Introducing Nested Learning: A new ML paradigm for continual learning

Fleetwood on Twitter / X

Studying continual learning at the moment, best papers thus far:https://t.co/Y9oXBAiyj2https://t.co/ByWlaF3ncnhttps://t.co/hG0XIzq6cHhttps://t.co/5VSEnBIkX2— Fleetwood (@fleetwood___) April 11, 2026

The huge potential implications of long-context inference

Continual learning, scaling RL, and research feedback loops

The Continual Learning Problem

A perspective on continual learning, motivating our paper on sparse memory finetuning

A Comprehensive Survey of Continual Learning: Theory, Method and Application

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 develop themselves adaptively. In a general sense, continual learning is explicitly limited by catastrophic forgetting, where learning a new task usually results in a dramatic performance degradation of the old tasks. Beyond this, increasingly numerous advances have emerged in recent years that largely extend the understanding and application of continual learning. The growing and widespread interest in this direction demonstrates its realistic significance as well as complexity. In this work, we present a comprehensive survey of continual learning, seeking to bridge the basic settings, theoretical foundations, representative methods, and practical applications. Based on existing theoretical and empirical results, we summarize the general objectives of continual learning as ensuring a proper stability-plasticity trade-off and an adequate intra/inter-task generalizability in the context of resource efficiency. Then we provide a state-of-the-art and elaborated taxonomy, extensively analyzing how representative methods address continual learning, and how they are adapted to particular challenges in realistic applications. Through an in-depth discussion of promising directions, we believe that such a holistic perspective can greatly facilitate subsequent exploration in this field and beyond.

Large-Scale Study of Curiosity-Driven Learning

Burda*, Edwards*, Pathak* et.al. (* equal contribution, alphabetical order) Large-Scale Study of Curiosity-Driven Learning. 2018.

Titans + MIRAS: Helping AI have long-term memory

Ali Behrouz, Student Researcher, Meisam Razaviyayn, Staff Researcher, and Vahab Mirrokni, VP and Google Fellow, Google Research

Experimental Evidence on the Learning Impact of Generative AI

We study whether access to off-the-shelf generative AI changes how much students learn in a timed assignment. In a proctored, in-person randomized experiment, undergraduates study an unfamiliar topic and write an essay with or without AI, then complete unaided assessments immediately and one week later. AI access raises test scores, and a smaller gain persists a week later. Gains remain for students who use AI as a tutor ("augmentation") and fade for students who have AI write for them ("automation"). We document two mechanisms: students shift time from writing toward reading and searching for information, and report greater learning enjoyment.

Learning in the Open: What AI Is (and Isn’t) Changing

Khan Academy shares what’s working with AI tutoring, what isn’t, and what we’ve learned from Khanmigo to better support student learning.

Introducing beginners to the mechanics of machine learning – Miriam Posner

Every year, I spend some time introducing students to the mechanics of machine learning with neural nets. I definitely don’t go into great depth; I usually only have one class for this. But I try to unpack at least some of the major concepts, so that ML isn’t quite such a black box.

Learning to Learn: You, Too, Can Rewire Your Brain (Published 2017)

How an engineering professor who “flunked my way” through high school math and science went on to create the world’s most popular online course.

The Buffett Formula: Going to Bed Smarter Than When You Woke Up

Learn how Warren Buffett and Charlie Munger turn curiosity into insight. Discover how interest-driven learning builds understanding and reveals hidden opportunities.

How Learning Happens | Seminal Works in Educational Psychology and Wha

How Learning Happens introduces 28 giants of educational research and their findings on how we learn and what we need to learn effectively, efficiently, and

How to keep learning in the age of LLMs | Oğuzhan Olguncu

Notes on how I keep learning as a programmer in the age of LLMs

ChatGPT as a cognitive crutch: Evidence from a randomized controlled trial on knowledge retention

The rapid integration of generative artificial intelligence into higher education has outpaced empirical understanding of its effects on fundamental learning processes. To address this gap, this randomized controlled trial (n = 120) tested ChatGPT's impact on long-term knowledge retention in undergraduates learning AI. Participants were randomly assigned either to use ChatGPT as a study aid (AI-Assisted Group) or to use only traditional, non-AI study methods (traditional learning group). Knowledge retention was assessed with a surprise test 45 days after learning. Students who used ChatGPT scored significantly lower on the retention test (57.5 % correct) compared to those who studied traditionally (68.5 % correct), t (83) = −3.19, p = .002, Cohen's d = 0.68. This suggests that unrestricted ChatGPT use impaired long-term retention, likely by reducing the cognitive effort that supports durable memory. The findings align with cognitive offloading theory and the ‘desirable difficulties’ principle: while AI assistance may ease initial learning, it appears to undermine the effortful processes needed for robust learning. These results have important implications for how generative AI tools should be integrated into higher education.

huggingface/ml-intern

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models