The paper introduces the Lattice Representation Hypothesis (LRH) to explain why different alignment criteria—such as neighbor overlap, spanning trees, and distances—yield varying views on model representation convergence. It shows that the Platonic Representation Hypothesis (PRH) reflects agreement at the top of a lattice, while evidence comes from criteria near the bottom, and that the Aristotelian Representation Hypothesis (ARH) limits convergence to local neighborhoods due to calibration effects. Experiments on numerous pretrained vision and language models, along with theoretical analyses of linear autoencoders and contrastive Gibbs models, support the LRH’s claim that training procedures and objectives determine which criteria are reliably met across runs.
arXiv:2609.24209v1 Announce Type: new Abstract: The Platonic Representation Hypothesis (PRH) claims that independently trained models converge on a shared statistical model of reality, yet recent wor...
The Platonic Representation Hypothesis (PRH) claims that independently trained models converge on a shared statistical model of reality, yet recent work finds only weak pointwise similarity between mo...
The paper investigates the Platonic Representation Hypothesis, which posits that more capable models converge toward shared representations. By distinguishing relational structure (which samples are related) from metric geometry (quantitative relations like distances), the authors develop a controlled $2 imes2$ framework to evaluate both aspects at local and global scales. Their findings show that relational structure consistently converges across vision‑language and video‑text models, while metric geometry converges much more weakly, a pattern that persists even when using a Riemannian metric approximation.
arXiv:2604. 18572v2 Announce Type: replace-cross Abstract: The Platonic Representation Hypothesis suggests that neural networks trained on different modalities (e.
arXiv:2602. 14486v2 Announce Type: replace-cross Abstract: The Platonic Representation Hypothesis suggests that representations from neural networks are converging to a common statistical model of reality.
arXiv:2606. 02765v1 Announce Type: cross Abstract: Model dimension ($d_{model}$) is a fundamental hyperparameter in transformer language models, yet its role in setting the geometric limits of feature representation remains under-explored.
arXiv:2607. 17800v1 Announce Type: new Abstract: Representation is a central concept in modern machine learning, where it usually refers to internal encodings that support learning and generalization.
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:2512. 07355v2 Announce Type: replace Abstract: Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what a concept should be, and Sparse Autoencoders (SAEs), which discover what concepts emerge.
arXiv:2506. 20699v2 Announce Type: replace Abstract: Learning in non-stationary and multi-context environments requires more than ordinary within-task generalization.
arXiv:2607. 08843v1 Announce Type: new Abstract: In artificial and biological neural networks, concepts are often encoded as consistent linear directions in representation space.
arXiv:2610.07168v1 Announce Type: new Abstract: Representations of translated sentences are similar in the inner layers of multilingual language models -- an observation connected to the platonic rep...