arXiv Computer Vision August 26, 2026 By Matteo Dunnhofer, Christian Micheloni, Kohitij Kar

Primate vision reveals a missing principle for robust dynamic AI

Read the original on arXiv Computer Vision →

The study investigates how intelligent visual systems integrate object appearance with motion while maintaining robustness to appearance changes. By comparing human perception, macaque inferior temporal cortex activity, and various neural network models, the authors find that temporal integration enhances object representations, yet most video models fail to generalize when appearance varies. Predictive world models show the best cross‑appearance generalization and neural fidelity, though none fully replicate the cortical shift from appearance‑dominated to motion‑invariant coding.

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 Computer Vision.

computer-vision

arXiv AI

1d ago

Future Video Generation Better Aligns with the Human Visual Cortex than Observed Video

The study investigates how internal representations of video diffusion models align with human visual cortex responses. It finds that representations used for future video generation in an autoregressive (AR) model better match cortical activity than those for observed video, with future‑generation alignment concentrated in higher‑order visual areas. A behavioral experiment further shows that humans prefer videos enhanced by layers that align more strongly with cortical responses.

By Chang-Bae Bang, Hyungjin Chung, Byung-Hoon Kim

diffusion safety

arXiv AI

Jul 7

Human-like Object Grouping in Self-supervised Vision Transformers

arXiv:2603. 13994v2 Announce Type: replace-cross Abstract: Vision foundation models trained with self-supervised objectives achieve strong performance across diverse tasks and exhibit emergent object segmentation properties.

By Hossein Adeli, Seoyoung Ahn, Andrew Luo, Mengmi Zhang, Nikolaus Kriegeskorte, Gregory Zelinsky

llms computer-vision efficiency benchmarks safety

arXiv Computer Vision

1d ago

Image Classifiers are Efficient Self-Supervised Video Representation Learners

arXiv:2609.40347v1 Announce Type: new Abstract: We introduce VideoMSN, a Masked Siamese Network framework for efficient self-supervised spatio-temporal representation learning in videos. Instead of r...

By Owais Iqbal, Sudipta Sarkar, Shyam Marjit, Omprakash Chakraborty, Anirban Chakraborty, Abir Das

llms rag computer-vision benchmarks

arXiv AI

Jun 9

What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction

arXiv:2606. 07687v1 Announce Type: cross Abstract: Video world models are increasingly used to provide predictive visual representations, yet it remains unclear which pretraining signals induce action-relevant structure in their latent spaces.

By Jewon Yeom, Hanseul Kim, Jeongjae Park, Sungmok Jung, Jaejin Lee, Taesup Kim

diffusion robotics benchmarks

arXiv AI

Jun 16

You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences

arXiv:2606. 15956v1 Announce Type: cross Abstract: Progress in AI has largely been driven by methods that assume less.

By Ninad Daithankar, Alexi Gladstone, Yann LeCun, Heng Ji

benchmarks

arXiv Computer Vision

Sep 16

Extremely coarse learning objectives induce human-aligned representations in AI vision models

arXiv:2605.05556v2 Announce Type: replace Abstract: Artificial neural networks trained on visual tasks develop internal representations resembling those of the primate visual system, a discovery that...

By Yash Mehta, Michael F. Bonner

llms rag safety

One email a morning, machine-written

Related stories

Future Video Generation Better Aligns with the Human Visual Cortex than Observed Video

Human-like Object Grouping in Self-supervised Vision Transformers

Image Classifiers are Efficient Self-Supervised Video Representation Learners

What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction

You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences

Extremely coarse learning objectives induce human-aligned representations in AI vision models