中文
相关论文

相关论文: Time Series, Vision, and Language: Exploring the L…

200 篇论文

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…

计算机视觉与模式识别 · 计算机科学 2026-04-21 A. Sophia Koepke , Daniil Zverev , Shiry Ginosar , Alexei A. Efros

Time series forecasting traditionally relies on unimodal numerical inputs, which often struggle to capture high-level semantic patterns due to their dense and unstructured nature. While recent approaches have explored representing time…

机器学习 · 计算机科学 2025-07-02 Sixun Dong , Wei Fan , Teresa Wu , Yanjie Fu

The Platonic Representation Hypothesis posits that neural networks trained on different modalities converge toward a shared statistical model of the world. Recent work exploits this convergence by aligning frozen pretrained vision and…

机器学习 · 计算机科学 2026-02-27 Simon Roschmann , Paul Krzakala , Sonia Mazelet , Quentin Bouniot , Zeynep Akata

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…

机器学习 · 计算机科学 2024-07-26 Minyoung Huh , Brian Cheung , Tongzhou Wang , Phillip Isola

While many advances in time series models focus exclusively on numerical data, research on multimodal time series, particularly those involving contextual textual information, remains in its infancy. With recent progress in large language…

机器学习 · 计算机科学 2026-03-10 Zihao Li , Xiao Lin , Zhining Liu , Jiaru Zou , Ziwei Wu , Lecheng Zheng , Dongqi Fu , Yada Zhu , Hendrik Hamann , Hanghang Tong , Jingrui He

The platonic representation hypothesis suggests that vision and language embeddings become more homogeneous as model and dataset sizes increase. In particular, pairwise distances within each modality become more similar. This suggests that…

计算机视觉与模式识别 · 计算机科学 2025-05-30 Dominik Schnaus , Nikita Araslanov , Daniel Cremers

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…

神经元与认知 · 定量生物学 2025-10-22 Ángela López-Cardona , Sebastián Idesis , Mireia Masias-Bruns , Sergi Abadal , Ioannis Arapakis

Large language models trained under diverse objectives and architectures have been shown to develop increasingly similar internal representations, an observation formalized as the Platonic Representation Hypothesis. Whether this…

计算与语言 · 计算机科学 2026-05-25 Muhammad Usama , Dong Eui Chang

Understanding why independently trained neural networks from different modalities converge toward shared representations, and where this convergence leads, remains an open question in representation learning. All existing evidence relies on…

人工智能 · 计算机科学 2026-05-12 Zhaoyang Zhang , Run Shao , Dongyue Wu , Jiajie Teng , Chao Tao , Jingdong Chen , Haifeng Li

Recent studies show that deep vision-only and language-only models--trained on disjoint modalities--nonetheless project their inputs into a partially aligned representational space. Yet we still lack a clear picture of where in each network…

计算机视觉与模式识别 · 计算机科学 2025-09-26 Zoe Wanying He , Sean Trott , Meenakshi Khosla

We investigate the Platonic Representation Hypothesis (PRH) through a tripartite statistical framework of representations: signal, bias, and noise. {1) Signal:} We propose that Platonic alignment arises from the universal relationship…

机器学习 · 计算机科学 2026-05-29 Kiril Bangachev , Guy Bresler , Yury Polyanskiy

Large language models (LLMs) have become increasingly useful computational models of human language processing, but it remains unclear whether vision-language learning makes text representations more human-like during natural reading. Here,…

计算与语言 · 计算机科学 2026-05-28 Jinzhou Wu , Zhengwu Ma , Jixing Li , Baoping Tang , Zitong Lu

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…

神经元与认知 · 定量生物学 2026-02-19 Akhil Ramidi , Kevin Scharp

Although an object may appear in numerous contexts, we often describe it in a limited number of ways. Language allows us to abstract away visual variation to represent and communicate concepts. Building on this intuition, we propose an…

计算机视觉与模式识别 · 计算机科学 2023-03-30 Mohamed El Banani , Karan Desai , Justin Johnson

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…

机器学习 · 计算机科学 2026-02-17 Fabian Gröger , Shuo Wen , Maria Brbić

Humans can effortlessly describe what they see, yet establishing a shared representational format between vision and language remains a significant challenge. Emerging evidence suggests that human brain representations in both vision and…

神经元与认知 · 定量生物学 2025-07-30 Katerina Marie Simkova , Adrien Doerig , Clayton Hickey , Ian Charest

Independently trained vision and language models inhabit disjoint representational spaces, shaped by their respective modalities, objectives, and architectures. The Platonic Representation Hypothesis (PRH) suggests these models may…

机器学习 · 计算机科学 2026-05-18 Lauren Hyoseo Yoon , Yisong Yue , Been Kim

The platonic representation hypothesis suggests that sufficiently large models converge to a shared representation geometry, even across modalities. Motivated by this, we ask: Can the semantic knowledge of a language model efficiently…

计算机视觉与模式识别 · 计算机科学 2026-05-22 Tobias Christian Nauen , Stanislav Frolov , Brian Bernhard Moser , Federico Raue , Ahmed Anwar , Andreas Dengel

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…

计算机视觉与模式识别 · 计算机科学 2025-06-05 Laure Ciernik , Lorenz Linhardt , Marco Morik , Jonas Dippel , Simon Kornblith , Lukas Muttenthaler

The Strong Platonic Representation Hypothesis suggests that representational convergence in artificial neural networks can be harnessed constructively: embeddings can be translated across models through a universal latent space without…

神经元与认知 · 定量生物学 2026-05-21 Pablo Marcos-Manchón , Rishi Jha , Lluís Fuentemilla
‹ 上一页 1 2 3 10 下一页 ›