arXiv:2607. 27092v1 Announce Type: new Abstract: We analyze whether language models of size ~100B have a representation of the night sky map that is decodable from their residual stream.
arXiv:2511. 21594v3 Announce Type: replace Abstract: Large language models (LLMs) achieve state-of-the-art results across many natural language tasks, but their internal mechanisms remain difficult to interpret.
arXiv:2607. 14419v1 Announce Type: new Abstract: Machine-learning datasets labelled "4D" universally denote three spatial dimensions plus time.
arXiv:2606. 19249v1 Announce Type: cross Abstract: Despite the widespread adoption of Vision Transformers (ViTs) and their success across numerous computer vision applications, the fundamental understanding of their dimensional and representational geometry remains relatively underexplored.
arXiv:2602. 15029v3 Announce Type: replace Abstract: The internal representations learned by language models consistently exhibit striking geometric structure: calendar months organize into a circle, historical years form a smooth one-dimensional manifold, and cities' latitudes and longitudes can be decoded using a linear probe.
arXiv:2601. 09173v5 Announce Type: replace Abstract: Representational similarity analysis and related methods compare the internal geometries of neural networks, but they measure only alignment between spaces, leaving a blind spot -- whether a representation's structure is reliably recoverable, not merely similar.
arXiv:2608. 09997v1 Announce Type: new Abstract: Transformers have had a profound impact on the world of language processing and computer vision.
arXiv:2609.00661v1 Announce Type: new Abstract: Satellite foundation models offer a globally available alternative to census data for commuting origin-destination (OD) generation, yet no study has sy...
arXiv:2607. 10578v1 Announce Type: new Abstract: Existing hypotheses represent a concept in an LLM as a single point, a linear direction, or a Gaussian cluster, yet it remains unclear how and why such structures emerge.
arXiv:2608. 05242v1 Announce Type: new Abstract: In this work, we explore an alternative paradigm for spatial reasoning by explicitly disentangling 3D perception from reasoning, rather than jointly acquiring implicit 3D perception and reasoning through large-scale training.
arXiv:2608. 15632v1 Announce Type: cross Abstract: Neural representations have become a central tool for studying the internal mechanisms of modern AI models, yet their complex high-dimensional structure makes them difficult to interpret.
arXiv:2601. 18823v4 Announce Type: replace Abstract: Variational autoencoders (VAE) encode data into lower-dimensional latent vectors before decoding those vectors back to data.
arXiv:2605. 20448v2 Announce Type: replace-cross Abstract: Vision-language models reliably name objects in a scene, but do they represent the 3D layout those objects inhabit?