Related papers: PromptFusion: Decoupling Stability and Plasticity …

Quantum computers may outperform classical computers on machine learning tasks. In recent years, a variety of quantum algorithms promising unparalleled potential to enhance, speed up, or innovate machine learning have been proposed. Yet,…

Prompt learning is an effective paradigm that bridges gaps between the pre-training tasks and the corresponding downstream applications. Approaches based on this paradigm have achieved great transcendent results in various applications.…

Modern representation learning methods often struggle to adapt quickly under non-stationarity because they suffer from catastrophic forgetting and decaying plasticity. Such problems prevent learners from fast adaptation since they may…

This paper investigates the problem of data-driven modeling of port-Hamiltonian systems while preserving their intrinsic Hamiltonian structure and stability properties. We propose a novel neural-network-based port-Hamiltonian modeling…

Multimodal learning with incomplete modality is practical and challenging. Recently, researchers have focused on enhancing the robustness of pre-trained MultiModal Transformers (MMTs) under missing modality conditions by applying learnable…

Real-time semantic segmentation models offer an excellent balance between accuracy and inference speed. However, deploying these models in dynamic real world environments often requires the ability to learn novel classes incrementally…

Working with a non-stationary stream of data requires for the analysis system to evolve its model (the parameters as well as the structure) over time. In particular, concept drifts can occur, which makes it necessary to forget knowledge…

Continual learning (CL) empowers pre-trained vision-language models to adapt effectively to novel or previously underrepresented data distributions without comprehensive retraining, enhancing their adaptability and efficiency. While…

Recently, the use of bio-inspired learning techniques such as Hebbian learning and its closely-related Spike-Timing-Dependent Plasticity (STDP) variant have drawn significant attention for the design of compute-efficient AI systems that can…

Catastrophic forgetting is a challenge issue in continual learning when a deep neural network forgets the knowledge acquired from the former task after learning on subsequent tasks. However, existing methods try to find the joint…

Despite the demonstrated parameter efficiency of prompt-based fusion, its limited adaptivity and expressiveness hinder its effectiveness for multimodal applications at scale. In this paper, we present the first comprehensive study…

Significant advancements have been made in single label incremental learning (SLCIL),yet the more practical and challenging multi label class incremental learning (MLCIL) remains understudied. Recently,visual language models such as CLIP…

Custom Diffusion Models (CDMs) have gained significant attention due to their remarkable ability to personalize generative processes. However, existing CDMs suffer from catastrophic forgetting when continuously learning new concepts. Most…

The performance of Visio-Language Transformers drops sharply when an input modality (e.g., image) is missing, because the model is forced to make predictions using incomplete information. Existing missing-aware prompt methods help reduce…

The ability to continuously learn remains elusive for deep learning models. Unlike humans, models cannot accumulate knowledge in their weights when learning new tasks, mainly due to an excess of plasticity and the low incentive to reuse…

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…

Prompting a pretrained language model with natural language patterns has been proved effective for natural language understanding (NLU). However, our preliminary study reveals that manual discrete prompts often lead to unstable performance…

Prompt learning approaches have made waves in natural language processing by inducing better few-shot performance while they still follow a parametric-based learning paradigm; the oblivion and rote memorization problems in learning may…

With the emergence of large pre-trained vison-language model like CLIP, transferable representations can be adapted to a wide range of downstream tasks via prompt tuning. Prompt tuning tries to probe the beneficial information for…

General continual learning (GCL) is a broad concept to describe real-world continual learning (CL) problems, which are often characterized by online data streams without distinct transitions between tasks, i.e., blurry task boundaries. Such…