activity
20242026
collaborators

28 papers

cs.CV2026

SeeSE3: Emergence of 3D Space in Vision Features

Caroline Chen, Sayna Ebrahimi, Fedor Kitashov +4

The paper examines whether vision foundation models implicitly encode the geometry of 3D Euclidean space, introducing probes such as a mutual neighborhood metric and a Poincaré Ada…

cs.LG2026

The Computational Basis of Confidence in Large Language Models

Dharshan Kumaran, Viorica Patraucean, Maks Ovsjanikov +3

The paper investigates what the confidence signal in large language models actually represents, showing that answer logits often act as monotonic readouts of a latent decision vari…

cs.CV2026

Gen4U: Unifying Video Generation and Understanding via Diffusion

Michael King, Aravindh Mahendran, Matthew Koichi Grimes +5

Prior work suggests that diffusion representations capture low-level geometry but struggle with high-level semantics. We demonstrate that state-of-the-art video diffusion models ov…

cs.LG2026

Graph Alignment via Dual-Pass Spectral Encoding and Latent Space Communication

Maysam Behmanesh, Erkan Turan, Maks Ovsjanikov

Graph alignment, the problem of identifying corresponding nodes across multiple graphs, is fundamental to numerous applications. Most existing unsupervised methods embed node featu…

cs.AI2026

The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning

Theo Uscidda, Marta Tintore Gazulla, Maks Ovsjanikov +2

Current Large Reasoning Models (LRMs) exhibit remarkable general capabilities but significantly underperform in spatial reasoning tasks. Existing approaches treat this gap as a kno…

cs.CV2026

A Mixed Diet Makes DINO An Omnivorous Vision Encoder

Rishabh Kabra, Maks Ovsjanikov, Drew A. Hudson +5

Pre-trained vision encoders like DINOv2 have demonstrated exceptional performance on unimodal tasks. However, we observe that their features are poorly aligned across different vis…