linear-representation

Tag

Cards List
#linear-representation

@kdariina: Why do embedding models struggle with binding, a core requirement for multi-object understanding? We find that objects …

X AI KOLs Timeline · 2026-06-30 Cached

This thread discusses a finding that embedding models struggle with binding (a core requirement for multi-object understanding) and that solving it requires going beyond the linear representation hypothesis.

0 favorites 0 likes
#linear-representation

Representational Capacity: Geometric Limits on Feature Representation in Transformer Language Models

arXiv cs.LG · 2026-06-03 Cached

This paper introduces a quantitative framework for estimating how many near-orthogonal directions a transformer language model's latent space can support, based on the linear representation and superposition hypotheses. The authors define representational capacity as an upper bound on distinguishable features and show it is exponentially sensitive to the allowed deviation from orthogonality, with larger models favoring tighter constraints.

0 favorites 0 likes
#linear-representation

Representation Alignment Rests on Linear Structure

arXiv cs.LG · 2026-05-29 Cached

This paper investigates the Platonic Representation Hypothesis, proposing that alignment arises from linear structure in representations, and introduces a statistical framework of signal, bias, and noise.

0 favorites 0 likes
← Back to home

Submit Feedback