paper-with-me

홈 › Papers

BOWLL: A Deceptively Simple Open World Lifelong Learner

2024-02-07 · Roshni Kamath, Rupert Mitchell, Subarnaduti Paul, Kristian Kersting, Martin Mundt

The quest to improve scalar performance numbers on predetermined benchmarks seems to be deeply engraved in deep learning. However, the real world is seldom carefully curated and applications are seldom limited to excelling on test sets. A practical system is generally required to recognize novel concepts, refrain from actively including uninformative data, and retain previously acquired knowledge throughout its lifetime. Despite these key elements being rigorously researched individually, the study of their conjunction, open world lifelong learning, is only a recent trend. To accelerate this multifaceted field's exploration, we introduce its first monolithic and much-needed baseline. Leveraging the ubiquitous use of batch normalization across deep neural networks, we propose a deceptively simple yet highly effective way to repurpose standard models for open world lifelong learning. Through extensive empirical evaluation, we highlight why our approach should serve as a future standard for models that are able to effectively maintain their knowledge, selectively focus on informative data, and accelerate future learning.

📄 PDF Abstract BibTeX arXiv:2402.04814

Code (1)

ml-research/bowll 공식 구현 pytorch

Tasks

Lifelong learningNovel Concepts

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음
Focus 설명 없음

Similar Papers 제목 키워드 기반

Lifelong Learning with a Changing Action Set

2019-06-05 · Yash Chandak, Georgios Theocharous, Chris Nota, Philip S. Thomas

In many real-world sequential decision making problems, the number of available actions (decisions) can vary over time. While problems like catastrophic forgetting, changing transition dynamics, changing rewards function…

Decision MakingLifelong learningSequential Decision Making

Are We Ready for Service Robots? The OpenLORIS-Scene Datasets for Lifelong SLAM

2019-11-13 · Xuesong Shi, Dongjiang Li, Pengpeng Zhao, Qinbin Tian 외

Service robots should be able to operate autonomously in dynamic and daily changing environments over an extended period of time. While Simultaneous Localization And Mapping (SLAM) is one of the most fundamental problems…

BenchmarkingPose EstimationSimultaneous Localization and Mapping

Ella: Embodied Social Agents with Lifelong Memory

2025-06-30 · Hongxin Zhang, Zheyuan Zhang, Zeyuan Wang, Zunzhe Zhang 외

We introduce Ella, an embodied social agent capable of lifelong learning within a community in a 3D open world, where agents accumulate experiences and acquire knowledge through everyday visual observations and social in…

Lifelong learning

TANGO: Training-free Embodied AI Agents for Open-world Tasks

2024-12-05 · CVPR 2025 1 · Filippo Ziliotto, Tommaso Campari, Luciano Serafini, Lamberto Ballan

Large Language Models (LLMs) have demonstrated excellent capabilities in composing various modules together to create programs that can perform complex reasoning tasks on images. In this paper, we propose TANGO, an appro…

Embodied Question AnsweringObjectGoal NavigationPointGoal NavigationQuestion Answering

AllDayNav: Lifelong Navigation via Real-World Reinforcement Learning

2026-06-09 · Hang Yin, Yinan Liang, Jiazhao Zhang, Jiahang Liu 외 arxiv

Lifelong embodied navigation in dynamic environments requires robots to form persistent scene understanding from fragmentary observations, which remains difficult for existing methods that rely on explicit maps or scene …

Reinforcement LearningScene Understanding