相关论文: I2I: Initializing Adapters with Improvised Knowled…

Large language models (LLMs) can acquire new capabilities through fine-tuning, but continual adaptation often leads to catastrophic forgetting. We propose CRAFT, a continual learning framework that avoids updating model weights by instead…

Contrastive representation learning has emerged as a promising technique for continual learning as it can learn representations that are robust to catastrophic forgetting and generalize well to unseen future tasks. Previous work in…

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…

Improvisation training for actors presents unique challenges, particularly in maintaining narrative coherence and managing cognitive load during performances. Previous research on AI in improvisation performance often predates advances in…

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…

Instruction tuning (IT) achieves impressive zero-shot generalization results by training large language models (LLMs) on a massive amount of diverse tasks with instructions. However, how to select new tasks to improve the performance and…

Prompt-based continual learning provides a rehearsal-free solution by tuning small sets of parameters while keeping pre-trained models frozen. To meet the complex demands of sequential tasks, it is crucial to integrate task-specific…

Text-to-image (T2I) models are well known for their ability to produce highly realistic images, while multimodal large language models (MLLMs) are renowned for their proficiency in understanding and integrating multiple modalities. However,…

The goal of imitation learning is to mimic expert behavior from demonstrations, without access to an explicit reward signal. A popular class of approach infers the (unknown) reward function via inverse reinforcement learning (IRL) followed…

Continual learning, also known as lifelong learning or incremental learning, refers to the process by which a model learns from a stream of incoming data over time. A common problem in continual learning is the classification layer's bias…

Most artificial intelligence models have limiting ability to solve new tasks faster, without forgetting previously acquired knowledge. The recently emerging paradigm of continual learning aims to solve this issue, in which the model learns…

Traditional Incremental Learning (IL) targets to handle sequential fully-supervised learning problems where novel classes emerge from time to time. However, due to inherent annotation uncertainty and ambiguity, collecting high-quality…

Imitation Learning is a sequential task where the learner tries to mimic an expert's action in order to achieve the best performance. Several algorithms have been proposed recently for this task. In this project, we aim at proposing a wide…

Continual learning aims to learn knowledge of tasks observed in sequential time steps while mitigating the forgetting of previously learned knowledge. Existing methods were designed to learn a single modality (e.g., image) over time, which…

This paper introduces Prompt-to-Primal (P2P) Teaching, an AI-integrated instructional approach that links prompt-driven exploration with first-principles reasoning, guided and moderated by the instructor within the classroom setting. In P2P…

Advanced life forms, sustained by the synergistic interaction of neural cognitive mechanisms, continually acquire and transfer knowledge throughout their lifespan. In contrast, contemporary machine learning paradigms exhibit limitations in…

In-context Learning (ICL) empowers large language models (LLMs) to swiftly adapt to unseen tasks at inference-time by prefixing a few demonstration examples before queries. Despite its versatility, ICL incurs substantial computational and…

Text-to-image (T2I) generation has greatly enhanced creative expression, yet achieving preference-aligned generation in a real-time and training-free manner remains challenging. Previous methods often rely on static, pre-collected…

Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This…

Imitation learning aims to mimic the behavior of experts without explicit reward signals. Passive imitation learning methods which use static expert datasets typically suffer from compounding error, low sample efficiency, and high…