English
Related papers

Related papers: Consecutive Batch Model Editing with HooK Layers

200 papers

Standard approaches to sequential decision-making exploit an agent's ability to continually interact with its environment and improve its control policy. However, due to safety, ethical, and practicality constraints, this type of…

Machine Learning · Computer Science 2023-05-11 Patrick Emedom-Nnamdi , Abram L. Friesen , Bobak Shahriari , Nando de Freitas , Matt W. Hoffman

In the study of human learning, there is broad evidence that our ability to retain information improves with repeated exposure and decays with delay since last exposure. This plays a crucial role in the design of educational software,…

Artificial Intelligence · Computer Science 2016-06-09 Siddharth Reddy , Igor Labutov , Siddhartha Banerjee , Thorsten Joachims

Learning to collaborate with previously unseen partners is a fundamental generalization challenge in multi-agent learning, known as Ad Hoc Teamwork (AHT). Existing AHT approaches often adopt a two-stage pipeline, where first, a fixed…

Artificial Intelligence · Computer Science 2025-10-23 Caroline Wang , Arrasy Rahman , Jiaxun Cui , Yoonchang Sung , Peter Stone

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision-making,…

Continual learning (CL) aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information. CL faces the challenge of mitigating catastrophic forgetting while maintaining interpretability…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Lu Yu , Haoyu Han , Zhe Tao , Hantao Yao , Changsheng Xu

Deep learning has brought great progress for the sequential recommendation (SR) tasks. With advanced network architectures, sequential recommender models can be stacked with many hidden layers, e.g., up to 100 layers on real-world…

Information Retrieval · Computer Science 2021-05-13 Jiachun Wang , Fajie Yuan , Jian Chen , Qingyao Wu , Min Yang , Yang Sun , Guoxiao Zhang

Continual reinforcement learning poses a major challenge due to the tendency of agents to experience catastrophic forgetting when learning sequential tasks. In this paper, we introduce a modularity-based approach, called Hierarchical…

Machine Learning · Computer Science 2024-11-06 Thomas P Cannon , Özgür Simsek

Language models deployed in real-world systems often require post-hoc updates to incorporate new or corrected knowledge. However, editing such models efficiently and reliably-without retraining or forgetting previous information-remains a…

Computation and Language · Computer Science 2026-02-03 Ke Wang , Yiming Qin , Nikolaos Dimitriadis , Alessandro Favero , Pascal Frossard

In Continual Learning (CL), a model is required to learn a stream of tasks sequentially without significant performance degradation on previously learned tasks. Current approaches fail for a long sequence of tasks from diverse domains and…

Machine Learning · Computer Science 2023-05-29 Iordanis Fostiropoulos , Jiaye Zhu , Laurent Itti

Concept bottleneck models (CBM) aim to produce inherently interpretable models that rely on human-understandable concepts for their predictions. However, existing approaches to design interpretable generative models based on CBMs are not…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Akshay Kulkarni , Ge Yan , Chung-En Sun , Tuomas Oikarinen , Tsui-Wei Weng

The ability of intelligent agents to learn and remember multiple tasks sequentially is crucial to achieving artificial general intelligence. Many continual learning (CL) methods have been proposed to overcome catastrophic forgetting which…

Machine Learning · Computer Science 2020-09-15 Gehui Shen , Song Zhang , Xiang Chen , Zhi-Hong Deng

N-agent ad hoc teamwork (NAHT) is a newly introduced challenge in multi-agent reinforcement learning, where controlled subteams of varying sizes must dynamically collaborate with varying numbers and types of unknown teammates without…

Multiagent Systems · Computer Science 2025-10-21 Caroline Wang , Di Yang Shi , Elad Liebman , Ishan Durugkar , Arrasy Rahman , Peter Stone

We study the problem of optimizing biological sequences, e.g., proteins, DNA, and RNA, to maximize a black-box score function that is only evaluated in an offline dataset. We propose a novel solution, bootstrapped training of…

Quantitative Methods · Quantitative Biology 2024-03-26 Minsu Kim , Federico Berto , Sungsoo Ahn , Jinkyoo Park

Both the human brain and artificial learning agents operating in real-world or comparably complex environments are faced with the challenge of online model selection. In principle this challenge can be overcome: hierarchical Bayesian…

Machine Learning · Computer Science 2017-12-05 David G. Nagy , Gergő Orbán

The ability to train complex and highly effective models often requires an abundance of training data, which can easily become a bottleneck in cost, time, and computational resources. Batch active learning, which adaptively issues batched…

As new knowledge rapidly accumulates, language models (LMs) with pretrained knowledge quickly become obsolete. A common approach to updating LMs is fine-tuning them directly on new knowledge. However, recent studies have shown that…

Computation and Language · Computer Science 2025-02-28 Howard Chen , Jiayi Geng , Adithya Bhaskar , Dan Friedman , Danqi Chen

In continual learning, a model learns incrementally over time while minimizing interference between old and new tasks. One of the most widely used approaches in continual learning is referred to as replay. Replay methods support interleaved…

Computer Vision and Pattern Recognition · Computer Science 2024-05-13 Truman Hickok , Dhireesha Kudithipudi

We consider a sequential decision making problem where the agent faces the environment characterized by the stochastic discrete events and seeks an optimal intervention policy such that its long-term reward is maximized. This problem exists…

Machine Learning · Computer Science 2022-12-29 Chao Qu , Xiaoyu Tan , Siqiao Xue , Xiaoming Shi , James Zhang , Hongyuan Mei

We propose incremental (re)training of a neural network model to cope with a continuous flow of new data in inference during model serving. As such, this is a life-long learning process. We address two challenges of life-long retraining:…

Machine Learning · Computer Science 2020-04-30 Diego Klabjan , Xiaofeng Zhu

Prompting and fine-tuning have emerged as two competing paradigms for augmenting language models with new capabilities, such as the use of tools. Prompting approaches are quick to set up but rely on providing explicit demonstrations of each…

Computation and Language · Computer Science 2024-12-10 Damien de Mijolla , Wen Yang , Philippa Duckett , Christopher Frye , Mark Worrall