Related papers: P2L-CA: An Effective Parameter Tuning Framework fo…

A fundamental requirement for intelligent systems is the ability to learn continuously under changing environments. However, models trained in this regime often suffer from catastrophic forgetting. Leveraging pre-trained models has recently…

Parameter-efficient transfer learning (PETL) aims to reduce the scales of pretrained models for multiple downstream tasks. However, as the models keep scaling up, the memory footprint of existing PETL methods is not significantly reduced…

The emergence of in-context learning (ICL) enables large pre-trained language models (PLMs) to make predictions for unseen inputs without updating parameters. Despite its potential, ICL's effectiveness heavily relies on the quality,…

Long input sequences are central to in-context learning, document understanding, and multi-step reasoning of Large Language Models (LLMs). However, the quadratic attention cost of Transformers makes inference memory-intensive and slow.…

In-context learning (ICL) leverages in-context examples as prompts for the predictions of Large Language Models (LLMs). These prompts play a crucial role in achieving strong performance. However, the selection of suitable prompts from a…

Despite the critical importance of the medical domain in Deep Learning, most of the research in this area solely focuses on training models in static environments. It is only in recent years that research has begun to address dynamic…

The partial label challenge in Multi-Label Class-Incremental Learning (MLCIL) arises when only the new classes are labeled during training, while past and future labels remain unavailable. This issue leads to a proliferation of…

Continual instruction tuning enables large language models (LLMs) to learn incrementally while retaining past knowledge, whereas existing methods primarily focus on how to retain old knowledge rather than on selecting which new knowledge to…

Multi-label (ML) data deals with multiple classes associated with individual samples at the same time. This leads to the co-occurrence of several classes repeatedly, which indicates some existing correlation among them. In this article, the…

Text-based person retrieval aims to identify specific individuals within an image database using textual descriptions. Due to the high cost of annotation and privacy protection, researchers resort to synthesized data for the paradigm of…

Diffusion models have become a powerful backbone for text-to-image generation, producing high-quality visuals from natural language prompts. However, when prompts involve multiple objects alongside global or local style instructions, the…

Complementary-label learning (CLL) is a weakly supervised paradigm where instances are labeled with classes they do not belong to. Despite a decade of research, CLL methods remain competitive mainly on 10-class classification, with scaling…

Convolutional Dictionary Learning (CDL) has emerged as a powerful approach for signal representation by learning translation-invariant features through convolution operations. While existing CDL methods are predominantly designed and used…

Partial label learning is a prominent weakly supervised classification task, where each training instance is ambiguously labeled with a set of candidate labels. In real-world scenarios, candidate labels are often influenced by instance…

Multi-label image classification aims to predict all possible labels in an image. It is usually formulated as a partial-label learning problem, given the fact that it could be expensive in practice to annotate all labels in every training…

Recent years have witnessed increasing interests in prompt-based learning in which models can be trained on only a few annotated instances, making them suitable in low-resource settings. When using prompt-based learning for text…

Continual learning (CL) aims to incrementally train a model on a sequence of tasks while retaining performance on prior ones. However, storing and replaying data is often infeasible due to privacy or security constraints and impractical for…

Continual learning (CL) aims to train models that can learn a sequence of tasks without forgetting previously acquired knowledge. A core challenge in CL is balancing stability -- preserving performance on old tasks -- and plasticity --…

The goal of meta-learning is to learn to adapt to a new task with only a few labeled examples. To tackle this problem in NLP, we propose $\textit{in-context tuning}$, which recasts adaptation and prediction as a simple sequence prediction…

Previous work on augmenting large multimodal models (LMMs) for text-to-image (T2I) generation has focused on enriching the input space of in-context learning (ICL). This includes providing a few demonstrations and optimizing image…