paper-with-me

Papers

Streaming Continual Learning for Unified Adaptive Intelligence in Dynamic Environments

2026-03-02 · Federico Giannini, Giacomo Ziffer, Andrea Cossu, Vincenzo Lomonaco arxiv

Developing effective predictive models becomes challenging in dynamic environments that continuously produce data and constantly change. Continual Learning (CL) and Streaming Machine Learning (SML) are two research areas that tackle this arduous task. We put forward a unified setting that harnesses the benefits of both CL and SML: their ability to quickly adapt to non-stationary data streams without forgetting previous knowledge. We refer to this setting as Streaming Continual Learning (SCL). SCL does not replace either CL or SML. Instead, it extends the techniques and approaches considered by both fields. We start by briefly describing CL and SML and unifying the languages of the two frameworks. We then present the key features of SCL. We finally highlight the importance of bridging the two communities to advance the field of intelligent systems.

📄 PDF Abstract BibTeX arXiv:2603.01695

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Keep It in Mind: User Centric Continual Spatial Intelligence Reasoning in Egocentric Video Streams

2026-06-13 · Yun Wang, Junbin Xiao, Han Lyu, Yifan Wang 외 arxiv

We introduce UCS-Bench, a dataset spanning 170+ hours of egocentric visual observations with 8.1K+ timestamped questions for diagnosing User-Centric Continual Spatial intelligence in egocentric video streams. UCS-Bench t…

Spatial Reasoning

From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models

2026-03-04 · Junlong Tong, Zilong Wang, YuJie Ren, Peiran Yin 외 arxiv

Standard Large Language Models (LLMs) are predominantly designed for static inference with pre-defined inputs, which limits their applicability in dynamic, real-time scenarios. To address this gap, the streaming LLM para…

CREAM: Continual Retrieval on Dynamic Streaming Corpora with Adaptive Soft Memory

2026-01-06 · HuiJeong Son, Hyeongu Kang, Sunho Kim, Subeen Ho 외 arxiv

Information retrieval (IR) in dynamic data streams is a crucial task, as shifts in data distribution degrade the performance of AI-powered IR systems. To mitigate this issue, memory-based continual learning has been wide…

Information RetrievalContinual Learning

CLeAN: Continual Learning Adaptive Normalization in Dynamic Environments

2026-03-18 · Isabella Marasco, Davide Evangelista, Elena Loli Piccolomini, Michele Colajanni arxiv

Artificial intelligence systems predominantly rely on static data distributions, making them ineffective in dynamic real-world environments, such as cybersecurity, autonomous transportation, or finance, where data shifts…

Continual Learning

Degradation of Feature Space in Continual Learning

2026-02-06 · Chiara Lanza, Roberto Pereira, Marco Miozzo, Eduard Angelats 외 arxiv

Centralized training is the standard paradigm in deep learning, enabling models to learn from a unified dataset in a single location. In such setup, isotropic feature distributions naturally arise as a mean to support we…

Continual Learning