training dynamics can be surprisingly complex as they depend on several hyperparameters such as…

Instruction fine-tuned language models on a collection of instruction annotated datasets (FLAN) have shown highly effective to improve model performance and generalization to unseen tasks. However, a majority of standard parsing tasks…

The rapid advancement of foundation modelslarge-scale neural networks trained on diverse, extensive datasetshas revolutionized artificial intelligence, enabling unprecedented advancements across domains such as natural language processing,…

Pretrained Transformers achieve state-of-the-art performance in various code-processing tasks but may be too large to be deployed. As software development tools often incorporate modules for various purposes which may potentially use a…

Vision-Language-Action (VLA) models pre-trained on large, diverse datasets show remarkable potential for general-purpose robotic manipulation. However, a primary bottleneck remains in adapting these models to downstream tasks, especially…

In recent years, the development of robotics and artificial intelligence (AI) systems has been nothing short of remarkable. As these systems continue to evolve, they are being utilized in increasingly complex and unstructured environments,…

Transfer learning (TL) leverages previously obtained knowledge to learn new tasks efficiently and has been used to train deep learning (DL) models with limited amount of data. When TL is applied to DL, pretrained (teacher) models are…

Language models (LMs) pretrained on a large text corpus and fine-tuned on a downstream text corpus and fine-tuned on a downstream task becomes a de facto training strategy for several natural language processing (NLP) tasks. Recently, an…

Transformers pretrained on diverse tasks exhibit remarkable in-context learning (ICL) capabilities, enabling them to solve unseen tasks solely based on input contexts without adjusting model parameters. In this paper, we study ICL in one of…

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…

Policy learning under action constraints plays a central role in ensuring safe behaviors in various robot control and resource allocation applications. In this paper, we study a new problem setting termed Action-Constrained Imitation…

The ability of Large Language Models (LLMs) to solve complex tasks has made them crucial in the development of AI-based applications. However, the high computational requirements to fine-tune these LLMs on downstream tasks pose significant…

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…

In the context of resource-constrained environments such as embedded systems, adapting reduced-size foundation models to downstream tasks has become increasingly popular. This has recently motivated the emerging setting of task-specific…

The emergent ability of Large Language Models to use a small number of examples to learn to perform in novel domains and tasks, also called in-context learning (ICL). In this work, we show that a much smaller model can be trained to perform…

Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments, a critical step toward generalized AI. However, the standard supervised fine-tuning (SFT) approach, which relies on large-scale…