Related papers: DynaMiCS: Fine-tuning LLMs with Performance Constr…
Because the choice and tuning of the optimizer affects the speed, and ultimately the performance of deep learning, there is significant past and recent research in this area. Yet, perhaps surprisingly, there is no generally agreed-upon…
Efficient multimodal large language models (EMLLMs), in contrast to multimodal large language models (MLLMs), reduce model size and computational costs and are often deployed on resource-constrained devices. However, due to data privacy…
This article proposes an improved trajectory optimization approach for stochastic optimal control of dynamical systems affected by measurement noise by combining optimal control with maximum likelihood techniques to improve the reduction of…
Domain adaptation of neural networks commonly relies on three training phases: pretraining, selected data training and then fine tuning. Data selection improves target domain generalization by training further on pretraining data identified…
Vision-Language Models (VLMs) are typically trained on a diverse set of multi-modal domains, yet current practices rely on costly manual tuning. We propose MaD-Mix, a principled and computationally efficient framework that derives…
Achieving consistent high-quality machine translation (MT) across diverse domains remains a significant challenge, primarily due to the limited and imbalanced parallel training data available in various domains. While large language models…
As deep neural networks (DNNs) prove their importance and feasibility, more and more DNN-based apps, such as detection and classification of objects, have been developed and deployed on autonomous vehicles (AVs). To meet their growing…
When using an LLM to process text outside the training domain(s), an often overlooked factor is vocabulary mismatch, where the general-domain tokenizer fails to capture frequent domain-specific terms, leading to higher token fertility and…
Aligning large language models (LLMs) to human preferences is challenging in domains where preference data is unavailable. We address the problem of learning reward models for such target domains by leveraging feedback collected from…
Domain shift refers to the well known problem that a model trained in one source domain performs poorly when applied to a target domain with different statistics. {Domain Generalization} (DG) techniques attempt to alleviate this issue by…
The distribution shifts between training and test data typically undermine the performance of models. In recent years, lots of work pays attention to domain generalization (DG) where distribution shifts exist, and target data are unseen.…
Pre-trained large language models (LLMs) have become a cornerstone of modern natural language processing, with their capabilities extending across a wide range of applications and languages. However, the fine-tuning of multilingual LLMs,…
Large Language Models (LLMs), with billions of parameters, present significant challenges for full finetuning due to the high computational demands, memory requirements, and impracticality of many real-world applications. When faced with…
Dynamic data selection aims to accelerate training with lossless performance. However, reducing training data inherently limits data diversity, potentially hindering generalization. While data augmentation is widely used to enhance…
Despite the impressive performance of large language models (LLMs), they often lag behind specialized models in various tasks. LLMs only use a fraction of the existing training data for in-context learning, while task-specific models…
Deep metric learning (DML) aims to minimize empirical expected loss of the pairwise intra-/inter- class proximity violations in the embedding space. We relate DML to feasibility problem of finite chance constraints. We show that minimizer…
Instruction tuning significantly enhances the performance of large language models (LLMs) across various tasks. However, the procedure to optimizing the mixing of instruction datasets for LLM fine-tuning is still poorly understood. This…
Increasingly large imitation learning datasets are being collected with the goal of training foundation models for robotics. However, despite the fact that data selection has been of utmost importance in vision and natural language…
Deep Learning (DL) models achieve great successes in many domains. However, DL models increasingly face safety and robustness concerns, including noisy labeling in the training stage and feature distribution shifts in the testing stage.…
Ensembling fine-tuned models initialized from powerful pre-trained weights is a common strategy to improve robustness under distribution shifts, but it comes with substantial computational costs due to the need to train and store multiple…