English
Related papers

Related papers: Representation Alignment Rests on Linear Structure

200 papers

Historical approaches to Table Representation Learning (TRL) have largely adopted the sequential paradigms of Natural Language Processing (NLP). We argue that this linearization of tables discards their essential geometric and relational…

Artificial Intelligence · Computer Science 2026-04-15 Willy Carlos Tchuitcheu , Tan Lu , Ann Dooms

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

The Platonic Representation Hypothesis suggests that neural networks trained on different modalities (e.g., text and images) align and eventually converge toward the same representation of reality. If true, this has significant implications…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 A. Sophia Koepke , Daniil Zverev , Shiry Ginosar , Alexei A. Efros

The Platonic Representation Hypothesis suggests that representations from neural networks are converging to a common statistical model of reality. We show that the existing metrics used to measure representational similarity are confounded…

Machine Learning · Computer Science 2026-02-17 Fabian Gröger , Shuo Wen , Maria Brbić

The Platonic Representation Hypothesis posits that learned representations from models trained on different modalities converge to a shared latent structure of the world. However, this hypothesis has largely been examined in vision and…

Artificial Intelligence · Computer Science 2026-02-24 Pratham Yashwante , Rose Yu

We argue that representations in AI models, particularly deep networks, are converging. First, we survey many examples of convergence in the literature: over time and across multiple domains, the ways by which different neural networks…

Machine Learning · Computer Science 2024-07-26 Minyoung Huh , Brian Cheung , Tongzhou Wang , Phillip Isola

Understanding neural representations will help open the black box of neural networks and advance our scientific understanding of modern AI systems. However, how complex, structured, and transferable representations emerge in modern neural…

Machine Learning · Computer Science 2025-02-28 Liu Ziyin , Isaac Chuang , Tomer Galanti , Tomaso Poggio

It has recently been argued that AI models' representations are becoming aligned as their scale and performance increase. Empirical analyses have been designed to support this idea and conjecture the possible alignment of different…

Machine Learning · Computer Science 2025-02-21 Francesco Insulla , Shuo Huang , Lorenzo Rosasco

We introduce a mathematical framework for the linear representation hypothesis (LRH), which asserts that intermediate layers of language models store features linearly. We separate the hypothesis into two claims: linear representation…

Machine Learning · Computer Science 2026-02-13 Nikhil Garg , Jon Kleinberg , Kenny Peng

There is a large ongoing scientific effort in mechanistic interpretability to map embeddings and internal representations of AI systems into human-understandable concepts. A key element of this effort is the linear representation…

Machine Learning · Computer Science 2025-05-27 Alexander Modell , Patrick Rubin-Delanchy , Nick Whiteley

Neural networks are known to develop latent representations that are $aligned$, namely structurally similar across networks trained with different architectures, training protocols, or training datasets. We study this phenomenon in a…

Machine Learning · Statistics 2026-05-27 Ali Hussaini Umar , Alessandro Laio

Do brains and language models converge toward the same internal representations of the world? Recent years have seen a rise in studies of neural activations and model alignment. In this work, we review 25 fMRI-based studies published…

Neurons and Cognition · Quantitative Biology 2025-10-22 Ángela López-Cardona , Sebastián Idesis , Mireia Masias-Bruns , Sergi Abadal , Ioannis Arapakis

Informally, the 'linear representation hypothesis' is the idea that high-level concepts are represented linearly as directions in some representation space. In this paper, we address two closely related questions: What does "linear…

Computation and Language · Computer Science 2026-05-18 Kiho Park , Yo Joong Choe , Victor Veitch

The Platonic Representation Hypothesis claims that recent foundation models are converging to a shared representation space as a function of their downstream task performance, irrespective of the objectives and data modalities used to train…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Laure Ciernik , Lorenz Linhardt , Marco Morik , Jonas Dippel , Simon Kornblith , Lukas Muttenthaler

Steering is a widely used technique for controlling large language models, yet its effects are often unstable and hard to predict. Existing theoretical accounts are largely based on the Linear Representation Hypothesis (LRH). While LRH…

Computation and Language · Computer Science 2026-05-05 Lang Gao , Jinghui Zhang , Wei Liu , Fengxian Ji , Chenxi Wang , Zirui Song , Akash Ghosh , Youssef Mohamed , Preslav Nakov , Xiuying Chen

In this note, we elaborate on and explain in detail the proof given by Ziyin et al. (2025) of the ``perfect" Platonic Representation Hypothesis (PRH) for the embedded deep linear network model (EDLN). We show that if trained with the…

Machine Learning · Computer Science 2025-12-12 Liu Ziyin , Isaac Chuang

Reinforcement Learning frameworks, particularly those utilizing human annotations, have become an increasingly popular method for preference fine-tuning, where the outputs of a language model are tuned to match a certain set of behavioral…

Machine Learning · Computer Science 2025-10-21 Archie Chaudhury

Deep neural networks come in many sizes and architectures. The choice of architecture, in conjunction with the dataset and learning algorithm, is commonly understood to affect the learned neural representations. Yet, recent results have…

Machine Learning · Computer Science 2024-07-08 Loek van Rossem , Andrew M. Saxe

Conventional preference learning methods often prioritize opinions held more widely when aggregating preferences from multiple evaluators. This may result in policies that are biased in favor of some types of opinions or groups and…

Artificial Intelligence · Computer Science 2026-03-03 Kihyun Kim , Jiawei Zhang , Asuman Ozdaglar , Pablo A. Parrilo

Robots that interact with humans in a physical space or application need to think about the person's posture, which typically comes from visual sensors like cameras and infra-red. Artificial intelligence and machine learning algorithms use…

Artificial Intelligence · Computer Science 2022-10-25 Richard G. Freedman , Joseph B. Mueller , Jack Ladwig , Steven Johnston , David McDonald , Helen Wauck , Ruta Wheelock , Hayley Borck
‹ Prev 1 2 3 10 Next ›