{"slug": "primate-vision-reveals-a-missing-principle-for-robust-dynamic-ai", "title": "Primate vision reveals a missing principle for robust dynamic AI", "summary": "A new study from arXiv (2608.23790v1) comparing human and macaque vision with neural networks found that predictive world models achieve the closest correspondence to primate inferior temporal cortex and outperform other video-modeling approaches in cross-appearance generalization, yet no model fully replicates the cortical shift from appearance-based to motion-based coding. The findings identify progressive motion integration as a key principle for robust dynamic vision in AI.", "body_md": "arXiv:2608.23790v1 Announce Type: new\nAbstract: How does an intelligent visual system combine what objects look like with how they move while remaining robust as appearance changes? We addressed this question by comparing human perception and neural activity in macaque inferior temporal cortex with representations from image- and video-based neural networks spanning recognition, segmentation, optic-flow processing and predictive world modeling. Temporal integration improved object representations, but most video recognition models generalized poorly when appearance was disrupted while motion structure was preserved. Humans and macaque IT remained robust. Notably, predictive world models combined strong cross-appearance generalization with the closest correspondence to IT, outperforming other video-modeling approaches in neural fidelity. Yet no model reproduced the cortical transformation from early appearance-dominated responses toward later appearance-invariant motion coding. These results identify progressive integration of motion into object representations as a principle of robust dynamic vision and implicate predictive learning as a promising route toward realizing this computation in artificial systems.", "url": "https://wpnews.pro/news/primate-vision-reveals-a-missing-principle-for-robust-dynamic-ai", "canonical_source": "https://arxiv.org/abs/2608.23790", "published_at": "2026-08-26 04:00:00+00:00", "updated_at": "2026-08-26 04:13:57.944072+00:00", "lang": "en", "topics": ["artificial-intelligence", "computer-vision", "machine-learning", "neural-networks"], "entities": ["arXiv", "macaque inferior temporal cortex"], "alternates": {"html": "https://wpnews.pro/news/primate-vision-reveals-a-missing-principle-for-robust-dynamic-ai", "markdown": "https://wpnews.pro/news/primate-vision-reveals-a-missing-principle-for-robust-dynamic-ai.md", "text": "https://wpnews.pro/news/primate-vision-reveals-a-missing-principle-for-robust-dynamic-ai.txt", "jsonld": "https://wpnews.pro/news/primate-vision-reveals-a-missing-principle-for-robust-dynamic-ai.jsonld"}}