相关论文: SEAL: Searching Expandable Architectures for Incre…

Knowledge-based conversational question answering (KBCQA) confronts persistent challenges in resolving coreference, modeling contextual dependencies, and executing complex logical reasoning. Existing approaches often suffer from…

Task-incremental learning involves the challenging problem of learning new tasks continually, without forgetting past knowledge. Many approaches address the problem by expanding the structure of a shared neural network as tasks arrive, but…

Adversarial Imitation Learning (AIL) is a broad family of imitation learning methods designed to mimic expert behaviors from demonstrations. While AIL has shown state-of-the-art performance on imitation learning with only small number of…

The objective of this internship is to propose an innovative method that uses unlabelled data, i.e. data that will allow the AI to automatically learn to predict the correct outcome. To reach this stage, the steps to be followed can be…

The neural architecture search (NAS) algorithm with reinforcement learning can be a powerful and novel framework for the automatic discovering process of neural architectures. However, its application is restricted by noncontinuous and…

The ability to learn in dynamic, nonstationary environments without forgetting previous knowledge, also known as Continual Learning (CL), is a key enabler for scalable and trustworthy deployments of adaptive solutions. While the importance…

Imitation learning has been a trend recently, yet training a generalist agent across multiple tasks still requires large-scale expert demonstrations, which are costly and labor-intensive to collect. To address the challenge of limited…

Numerous noise adaptation techniques have been proposed to fine-tune deep-learning models in speech enhancement (SE) for mismatched noise environments. Nevertheless, adaptation to a new environment may lead to catastrophic forgetting of the…

Non-exhaustive learning (NEL) is an emerging machine-learning paradigm designed to confront the challenge of non-stationary environments characterized by anon-exhaustive training sets lacking full information about the available…

Siamese networks are one of the most trending methods to achieve self-supervised visual representation learning (SSL). Since hand labeling is costly, SSL can play a crucial part by allowing deep learning to train on large unlabeled…

Single Image Super-Resolution (SISR) tasks have achieved significant performance with deep neural networks. However, the large number of parameters in CNN-based met-hods for SISR tasks require heavy computations. Although several efficient…

The paper provides a comprehensive overview of Neural Architecture Search (NAS), emphasizing its evolution from manual design to automated, computationally-driven approaches. It covers the inception and growth of NAS, highlighting its…

Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Despite the strong performance of Pre-Trained Models (PTMs) in CIL, a critical issue persists: learning new classes often…

This paper studies the challenging continual learning (CL) setting of Class Incremental Learning (CIL). CIL learns a sequence of tasks consisting of disjoint sets of concepts or classes. At any time, a single model is built that can be…

Large language models (LLMs) have been significantly improved by instruction fine-tuning, but still lack transparency and the ability to utilize up-to-date knowledge and information. In this work, we propose search-augmented instruction…

The current dominant paradigm when building a machine learning model is to iterate over a dataset over and over until convergence. Such an approach is non-incremental, as it assumes access to all images of all categories at once. However,…

In long structured document retrieval, existing methods typically fine-tune pre-trained language models (PLMs) using contrastive learning on datasets lacking explicit structural information. This practice suffers from two critical issues:…

In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine…

While many advanced LLMs are designed to handle long sequence data, we can still observe notable quality degradation even within the sequence limit. In this work, we introduce a novel approach called Scaling to Emphasize Attention for…

Neural Architecture Search (NAS) is a collection of methods to craft the way neural networks are built. Current NAS methods are far from ab initio and automatic, as they use manual backbone architectures or micro building blocks (cells),…