arXiv Machine Learning July 7, 2026 By Arnas Uselis, Andrea Dittadi, Seong Joon Oh

Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models

Read the original on arXiv Machine Learning →

arXiv:2602. 24264v2 Announce Type: replace-cross Abstract: Compositional generalization, the ability to recognize familiar parts in novel contexts, is a defining property of intelligent systems.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 2

Global Geometry Is Not Enough for Vision Representations

arXiv:2602. 03282v2 Announce Type: replace-cross Abstract: A common assumption in representation learning is that globally well-distributed embeddings support robust and generalizable representations.

By Jiwan Chung, Seon Joo Kim

rag

arXiv AI

Jun 3

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

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.

By Alexander Guha

llms rag diffusion

arXiv AI

Jun 12

Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality

arXiv:2606. 13288v1 Announce Type: cross Abstract: Contrastively trained vision-language models like CLIP, have made remarkable progress in learning joint image-text representations, but still face challenges in compositional understanding.

By Wei Li, Zhen Huang, Xinmei Tian

llms diffusion multimodal benchmarks

Hugging Face Trending Papers

Sep 21

Displacement Geometry Captures Platonic Shared Reality Across Models and Modalities

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...

fine-tuning efficiency safety

arXiv Machine Learning

Sep 22

Displacement Geometry Captures Platonic Shared Reality Across Models and Modalities

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...

By Chenming Shang, Yujin Tang, Jun Jie Ou Yang, Ruize Xu, Adam Breuer, Nikhil Singh

fine-tuning efficiency safety

arXiv AI

6d ago

Beyond Bag-of-Words: Diagnosing Compositional Binding Failures in Vision-Language Models

The paper introduces Auto-Comp, a fully automated, concept-driven pipeline that generates photorealistic compositional benchmarks for vision‑language models. Auto‑Comp creates paired Minimal and Contextual samples for each concept, enabling isolation of core binding abilities from visio‑linguistic complexity. Evaluations across 25 models reveal consistent failures in attribute and relational binding, with context helping relational tasks but hindering attribute tasks due to visual clutter.

By Cristian Sbrolli, Toshihiko Yamasaki, Matteo Matteucci

llms multimodal benchmarks

One email a morning, machine-written

Related stories

Global Geometry Is Not Enough for Vision Representations

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

Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality

Displacement Geometry Captures Platonic Shared Reality Across Models and Modalities

Displacement Geometry Captures Platonic Shared Reality Across Models and Modalities

Beyond Bag-of-Words: Diagnosing Compositional Binding Failures in Vision-Language Models