相关论文: Modality-Inconsistent Continual Learning of Multim…

Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to…

Language models (LMs) exhibit impressive performance and generalization capabilities. However, LMs struggle with the persistent challenge of catastrophic forgetting, which undermines their long-term sustainability in continual learning…

Most existing works on continual learning (CL) focus on overcoming the catastrophic forgetting (CF) problem, with dynamic models and replay methods performing exceptionally well. However, since current works tend to assume exclusivity or…

Missing modality issues are common in real-world applications, arising from factors such as equipment failures and privacy concerns. When fine-tuning pre-trained models on downstream datasets with missing modalities, performance can degrade…

Large language-vision models (LVLMs) such as CLIP, Flamingo, and BLIP have revolutionized AI by enabling understanding across textual and visual modalities. These models excel at tasks like image captioning, visual question answering, and…

Continual learning focuses on incrementally training a model on a sequence of tasks with the aim of learning new tasks while minimizing performance drop on previous tasks. Existing approaches at the intersection of Continual Learning and…

New categories may be introduced over time, or existing categories may need to be reclassified. Class incremental learning (CIL) is employed for the gradual acquisition of knowledge about new categories while preserving information about…

Multimodal incremental learning needs to digest the information from multiple modalities while concurrently learning new knowledge without forgetting the previously learned information. There are numerous challenges for this task, mainly…

Motivated by in-context learning (ICL) capabilities of Large Language Models (LLMs), multimodal LLMs with additional visual modality are also exhibited with similar ICL abilities when multiple image-text pairs are provided as…

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…

User modeling in large e-commerce platforms aims to optimize user experiences by incorporating various customer activities. Traditional models targeting a single task often focus on specific business metrics, neglecting the comprehensive…

Conventional deep learning models have limited capacity in learning multiple tasks sequentially. The issue of forgetting the previously learned tasks in continual learning is known as catastrophic forgetting or interference. When the input…

In-Context Learning (ICL) is a significant paradigm for Large Multimodal Models (LMMs), using a few in-context demonstrations (ICDs) for new task adaptation. However, its performance is sensitive to demonstration configurations and…

Multimodal Biomedical Image Incremental Learning (MBIIL) is essential for handling diverse tasks and modalities in the biomedical domain, as training separate models for each modality or task significantly increases inference costs.…

Large language models (LLMs) and multimodal models (MMs) have exhibited impressive capabilities in various domains, particularly in general language understanding and visual reasoning. However, these models, trained on massive data, may not…

Large Language Models (LLMs) with in-context learning (ICL) ability can quickly adapt to a specific context given a few demonstrations (demos). Recently, Multimodal Large Language Models (MLLMs) built upon LLMs have also shown multimodal…

Continual learning is essential for adapting models to new tasks while retaining previously acquired knowledge. While existing approaches predominantly focus on uni-modal data, multi-modal learning offers substantial benefits by utilizing…

Continual learning (CL) aims to constantly learn new knowledge over time while avoiding catastrophic forgetting on old tasks. We focus on continual text classification under the class-incremental setting. Recent CL studies have identified…

In-Context Learning (ICL) enhances the performance of large language models (LLMs) with demonstrations. However, obtaining these demonstrations primarily relies on manual effort. In most real-world scenarios, users are often unwilling or…

State-of-the-art Vision-Language Models (VLMs) ground the vision and the language modality primarily via projecting the vision tokens from the encoder to language-like tokens, which are directly fed to the Large Language Model (LLM)…