Neurons++ is a visual‑stream framework that reconstructs both static images and dynamic videos from fMRI data. It builds on the earlier Neurons model by extending from video‑only to image‑and‑video reconstruction and replacing parallel task conditioning with a serial, cortex‑inspired decoding pipeline. The approach first pre‑trains on image‑fMRI pairs for stable spatial‑semantic initialization, then fine‑tunes separately for image and video tasks, organizing fMRI representations into spatial, semantic, language‑level, and temporal cues, and achieves state‑of‑the‑art video reconstruction with competitive image results while enabling neural‑to‑visual interpretability and ROI‑guided semantic modulation.
By Haonan Wang, Yuchen Wang, Jingyu Lu, Qixiang Zhang, Lehan Wang, Xuanqi Huang, Xiaomeng Li
arXiv:2606. 05328v1 Announce Type: cross Abstract: Modern video diffusion models generate increasingly realistic and temporally coherent videos, motivating their use as candidate world simulators.
By Parsa Esmati, Somjit Nath, Katja Hofmann, Derek Nowrouzezahrai, Samira Ebrahimi Kahou, Majid Mirmehdi
The study explores how to fine‑tune visual brain encoding models so that their internal representations better match individual human perceptual similarity judgments. Using similarity data from 100 images collected from eight participants in the Natural Scenes Dataset, the authors adapted a generic similarity model (DreamSim) to create personalized perceptual similarity models for each subject. They then fine‑tuned each participant’s baseline encoder with either generic or personalized similarity information, finding that models trained with personalized judgments were most aligned with human perceptual similarity and preserved inter‑subject correlations of those judgments.
By Daniel Chong, Haomiao Chen, Keith W Jamison, Raja Marjieh, Ilia Sucholutsky, Nori Jacoby, Amy Kuceyeski
NEvo is a neural‑guided evolutionary video synthesis framework that generates dynamic stimuli optimized for specific brain regions in the visual cortex. It performs evolutionary search over a structured prompt space, guided by a dynamic encoding model that predicts voxel‑level responses to video inputs, thereby discovering hyper‑activating videos that outperform handcrafted localizers. The synthesized videos recover known selectivities across ventral, dorsal, and lateral pathways and reveal systematic differences in sensitivity to temporal dynamics, offering new insights into the progression of social‑dynamic features along the lateral stream.
By Yingtian Tang, Sogand Salehi, Ming Zhou, Amir Zamir, Leyla Isik, Martin Schrimpf
arXiv:2607. 16292v4 Announce Type: replace-cross Abstract: Brain-encoding foundation models predict fMRI responses to video, audio and text well enough to win the Algonauts 2025 challenge.
By Carson Rodrigues
The paper introduces a multidimensional observer model that represents images as distributions in a latent perceptual space and models human image quality judgment as comparisons of noisy samples. By aligning the model with neural representations in the primate ventral stream and fitting it to large-scale behavioral data, the authors demonstrate that the perceptual space required for human quality assessment is extremely low-dimensional relative to the image space. The study reveals that the structure of this perceptual space differs between low-level and high-level quality judgments, indicating that humans construct task-dependent perceptual spaces during visual decision making.
By Sheng Zhao, Weikai Lin, Yuhao Zhu
arXiv:2605.19352v2 Announce Type: replace-cross
Abstract: Understanding how humans and artificial intelligence systems predict and plan by interacting with their environment is a fundamental challeng...
By Subba Reddy Oota, Anant Khandelwal, Khushbu Pahwa, Satya Sai Srinath Namburi, Tanmoy Chakraborty, Bapi S. Raju, Manish Gupta
The paper introduces Ca2REAL, a neural-to-video framework that uses calcium imaging data from 7,863 V1 neurons to reconstruct natural movie clips. By conditioning a pretrained video diffusion model with layout and semantic controls derived from neural activity, Ca2REAL achieves 81.4% stimulus-identification accuracy and outperforms deterministic baselines in perceptual and semantic metrics. Additional tests on a virtual population of 116,705 neurons confirm that reconstruction relies on distributed, stimulus-specific population structure, with layout and semantic pathways providing complementary spatial and identity information.
By Yukai Huang, Haoyu Albert Wang, Jiawei Zhang, Jialun Ma, Jiayao Ding, Yiran Lin, Xingyu Chen, Ziqi Gao, Yuguo Yu
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.
By Matteo Dunnhofer, Christian Micheloni, Kohitij Kar
arXiv:2609.36366v1 Announce Type: cross
Abstract: Understanding how the brain parses actions and events from time-varying natural inputs is a central challenge in neuroscience. Recent work has used d...
By Iishaan Inabathini, Margaret M. Henderson
arXiv:2603.17825v2 Announce Type: replace
Abstract: In this work, we study the role of Massive Activations (MAs), which are rare, high-magnitude spikes confined to a few fixed hidden dimensions in vi...
By Xianhang Cheng, Yujian Zheng, Zhenyu Xie, Tingting Liao, Hao Li
arXiv:2511.18991v2 Announce Type: replace
Abstract: Camera-controlled video generation has attracted increasing interest for its applications in simulation, gaming, and world modeling. However, curre...
By Duolikun Danier, Ge Gao, Chengxi Zeng, Steven McDonagh, Changjian Li, Hakan Bilen, Oisin Mac Aodha