Visual Cortex
PulseAugur coverage of Visual Cortex — every cluster mentioning Visual Cortex across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New DRAFT method reconstructs 3D room layouts from fMRI and camera data
Researchers have developed a novel method called DRAFT that can reconstruct the 3D layout of rooms using only functional magnetic resonance imaging (fMRI) signals and camera trajectories, without relying on visual frame…
-
New research reveals subspace-level modularity in neural networks
A new research paper proposes a framework to identify modularity in neural networks beyond individual neuron specialization. The study introduces three levels of modularity: unit-level, orthogonal, and linear, and devel…
-
New research explores optimal adapter placement in vision transformers
Researchers have explored two distinct methods for optimizing the placement of task-specific adapters in continual learning models, specifically within vision transformers. One approach, placement search, involves train…
-
AI Video Generation Better Aligns with Human Visual Cortex
Researchers have developed a new method to evaluate video generation models by comparing their internal representations to human visual cortex activity. They found that autoregressive (AR) video diffusion models, when g…
-
New IRIS framework analyzes orientation selectivity in Vision Transformers
Researchers have developed a new framework called IRIS to analyze how orientation selectivity emerges in Vision Transformers (ViTs). This framework uses neuroscience-inspired metrics to study how ViTs encode low-level f…
-
Detailed exploration of eye anatomy and optical phenomena
This post delves into less commonly discussed aspects of the eye's structure and function, moving beyond introductory material. It explores evolutionary design features and addresses specific optical phenomena. The auth…
-
New framework NEvo synthesizes dynamic visual stimuli for brain region selectivity
Researchers have developed a new framework called NEvo for synthesizing dynamic visual stimuli that are optimized to probe selectivity in specific brain regions of the visual cortex. This neural-guided evolutionary appr…
-
Meta-learning approach yields human-like visual representations in AI
Researchers have developed a new approach to training neural networks that better mimics human visual representation learning. Unlike standard networks trained on a single objective, this new method uses meta-learning t…
-
OmniMouse brain model scales with data, not size
Researchers have developed OmniMouse, a multi-modal, multi-task model trained on over 150 billion neural tokens from a mouse's visual cortex. This model demonstrates state-of-the-art performance in neural prediction, be…
-
New AI model ICPNet mimics human vision to perceive illusory contours
Researchers have developed a novel deep neural network, the illusory contour perception network (ICPNet), inspired by the human visual cortex. This network aims to improve machine perception of illusory contours, which …
-
Biologically grounded neural networks leverage mouse brain data
Researchers have developed biologically grounded recurrent neural networks by leveraging data from the MICrONS program, which combines electron microscopy and calcium imaging of mouse visual cortex. These networks utili…
-
AI learning mechanism diverges from human brain processing
A new research paper explores the differences between how artificial neural networks learn and how the human brain processes visual information. While both deep learning models and the brain show similarities in represe…