English
Related papers

Related papers: Operationalising the Superficial Alignment Hypothe…

200 papers

Multitask learning is a framework that enforces multiple learning tasks to share knowledge to improve their generalization abilities. While shallow multitask learning can learn task relations, it can only handle predefined features. Modern…

Machine Learning · Computer Science 2022-07-05 Guangji Bai , Liang Zhao

It is commonly believed that networks cannot be both accurate and robust, that gaining robustness means losing accuracy. It is also generally believed that, unless making networks larger, network architectural elements would otherwise…

Machine Learning · Computer Science 2021-07-13 Cihang Xie , Mingxing Tan , Boqing Gong , Alan Yuille , Quoc V. Le

Large language models (LLMs) can perform remarkably complex tasks, yet the fine-grained details of how these capabilities emerge during pretraining remain poorly understood. Scaling laws on validation loss tell us how much a model improves…

Computation and Language · Computer Science 2026-04-10 Emmy Liu , Kaiser Sun , Millicent Li , Isabelle Lee , Lindia Tjuatja , Jen-tse Huang , Graham Neubig

Predicting human perceptual similarity is a challenging subject of ongoing research. The visual process underlying this aspect of human vision is thought to employ multiple different levels of visual analysis (shapes, objects, texture,…

Computer Vision and Pattern Recognition · Computer Science 2019-03-27 Amir Rosenfeld , Richard Zemel , John K. Tsotsos

High complexity models are notorious in machine learning for overfitting, a phenomenon in which models well represent data but fail to generalize an underlying data generating process. A typical procedure for circumventing overfitting…

Machine Learning · Statistics 2025-03-11 James Schmidt

The performance of Human Activity Recognition (HAR) models, particularly deep neural networks, is highly contingent upon the availability of the massive amount of annotated training data which should be sufficiently labeled. Though, data…

Computer Vision and Pattern Recognition · Computer Science 2020-12-08 Elnaz Soleimani , Ghazaleh Khodabandelou , Abdelghani Chibani , Yacine Amirat

There is growing evidence that independently trained AI systems come to represent the world in the same way. In other words, independently trained embeddings from text, vision, audio, and neural signals share an underlying geometry. We call…

Neurons and Cognition · Quantitative Biology 2026-02-19 Akhil Ramidi , Kevin Scharp

Multi-task learning by robots poses the challenge of the domain knowledge: complexity of tasks, complexity of the actions required, relationship between tasks for transfer learning. We demonstrate that this domain knowledge can be learned…

Robotics · Computer Science 2022-02-22 Sao Mai Nguyen , Nicolas Duminy , Alexandre Manoury , Dominique Duhaut , Cédric Buche

Gradient-based meta-learning techniques aim to distill useful prior knowledge from a set of training tasks such that new tasks can be learned more efficiently with gradient descent. While these methods have achieved successes in various…

Machine Learning · Computer Science 2023-10-16 Mike Huisman , Aske Plaat , Jan N. van Rijn

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

The fine-tuning paradigm in addressing long-tail learning tasks has sparked significant interest since the emergence of foundation models. Nonetheless, how fine-tuning impacts performance in long-tail learning was not explicitly quantified.…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Jiang-Xin Shi , Tong Wei , Zhi Zhou , Jie-Jing Shao , Xin-Yan Han , Yu-Feng Li

In many learning theory problems, a central role is played by a hypothesis class: we might assume that the data is labeled according to a hypothesis in the class (usually referred to as the realizable setting), or we might evaluate the…

Machine Learning · Computer Science 2022-11-17 Lunjia Hu , Charlotte Peale

Automating algorithm configuration is growing increasingly necessary as algorithms come with more and more tunable parameters. It is common to tune parameters using machine learning, optimizing performance metrics such as runtime and…

Artificial Intelligence · Computer Science 2020-12-25 Maria-Florina Balcan , Tuomas Sandholm , Ellen Vitercik

Recent studies suggest that very small language models (SLMs) can generate surprisingly coherent text when trained on simplified, child-directed corpora such as TinyStories. These findings have been interpreted as evidence that readability…

Computation and Language · Computer Science 2025-10-17 Ivan Lee , Taylor Berg-Kirkpatrick

Despite their successes, deep learning models struggle with tasks requiring complex reasoning and function composition. We present a theoretical and empirical investigation into the limitations of Structured State Space Models (SSMs) and…

Machine Learning · Computer Science 2025-03-04 Nikola Zubić , Federico Soldá , Aurelio Sulser , Davide Scaramuzza

Self-supervised learning (SSL) methods have become a dominant paradigm for creating general purpose models whose capabilities can be transferred to downstream supervised learning tasks. However, most such methods rely on vast amounts of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Lakshay Sharma , Alex Marin

Meta-Learning has emerged as a research direction to better transfer knowledge from related tasks to unseen but related tasks. However, Meta-Learning requires many training tasks to learn representations that transfer well to unseen tasks;…

Computation and Language · Computer Science 2022-10-13 Surya Kant Sahu

The impressive performance gains of modern language models currently rely on scaling parameters: larger models store more world knowledge and reason better. Yet compressing all world knowledge into parameters is unnecessary, as only a…

Computation and Language · Computer Science 2026-03-24 Hadi Pouransari , David Grangier , C Thomas , Michael Kirchhof , Oncel Tuzel

With hundreds of multilingual embedding models available, practitioners lack clear guidance on which provide genuine cross-lingual semantic alignment versus task performance through language-specific patterns. Task-driven benchmarks (MTEB)…

Computation and Language · Computer Science 2026-01-16 Wen G. Gong

Debates about large language model post-training often treat supervised fine-tuning (SFT) as imitation and reinforcement learning (RL) as discovery. But this distinction is too coarse. What matters is whether a training procedure increases…

Artificial Intelligence · Computer Science 2026-05-12 Yuhao Li , Shengchao Liu
‹ Prev 1 3 4 5 6 7 10 Next ›