Related papers: MELTR: Meta Loss Transformer for Learning to Fine-…

During recent years transformers architectures have been growing in popularity. Modulated Detection Transformer (MDETR) is an end-to-end multi-modal understanding model that performs tasks such as phase grounding, referring expression…

Pre-trained neural language models bring significant improvement for various NLP tasks, by fine-tuning the models on task-specific training sets. During fine-tuning, the parameters are initialized from pre-trained models directly, which…

The power of foundation models (FMs) lies in their capacity to learn highly expressive representations that can be adapted to a broad spectrum of tasks. However, these pretrained models require additional training stages to become effective…

Loss function learning is a new meta-learning paradigm that aims to automate the essential task of designing a loss function for a machine learning model. Existing techniques for loss function learning have shown promising results, often…

This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods…

Typically, loss functions, regularization mechanisms and other important aspects of training parametric models are chosen heuristically from a limited set of options. In this paper, we take the first step towards automating this process,…

This paper proposes Video-Teller, a video-language foundation model that leverages multi-modal fusion and fine-grained modality alignment to significantly enhance the video-to-text generation task. Video-Teller boosts the training…

Multi-task learning (MTL) is an efficient solution to solve multiple tasks simultaneously in order to get better speed and performance than handling each single-task in turn. The most current methods can be categorized as either: (i) hard…

In this paper, we explore the possibility of building a unified foundation model that can be adapted to both vision-only and text-only tasks. Starting from BERT and ViT, we design a unified transformer consisting of modality-specific…

Deploying natural language processing (NLP) models on mobile platforms requires models that can adapt across diverse applications while remaining efficient in memory and computation. We investigate pre-finetuning strategies to enhance the…

We present \textbf{Met}a-\textbf{T}oken \textbf{Le}arning (Mettle), a simple and memory-efficient method for adapting large-scale pretrained transformer models to downstream audio-visual tasks. Instead of sequentially modifying the output…

Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…

Deep neural networks have become a foundational tool for addressing imaging inverse problems. They are typically trained for a specific task, with a supervised loss to learn a mapping from the observations to the image to recover. However,…

The advent of pre-trained Vision-Language Models (VLMs) has significantly transformed Continual Learning (CL), mainly due to their zero-shot classification abilities. Such proficiency makes VLMs well-suited for real-world applications,…

Reinforcement Learning (RL) has been successful in various domains like robotics, game playing, and simulation. While RL agents have shown impressive capabilities in their specific tasks, they insufficiently adapt to new tasks. In…

In medical image analysis, transfer learning is a powerful method for deep neural networks (DNNs) to generalize well on limited medical data. Prior efforts have focused on developing pre-training algorithms on domains such as lung…

Distilling the tool-using capabilities of large language models (LLMs) into smaller, more efficient small language models (SLMs) is a key challenge for their practical application. The predominant approach, supervised fine-tuning (SFT),…

In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric. In this work we assess this assumption by meta-learning an adaptive loss function to…

Recent state-of-the-art language models utilize a two-phase training procedure comprised of (i) unsupervised pre-training on unlabeled text, and (ii) fine-tuning for a specific supervised task. More recently, many studies have been focused…

Multi-Task Learning (MTL) for Vision Transformer aims at enhancing the model capability by tackling multiple tasks simultaneously. Most recent works have predominantly focused on designing Mixture-of-Experts (MoE) structures and in…