arXiv Machine Learning July 7, 2026 By Jaeyoung Kim, Eunseok Kim, Dongsuk Jang

Is the Geometry Doing the Work? An Operating-Point Audit of Hierarchy in Hyperbolic Vision-Language Models

Read the original on arXiv Machine Learning →

arXiv:2607. 05268v1 Announce Type: cross Abstract: Whether a hyperbolic representation model uses its geometry cannot be read off its curvature parameter: what matters is the dimensionless operating point $\sqrt{c}\rho$ and whether the radial and cone machinery is active there.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 25

Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models

arXiv:2606. 24952v1 Announce Type: cross Abstract: A central aspiration of mechanistic interpretability is controllability: if we know where a behavior is represented in a model's activations, we should be able to modify it.

By Cosimo Galeone, Anna Ettorre, Minsu Park, Giuseppe Ettorre, Daniele Ligorio

llms fine-tuning safety

arXiv Machine Learning

Jul 8

No Subspace to Track: Non-Identifiability and Optimizer State in Low-Rank Training

arXiv:2607. 05872v1 Announce Type: new Abstract: Memory-efficient optimizers such as GaLore train large language models by projecting gradients onto a rank-r subspace recomputed every T steps, assuming this subspace is a slowly drifting object that can be tracked.

By Noel Thomas

llms computer-vision

arXiv AI

Jun 29

Do Vision Models Truly Forget? New Findings from Representation-Level Certification of Visual Unlearning in Vertical Federated Learning

arXiv:2605. 20282v3 Announce Type: replace-cross Abstract: Machine unlearning in Vertical Federated Learning (VFL) has attracted growing interest, yet existing methods certify forgetting solely using output-level metrics.

By Zhenyu Yu, Yangchen Zeng, Chunlei Meng, Guangzhen Yao, Shuigeng Zhou

safety

arXiv AI

Jul 21

After the Euclidean Highway: Hyperbolic Expert AI as the Next Innovation

arXiv:2607. 17513v1 Announce Type: cross Abstract: Expert domains are trees; the Euclidean transformer is not, diluting parent-child structure exponentially at depth.

By Kwan Soo Shin, In Seok Kang, Munho Lee

llms benchmarks

arXiv AI

Aug 12

Riemann GeoResolver: A Non-Euclidean Attention Framework from Euclidean Resolver to Hyperbolic-Spherical Geometry

arXiv:2608. 10416v1 Announce Type: cross Abstract: We present a theoretical foundation for inverse-distance attention, from its Euclidean prototype (Resolver) to its non-Euclidean realization (Riemann GeoResolver).

By Liangchen Ge

arXiv AI

Jul 29

CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model

arXiv:2607. 25487v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models translate natural-language commands into robot action sequences, but leading systems on the LIBERO-Plus robustness benchmark use three- to seven-billion-parameter backbones whose memory demands can exceed embedded robotic budgets.

By Minhyeok Lee, Chiyoung Kim, Chanhoe Gu, Seongrok Kim, Sanghyuk Roy Choi, Donghwan Hwang, Donghun Ryu, Seokhyun Kim

robotics efficiency multimodal benchmarks

Related stories

Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models

No Subspace to Track: Non-Identifiability and Optimizer State in Low-Rank Training

Do Vision Models Truly Forget? New Findings from Representation-Level Certification of Visual Unlearning in Vertical Federated Learning

After the Euclidean Highway: Hyperbolic Expert AI as the Next Innovation

Riemann GeoResolver: A Non-Euclidean Attention Framework from Euclidean Resolver to Hyperbolic-Spherical Geometry

CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model