English
Related papers

Related papers: The Geometric Anatomy of Capability Acquisition in…

200 papers

Many of the recent remarkable advances in computer vision and language models can be attributed to the success of transfer learning via the pre-training of large foundation models. However, a theoretical framework which explains this…

Machine Learning · Computer Science 2024-12-19 Michael Munn , Benoit Dherin , Javier Gonzalvo

We train Transformer-based language models on ten foundational algorithmic tasks and observe pronounced phase transitions in their loss curves that deviate from established power-law scaling trends. Over large ranges of compute, the…

Machine Learning · Computer Science 2026-01-15 Prudhviraj Naidu , Zixian Wang , Leon Bergen , Ramamohan Paturi

It is generally thought that transformer-based large language models benefit from pre-training by learning generic linguistic knowledge that can be focused on a specific task during fine-tuning. However, we propose that much of the benefit…

Computation and Language · Computer Science 2024-06-19 Anna C. Marbut , John W. Chandler , Travis J. Wheeler

Standard training metrics like loss fail to explain the emergence of complex capabilities in large language models. We take a spectral approach to investigate the geometry of learned representations across pretraining and post-training,…

Transformers have theoretical limitations in modeling certain sequence-to-sequence tasks, yet it remains largely unclear if these limitations play a role in large-scale pretrained LLMs, or whether LLMs might effectively overcome these…

Machine Learning · Computer Science 2025-10-24 Mayank Jobanputra , Yana Veitsman , Yash Sarrof , Aleksandra Bakalova , Vera Demberg , Ellie Pavlick , Michael Hahn

Search is an ability foundational in many important tasks, and recent studies have shown that large language models (LLMs) struggle to perform search robustly. It is unknown whether this inability is due to a lack of data, insufficient…

Manipulation tasks often consist of subtasks, each representing a distinct skill. Mastering these skills is essential for robots, as it enhances their autonomy, efficiency, adaptability, and ability to work in their environment. Learning…

Robotics · Computer Science 2025-05-21 Juyan Zhang , Dana Kulic , Michael Burke

Deep Neural Networks achieve state-of-the-art results in many different problem settings by exploiting vast amounts of training data. However, collecting, storing and - in the case of supervised learning - labelling the data is expensive…

Computer Vision and Pattern Recognition · Computer Science 2023-03-06 Matthias Rath , Alexandru Paul Condurache

Pre-training has marked numerous state of the arts in high-level computer vision, while few attempts have ever been made to investigate how pre-training acts in image processing systems. In this paper, we tailor transformer-based…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Wenbo Li , Xin Lu , Shengju Qian , Jiangbo Lu , Xiangyu Zhang , Jiaya Jia

Neural models learn representations of high-dimensional data on low-dimensional manifolds. Multiple factors, including stochasticities in the training process, model architectures, and additional inductive biases, may induce different…

Machine Learning · Computer Science 2025-12-02 Hanlin Yu , Berfin Inal , Georgios Arvanitidis , Soren Hauberg , Francesco Locatello , Marco Fumero

Graph Neural Networks (GNN) can capture the geometric properties of neural representations in EEG data. Here we utilise those to study how reinforcement-based motor learning affects neural activity patterns during motor planning, leveraging…

Machine Learning · Computer Science 2024-11-01 Federico Nardi , Jinpei Han , Shlomi Haar , A. Aldo Faisal

Does inverse scaling only occur as a function of model size, or can it also occur over the course of training? We carry out an exploratory study investigating whether the performance of language models on specific tasks can decrease (while…

Computation and Language · Computer Science 2024-08-27 James A. Michaelov , Benjamin K. Bergen

Scaling up language models has led to unprecedented performance gains, but little is understood about how the training dynamics change as models get larger. How do language models of different sizes learn during pre-training? Why do larger…

Computation and Language · Computer Science 2023-05-31 Mengzhou Xia , Mikel Artetxe , Chunting Zhou , Xi Victoria Lin , Ramakanth Pasunuru , Danqi Chen , Luke Zettlemoyer , Ves Stoyanov

Training Transformers on algorithmic tasks frequently demonstrates an intriguing abrupt learning phenomenon: an extended performance plateau followed by a sudden, sharp improvement. This work investigates the underlying mechanisms for such…

Machine Learning · Computer Science 2025-10-24 Pulkit Gopalani , Wei Hu

Transformers often fail to learn generalizable algorithms, instead relying on brittle heuristics. Using graph connectivity as a testbed, we explain this phenomenon both theoretically and empirically. We consider a simplified Transformer…

Machine Learning · Computer Science 2026-02-19 Qilin Ye , Deqing Fu , Robin Jia , Vatsal Sharan

Language modeling has shown us that transformers can discover latent structure from context, but the dynamics of how they acquire different components of that structure remain poorly understood, leading to assertions that models just remix…

Machine Learning · Computer Science 2026-04-23 Rohan Saha , Farzane Aminmansour , Alona Fyshe

Deep learning models are often considered black boxes due to their complex hierarchical transformations. Identifying suitable architectures is crucial for maximizing predictive performance with limited data. Understanding the geometric…

Machine Learning · Computer Science 2025-03-11 Michael Wienczkowski , Addisu Desta , Paschal Ugochukwu

The paper uses statistical and differential geometric motivation to acquire prior information about the learning capability of an artificial neural network on a given dataset. The paper considers a broad class of neural networks with…

Machine Learning · Computer Science 2020-12-02 Ankan Dutta , Arnab Rakshit

Grokking -- the delayed transition from memorization to generalization in small algorithmic tasks -- remains poorly understood. We present a geometric analysis of optimization dynamics in transformers trained on modular arithmetic. PCA of…

Machine Learning · Computer Science 2026-04-06 Yongzhong Xu

Transferability of learned features between tasks can massively reduce the cost of training a neural network on a novel task. We investigate the effect of network width on learned features using activation atlases --- a visualization…

Machine Learning · Computer Science 2019-09-26 Dar Gilboa , Guy Gur-Ari
‹ Prev 1 2 3 10 Next ›