Related papers: Resolving Token-Space Gradient Conflicts: Token Sp…
Multi-task learning (MTL) improves generalization and data efficiency by jointly learning related tasks through shared representations. In the widely used hard-parameter-sharing setting, a shared backbone is combined with task-specific…
Transformer-based methods have achieved remarkable success in various machine learning tasks. How to design efficient test-time adaptation methods for transformer models becomes an important research task. In this work, motivated by the…
In recent years, the parameters of backbones of Video Understanding tasks continue to increase and even reach billion-level. Whether fine-tuning a specific task on the Video Foundation Model or pre-training the model designed for the…
Balancing competing objectives remains a fundamental challenge in multi-task learning (MTL), primarily due to conflicting gradients across individual tasks. A common solution relies on computing a dynamic gradient update vector that…
Training a single network with multiple objectives often leads to conflicting gradients that degrade shared representations, forcing them into a compromised state that is suboptimal for any single task--a problem we term latent…
Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…
Multi-task learning (MTL) has become an essential machine learning tool for addressing multiple learning tasks simultaneously and has been effectively applied across fields such as healthcare, marketing, and biomedical research. However, to…
Large-scale pre-trained Vision-Language Models (VLMs) have significantly advanced transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, undermining their ability to…
Tabular data is the most abundant data type in the world, powering systems in finance, healthcare, e-commerce, and beyond. As tabular datasets grow and span multiple related targets, there is an increasing need to exploit shared task…
Multimodal Large Language Models (MLLMs) struggle with continual learning, often suffering from catastrophic forgetting when adapting to sequential tasks. We introduce a routing-based architecture that integrates new capabilities while…
In a multi-task learning (MTL) setting, a single model is trained to tackle a diverse set of tasks jointly. Despite rapid progress in the field, MTL remains challenging due to optimization issues such as conflicting and dominating…
Recently, researchers have utilized neural networks to accurately solve partial differential equations (PDEs), enabling the mesh-free method for scientific computation. Unfortunately, the network performance drops when encountering a high…
Transfer learning (TL) enables the transfer of knowledge gained in learning to perform one task (source) to a related but different task (target), hence addressing the expense of data acquisition and labeling, potential computational power…
Distance metric learning (DML) aims to find an appropriate way to reveal the underlying data relationship. It is critical in many machine learning, pattern recognition and data mining algorithms, and usually require large amount of label…
Multi-task-learning(MTL) is a multi-target optimization task. Neural networks try to realize each target using a shared interpretative space within MTL. However, as the scale of datasets expands and the complexity of tasks increases,…
Over the past decades, researchers have primarily focused on improving the generalization abilities of models, with limited attention given to regulating such generalization. However, the ability of models to generalize to unintended data…
Jointly learning multiple tasks with a unified model can improve accuracy and data efficiency, but it faces the challenge of task interference, where optimizing one task objective may inadvertently compromise the performance of another. A…
Large language models (LLMs) face inherent performance bottlenecks under parameter constraints, particularly in processing critical tokens that demand complex reasoning. Empirical analysis reveals challenging tokens induce abrupt gradient…
Multi-task learning (MTL) is a supervised learning paradigm in which the prediction models for several related tasks are learned jointly to achieve better generalization performance. When there are only a few training examples per task, MTL…
Distance metric learning (DML) approaches learn a transformation to a representation space where distance is in correspondence with a predefined notion of similarity. While such models offer a number of compelling benefits, it has been…