相关论文: Knowledge Composition using Task Vectors with Lear…

Reinforcement learning (RL) has demonstrated remarkable potential in robotic manipulation but faces challenges in sample inefficiency and lack of interpretability, limiting its applicability in real world scenarios. Enabling the agent to…

Successfully addressing a wide variety of tasks is a core ability of autonomous agents, requiring flexibly adapting the underlying decision-making strategies and, as we argue in this work, also adapting the perception modules. An analogical…

Tabular learning transforms raw features into optimized spaces for downstream tasks, but its effectiveness deteriorates under distribution shifts between training and testing data. We formalize this challenge as the Distribution Shift…

Leveraging task-aware annotated data as supervised signals to assist with self-supervised learning on large-scale unlabeled data has become a new trend in pre-training language models. Existing studies show that multi-task learning with…

Auxiliary tasks facilitate learning in situations where data is scarce or the principal task of interest is extremely complex. This idea is primarily inspired by the improved generalization capability induced by solving multiple tasks…

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…

Multi-task learning (MTL) models have demonstrated impressive results in computer vision, natural language processing, and recommender systems. Even though many approaches have been proposed, how well these approaches balance different…

Large-scale vision-language models (VLMs) pre-trained on billion-level data have learned general visual representations and broad visual concepts. In principle, the well-learned knowledge structure of the VLMs should be inherited…

Task arithmetic enables efficient model editing by representing task-specific changes as vectors in parameter space. Task arithmetic typically assumes that the source and target models are initialized from the same pre-trained parameters.…

Task arithmetic refers to editing the pre-trained model by adding a weighted sum of task vectors, each of which is the weight update from the pre-trained model to fine-tuned models for certain tasks. This approach recently gained attention…

A modular design encourages neural models to disentangle and recombine different facets of knowledge to generalise more systematically to new tasks. In this work, we assume that each task is associated with a subset of latent discrete…

While recent continual learning methods largely alleviate the catastrophic problem on toy-sized datasets, some issues remain to be tackled to apply them to real-world problem domains. First, a continual learning model should effectively…

Model merging integrates the weights of multiple task-specific models into a single multi-task model. Despite recent interest in the problem, a significant performance gap between the combined and single-task models remains. In this paper,…

Multi-task learning (MTL) is frequently used in settings where a target task has to be learnt based on limited training data, but knowledge can be leveraged from related auxiliary tasks. While MTL can improve task performance overall…

High-dimensional, heterogeneous data with complex feature interactions pose significant challenges for traditional predictive modeling approaches. While Projection to Latent Structures (PLS) remains a popular technique, it struggles to…

Adapting large pretrained models to diverse tasks is now routine, yet the two dominant strategies of parameter-efficient fine-tuning (PEFT) and low-rank compression are typically composed in sequence. This decoupled practice first…

Meta-learning stands for 'learning to learn' such that generalization to new tasks is achieved. Among these methods, Gradient-based meta-learning algorithms are a specific sub-class that excel at quick adaptation to new tasks with limited…

Systematic generalization refers to the capacity to understand and generate novel combinations from known components. Despite recent progress by large language models (LLMs) across various domains, these models often fail to extend their…

Large language models (LLMs) have demonstrated remarkable proficiency in in-context learning (ICL), where models adapt to new tasks through example-based prompts without requiring parameter updates. However, understanding how tasks are…

Adapter-style efficient transfer learning (ETL) has shown excellent performance in the tuning of vision-language models (VLMs) under the low-data regime, where only a few additional parameters are introduced to excavate the task-specific…