English
Related papers

Related papers: Learning $\textit{Ex Nihilo}$

200 papers

Learning Analytics (LA) has rapidly expanded through practical and technological innovation, yet its foundational identity has remained theoretically under-specified. This paper addresses this gap by proposing the first axiomatic theory…

Computers and Society · Computer Science 2025-12-12 Kensuke Takii , Changhao Liang , Hiroaki Ogata

In this paper, we make a bold attempt toward an ambitious task: given a pre-trained classifier, we aim to reconstruct an image generator, without relying on any data samples. From a black-box perspective, this challenge seems intractable,…

Machine Learning · Computer Science 2023-12-06 Runpeng Yu , Xinchao Wang

Closed-loop learning is the process of repeatedly estimating a model from data generated from the model itself. It is receiving great attention due to the possibility that large neural network models may, in the future, be primarily trained…

Machine Learning · Computer Science 2025-07-10 Fariba Jangjoo , Matteo Marsili , Yasser Roudi

Does RL teach LLMs genuinely new skills, or does it merely activate existing ones? This question lies at the core of ongoing debates about the role of RL in LLM post-training. On one side, strong empirical results can be achieved with RL…

Artificial Intelligence · Computer Science 2025-12-22 Lifan Yuan , Weize Chen , Yuchen Zhang , Ganqu Cui , Hanbin Wang , Ziming You , Ning Ding , Zhiyuan Liu , Maosong Sun , Hao Peng

LLM unlearning is a technique to remove the impacts of undesirable knowledge from the model without retraining from scratch, which is indispensable towards trustworthy AI. Existing unlearning methods face significant limitations:…

Machine Learning · Computer Science 2026-03-02 Yisheng Zhong , Zhengbang Yang , Zhuangdi Zhu

Machine learning (ML) in its current form implies that an answer to any problem can be well approximated by a function of a very peculiar form: a specially adjusted iteration of Heavyside theta-functions. It is natural to ask if the answers…

High Energy Physics - Theory · Physics 2023-04-05 V. Dolotin , A. Morozov , A. Popolitov

Training sophisticated agents for optimal decision-making under uncertainty has been key to the rapid development of modern autonomous systems across fields. Notably, model-free reinforcement learning (RL) has enabled decision-making agents…

Machine Learning · Computer Science 2025-07-21 Thomas Banker , Ali Mesbah

Compute scaling for language model (LM) pretraining has outpaced the growth of human-written texts, leading to concerns that data will become the bottleneck to LM scaling. To continue scaling pretraining in this data-constrained regime, we…

Machine Learning · Computer Science 2025-09-30 Yangjun Ruan , Neil Band , Chris J. Maddison , Tatsunori Hashimoto

Machine learning is at the heart of managing the real-world problems associated with massive data. With the success of neural networks on such large-scale problems, more research in machine learning is being conducted now than ever before.…

Machine Learning · Computer Science 2026-02-23 Ryan O'Dowd

Visual reasoning is crucial for understanding complex multimodal data and advancing Artificial General Intelligence. Existing methods enhance the reasoning capability of Multimodal Large Language Models (MLLMs) through Reinforcement…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Chaoyang Wang , Zeyu Zhang , Meng Meng , Xu Zhou , Haiyun Jiang

The advances in deep learning have enabled machine learning methods to outperform human beings in various areas, but it remains a great challenge for a well-trained model to quickly adapt to a new task. One promising solution to realize…

Machine Learning · Computer Science 2023-04-11 Shengyu Feng , Hanghang Tong

Since the advent of Large Language Models (LLMs), efforts have largely focused on improving their instruction-following and deductive reasoning abilities, leaving open the question of whether these models can truly discover new knowledge.…

Computation and Language · Computer Science 2025-10-31 Kaiyu He , Zhiyu Chen

For a long time, machine learning (ML) has been seen as the abstract problem of learning relationships from data independent of the surrounding settings. This has recently been challenged, and methods have been proposed to include external…

Machine Learning · Computer Science 2023-02-08 Sebastian Scher , Bernhard Geiger , Simone Kopeinik , Andreas Trügler , Dominik Kowald

The black-box nature of neural models has motivated a line of research that aims to generate natural language rationales to explain why a model made certain predictions. Such rationale generation models, to date, have been trained on…

Computation and Language · Computer Science 2020-12-16 Faeze Brahman , Vered Shwartz , Rachel Rudinger , Yejin Choi

Zero-shot learning (ZSL) aims at understanding unseen categories with no training examples from class-level descriptions. To improve the discriminative power of zero-shot learning, we model the visual learning process of unseen categories…

Computer Vision and Pattern Recognition · Computer Science 2019-12-04 Mohamed Elhoseiny , Mohamed Elfeki

Inspired by Bayesian approaches to brain function in neuroscience, we give a simple theory of probabilistic inference for a unified account of reasoning and learning. We simply model how data cause symbolic knowledge in terms of its…

Artificial Intelligence · Computer Science 2024-02-15 Hiroyuki Kido

We address the main problem of self-learning LLM: the question of what to learn. We propose a self-learning LLM framework that enables an LLM to independently learn previously unknown knowledge through self-assessment of their own…

Artificial Intelligence · Computer Science 2024-11-13 Teddy Ferdinan , Jan Kocoń , Przemysław Kazienko

This paper proposes a new approach to Machine Learning (ML) that focuses on unsupervised continuous context-dependent learning of complex patterns. Although the proposal is partly inspired by some of the current knowledge about the…

Neural and Evolutionary Computing · Computer Science 2024-05-07 Valentin Puente Varona

In this paper we consider a version of the zero-shot learning problem where seen class source and target domain data are provided. The goal during test-time is to accurately predict the class label of an unseen target domain instance based…

Computer Vision and Pattern Recognition · Computer Science 2015-09-29 Ziming Zhang , Venkatesh Saligrama

Scaling large language models (LLMs) leads to an emergent capacity to learn in-context from example demonstrations. Despite progress, theoretical understanding of this phenomenon remains limited. We argue that in-context learning relies on…

Computation and Language · Computer Science 2023-03-15 Michael Hahn , Navin Goyal