Related papers: Learning to Prompt Knowledge Transfer for Open-Wor…

Knowledge Transfer (KT) techniques tackle the problem of transferring the knowledge from a large and complex neural network into a smaller and faster one. However, existing KT methods are tailored towards classification tasks and they…

Growing concerns surrounding AI safety and data privacy have driven the development of Machine Unlearning as a potential solution. However, current machine unlearning algorithms are designed to complement the offline training paradigm. The…

Continual learning (CL) is a new online learning technique over sequentially generated streaming data from different tasks, aiming to maintain a small forgetting loss on previously-learned tasks. Existing work focuses on reducing the…

Continual Learning (CL) has generated attention as a method of avoiding Catastrophic Forgetting (CF) in the sequential training of neural networks, improving network efficiency and adaptability to different tasks. Additionally, CL serves as…

Vision-language models (VLMs) such as CLIP demonstrate strong performance but struggle when adapted to downstream tasks. Prompt learning has emerged as an efficient and effective strategy to adapt VLMs while preserving their pre-trained…

Open-World Object Detection (OWOD) enriches traditional object detectors by enabling continual discovery and integration of unknown objects via human guidance. However, existing OWOD approaches frequently suffer from semantic confusion…

Recently, prompt learning has become a new paradigm to utilize pre-trained language models (PLMs) and achieves promising results in downstream tasks with a negligible increase of parameters. The current usage of discrete and continuous…

Knowledge Tracing (KT) is a fundamental technology in intelligent tutoring systems used to simulate changes in students' knowledge state during learning, track personalized knowledge mastery, and predict performance. However, current KT…

Most modern neural networks for classification fail to take into account the concept of the unknown. Trained neural networks are usually tested in an unrealistic scenario with only examples from a closed set of known classes. In an attempt…

Continual Learning (CL) seeks to build an agent that can continuously learn a sequence of tasks, where a key challenge, namely Catastrophic Forgetting, persists due to the potential knowledge interference among different tasks. On the other…

This paper addresses the open set recognition (OSR) problem, where the goal is to correctly classify samples of known classes while detecting unknown samples to reject. In the OSR problem, "unknown" is assumed to have infinite possibilities…

Lifelong learning can be viewed as a continuous transfer learning procedure over consecutive tasks, where learning a given task depends on accumulated knowledge --- the so-called knowledge base. Most published work on lifelong learning…

Modern AI models are typically trained on static datasets, limiting their ability to continuously adapt to rapidly evolving real-world environments. While continual learning (CL) addresses this limitation, most CL methods are designed for…

The ability to evolve is fundamental for any valuable autonomous agent whose knowledge cannot remain limited to that injected by the manufacturer. Consider for example a home assistant robot: it should be able to incrementally learn new…

The longstanding goal of multi-lingual learning has been to develop a universal cross-lingual model that can withstand the changes in multi-lingual data distributions. There has been a large amount of work to adapt such multi-lingual models…

Prompt-based continual learning methods effectively mitigate catastrophic forgetting. However, most existing methods assign a fixed set of prompts to each task, completely isolating knowledge across tasks and resulting in suboptimal…

Knowledge Tracing (KT) infers a student's knowledge state from past interactions to predict future performance. Conventional Deep Learning (DL)-based KT models are typically tied to platform-specific identifiers and latent representations,…

Machine learning has achieved remarkable success in many applications. However, existing studies are largely based on the closed-world assumption, which assumes that the environment is stationary, and the model is fixed once deployed. In…

Deep learning has become the workhorse for a wide range of natural language processing applications. But much of the success of deep learning relies on annotated examples. Annotation is time-consuming and expensive to produce at scale. Here…

Soft prompts have been recently proposed as a tool for adapting large frozen language models (LMs) to new tasks. In this work, we repurpose soft prompts to the task of injecting world knowledge into LMs. We introduce a method to train soft…