English
Related papers

Related papers: IBCL: Zero-shot Model Generation for Task Trade-of…

200 papers

We formulate the continual learning (CL) problem via dynamic programming and model the trade-off between catastrophic forgetting and generalization as a two-player sequential game. In this approach, player 1 maximizes the cost due to lack…

Machine Learning · Computer Science 2022-02-25 Krishnan Raghavan , Prasanna Balaprakash

Reward models are central to aligning language models with human preferences via reinforcement learning (RL). As RL is increasingly applied to settings such as verifiable rewards and multi-objective alignment, RMs are expected to encode…

Machine Learning · Computer Science 2026-05-21 Jiwoo Hong , Shao Tang , Zhipeng Wang

Large pre-trained sequence models, such as transformer-based architectures, have been recently shown to have the capacity to carry out in-context learning (ICL). In ICL, a decision on a new input is made via a direct mapping of the input…

Information Theory · Computer Science 2024-01-23 Matteo Zecchin , Kai Yu , Osvaldo Simeone

We provide causal mechanistic validation that in-context learning (ICL) decomposes into two separable mechanisms: Task Schema (abstract task type recognition) and Binding (specific input-output associations). Through activation patching…

Machine Learning · Computer Science 2025-12-22 Chaeha Kim

In learning-to-learn the goal is to infer a learning algorithm that works well on a class of tasks sampled from an unknown meta distribution. In contrast to previous work on batch learning-to-learn, we consider a scenario where tasks are…

Machine Learning · Statistics 2018-03-23 Giulia Denevi , Carlo Ciliberto , Dimitris Stamos , Massimiliano Pontil

While tasks could come with varying the number of instances and classes in realistic settings, the existing meta-learning approaches for few-shot classification assume that the number of instances per task and class is fixed. Due to such…

Machine Learning · Computer Science 2022-02-15 Hae Beom Lee , Hayeon Lee , Donghyun Na , Saehoon Kim , Minseop Park , Eunho Yang , Sung Ju Hwang

Continual learning (CL) aims to train deep neural networks efficiently on streaming data while limiting the forgetting caused by new tasks. However, learning transferable knowledge with less interference between tasks is difficult, and…

Machine Learning · Computer Science 2023-10-31 Saurav Jha , Dong Gong , He Zhao , Lina Yao

Learning invariant representations is a critical first step in a number of machine learning tasks. A common approach corresponds to the so-called information bottleneck principle in which an application dependent function of mutual…

Machine Learning · Computer Science 2021-02-17 Aditya Kumar Akash , Vishnu Suresh Lokhande , Sathya N. Ravi , Vikas Singh

Continual learning (CL) can help pre-trained vision-language models efficiently adapt to new or under-trained data distributions without re-training. Nevertheless, during the continual training of the Contrastive Language-Image Pre-training…

Computer Vision and Pattern Recognition · Computer Science 2023-08-14 Zangwei Zheng , Mingyuan Ma , Kai Wang , Ziheng Qin , Xiangyu Yue , Yang You

Continual learning aims to learn new tasks without forgetting previously learned ones. This is especially challenging when one cannot access data from previous tasks and when the model has a fixed capacity. Current regularization-based…

Machine Learning · Computer Science 2020-02-21 Sayna Ebrahimi , Mohamed Elhoseiny , Trevor Darrell , Marcus Rohrbach

In-context learning (ICL) empowers generative models to address new tasks effectively and efficiently on the fly, without relying on any artificially crafted optimization techniques. In this paper, we study extending ICL to address a…

Artificial Intelligence · Computer Science 2024-09-13 Fan Wang , Chuan Lin , Yang Cao , Yu Kang

Fine-tuning and in-context learning (ICL) are two prevalent methods in imbuing large language models with task-specific knowledge. It is commonly believed that fine-tuning can surpass ICL given sufficient training samples as it allows the…

Machine Learning · Computer Science 2024-10-08 Qingyu Yin , Xuzheng He , Luoao Deng , Chak Tou Leong , Fan Wang , Yanzhao Yan , Xiaoyu Shen , Qiang Zhang

We propose bookworm continual learning(BCL), a flexible setting where unseen classes can be inferred via a semantic model, and the visual model can be updated continually. Thus BCL generalizes both continual learning (CL) and zero-shot…

Computer Vision and Pattern Recognition · Computer Science 2020-08-21 Kai Wang , Luis Herranz , Anjan Dutta , Joost van de Weijer

Deep reinforcement learning (RL) is a powerful approach to complex decision making. However, one issue that limits its practical application is its brittleness, sometimes failing to train in the presence of small changes in the environment.…

Machine Learning · Computer Science 2025-01-27 Jung-Hoon Cho , Vindula Jayawardana , Sirui Li , Cathy Wu

In Continual Learning (CL), a neural network is trained on a stream of data whose distribution changes over time. In this context, the main problem is how to learn new information without forgetting old knowledge (i.e., Catastrophic…

Continual learning (CL) aims to train models sequentially on multiple tasks while mitigating catastrophic forgetting of previously learned knowledge. Recent advances in large pre-trained models (LPMs) and model merging techniques, such as…

Machine Learning · Computer Science 2026-05-21 Kei Hiroshima , Kento Uchida , Shinichi Shirakawa

In-Context Learning (ICL) empowers Large Language Models (LLMs) for rapid task adaptation without Fine-Tuning (FT), but its reliance on demonstration selection remains a critical challenge. While many-shot ICL shows promising performance…

Computation and Language · Computer Science 2025-06-06 Jianfei Zhang , Bei Li , Jun Bai , Rumei Li , Yanmeng Wang , Chenghua Lin , Wenge Rong

Continual Learning (CL) aims to sequentially train models on streams of incoming data that vary in distribution by preserving previous knowledge while adapting to new data. Current CL literature focuses on restricted access to previously…

We present the problem of inverse constraint learning (ICL), which recovers constraints from demonstrations to autonomously reproduce constrained skills in new scenarios. However, ICL suffers from an ill-posed nature, leading to inaccurate…

Robotics · Computer Science 2023-12-11 Jaehwi Jang , Minjae Song , Daehyung Park

In-Context Learning (ICL) enables pretrained LLMs to adapt to downstream tasks by conditioning on a small set of input-output demonstrations, without any parameter updates. Although there have been many theoretical efforts to explain how…

Machine Learning · Computer Science 2026-03-23 Xuhan Tong , Yuchen Zeng , Jiawei Zhang