Related papers: Lifelong Learning with Task-Specific Adaptation: A…
Lifelong learning is critical for embodied agents in open-world environments, where reinforcement learning fine-tuning has emerged as an important paradigm to enable Vision-Language-Action (VLA) models to master dexterous manipulation…
Lifelong Reinforcement Learning (LRL) holds significant potential for addressing sequential tasks, but it still faces considerable challenges. A key difficulty lies in effectively preventing catastrophic forgetting and facilitating…
Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…
World model based reinforcement learning (RL) has emerged as a promising approach for autonomous driving, which learns a latent dynamics model and uses it to train a planning policy. To speed up the learning process, the pretrain-finetune…
Navigating multiple tasks$\unicode{x2014}$for instance in succession as in continual or lifelong learning, or in distributions as in meta or multi-task learning$\unicode{x2014}$requires some notion of adaptation. Evolution over timescales…
Activation steering has emerged as a promising approach for efficiently adapting large language models (LLMs) to downstream behaviors. However, most existing steering methods rely on a single static direction per task or concept, making…
Reinforcement learning (RL) faces substantial challenges when applied to real-life problems, primarily stemming from the scarcity of available data due to limited interactions with the environment. This limitation is exacerbated by the fact…
Continual learning (CL) enables models to adapt to evolving data streams. A major challenge of CL is catastrophic forgetting, where new knowledge will overwrite previously acquired knowledge. Traditional methods usually retain the past data…
Federated Parameter-Efficient Fine-Tuning (Fed-PEFT) enables lightweight adaptation of large pre-trained models in federated learning settings by updating only a small subset of parameters. However, Fed-PEFT methods typically assume a fixed…
Continual learning (CL) is essential for Large Language Models (LLMs) to adapt to evolving real-world demands, yet they are susceptible to catastrophic forgetting (CF). While traditional CF solutions rely on expensive data rehearsal, recent…
Alignment plays a crucial role in Large Language Models (LLMs) in aligning with human preferences on a specific task/domain. Traditional alignment methods suffer from catastrophic forgetting, where models lose previously acquired knowledge…
To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as continual learning, provides a foundation for AI systems to…
Linear attention offers a linear-time alternative to self-attention but often struggles to capture long-range patterns. We revisit linear attention through a prediction-correction lens and show that prevalent variants can be written as a…
This paper introduces a new lifelong learning solution where a single model is trained for a sequence of tasks. The main challenge that vision systems face in this context is catastrophic forgetting: as they tend to adapt to the most…
Intelligent agents should have the ability to leverage knowledge from previously learned tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have emerged as a popular solution to achieve this. However,…
Adversarial attacks pose a significant threat to the reliability of pre-trained language models (PLMs) such as GPT, BERT, RoBERTa, and T5. This paper presents Adversarial Robustness through Dynamic Ensemble Learning (ARDEL), a novel scheme…
While vision-and-language models significantly advance in many fields, the challenge of continual learning is unsolved. Parameter-efficient modules like adapters and prompts present a promising way to alleviate catastrophic forgetting.…
The pretrain-then-finetune paradigm has been widely used in various unimodal and multimodal tasks. However, finetuning all the parameters of a pre-trained model becomes prohibitive as the model size grows exponentially. To address this…
Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting-a critical limitation of the static…
This paper addresses the issues of parameter redundancy, rigid structure, and limited task adaptability in the fine-tuning of large language models. It proposes an adapter-based fine-tuning method built on a structure-learnable mechanism.…