Yingtian (David) Tang

🚨 NEW PREPRINT Videos strongly shape activity across the visual cortex. But can we design videos that maximally drive specific brain regions? We present NEvo 🧬🧠 — a neural-guided evolutionary framework that synthesizes videos to maximally activate target visual ROIs. (1/10)

Acknowledgments w/ Ming Zhou, Sogand Salehi, Amir Zamir, @lisik.bsky.social , @mschrimpf.bsky.social (10/10)

🚨 NEW PREPRINT Videos strongly shape activity across the visual cortex. But can we design videos that maximally drive specific brain regions? We present NEvo 🧬🧠 — a neural-guided evolutionary framework that synthesizes videos to maximally activate target visual ROIs. (1/10)

Controlled test: fix a non-naturalistic image anchor (two plasticine discs 🟢🟣), optimize only motion. Target pSTS → faces and coordinated interaction emerge Target MT → pure translation/oscillation, no social content Same anchor. Different content. (8/10)

🚨 NEW PREPRINT Videos strongly shape activity across the visual cortex. But can we design videos that maximally drive specific brain regions? We present NEvo 🧬🧠 — a neural-guided evolutionary framework that synthesizes videos to maximally activate target visual ROIs. (1/10)

Beyond fixed ROIs, NEvo runs as a searchlight 🔦 scoring overlapping cortical patches along a continuous cortical trajectory. We recover a clean lateral stream gradient: texture (V1) → motion/interaction (EBA/pSTS) → social scenes (aSTS) (6/10)

🚨 NEW PREPRINT Videos strongly shape activity across the visual cortex. But can we design videos that maximally drive specific brain regions? We present NEvo 🧬🧠 — a neural-guided evolutionary framework that synthesizes videos to maximally activate target visual ROIs. (1/10)

Two design choices matter: 1️⃣ **Two-stage search**: optimize a static anchor image first, then animate it → much more sample-efficient. 2️⃣ **Multi-block V-JEPA 2 features**: each voxel selects its best-predicting block → hierarchical feature modeling (4/10)

🚨 NEW PREPRINT Videos strongly shape activity across the visual cortex. But can we design videos that maximally drive specific brain regions? We present NEvo 🧬🧠 — a neural-guided evolutionary framework that synthesizes videos to maximally activate target visual ROIs. (1/10)

🔗 Website: nevo-project.epfl.ch 📄 arXiv: arxiv.org/abs/2607.02317 🤗 Model card: huggingface.co/epfl-neuroai... (2/10)

🧠🎬 RELEASE We are releasing two Hugging Face model cards for video brain encoding. 🎥 short video clips → 🧠 brain responses MODEL 1: vjepa2-basic
🔗 huggingface.co/epfl-neuroai... MODEL 2: vjepa2-enhanced
🔗 huggingface.co/epfl-neuroai... Brain encoders. Off the shelf !

3/ ⚡ MODEL INPUT / OUTPUT Both models are trained on 3-sec video fMRI data. Input: short video clips
Output: normalized fsaverage5 cortical responses across both hemispheres 20,484 mesh vertices. Short video in.
Whole-cortex prediction out.

🧠🎬 RELEASE We are releasing two Hugging Face model cards for video brain encoding. 🎥 short video clips → 🧠 brain responses MODEL 1: vjepa2-basic
🔗 huggingface.co/epfl-neuroai... MODEL 2: vjepa2-enhanced
🔗 huggingface.co/epfl-neuroai... Brain encoders. Off the shelf !

🧠 NEW PREPRINT Many-Two-One: Diverse Representations Across Visual Pathways Emerge from A Single Objective www.biorxiv.org/content/10.1...

8/🖼️ Big Picture
 Optimizing to model world dynamics leads to brain-like representations.
 🧠 The visual system isn't a patchwork of modules — it’s a unified system built on shared core principles.

🧠 NEW PREPRINT Many-Two-One: Diverse Representations Across Visual Pathways Emerge from A Single Objective www.biorxiv.org/content/10.1...

6/🌀 Finding 3 Putting observations together:
 • Single-objective models align with all regions and behaviors • Cortex shows hybrid, smooth representation transitions 💡 A new perspective: the brain may implement a shared feature backbone — reused for diverse tasks, just like a “foundation model”.

🧠 NEW PREPRINT Many-Two-One: Diverse Representations Across Visual Pathways Emerge from A Single Objective www.biorxiv.org/content/10.1...

4/🌐 Finding 2.1
 So, what does the brain actually compute during dynamic vision? Across 10 cognitive tasks (e.g., pose, social cues, action), just two suffice to explain brain-like representations: • Object form • Appearance-free motion

🧠 NEW PREPRINT Many-Two-One: Diverse Representations Across Visual Pathways Emerge from A Single Objective www.biorxiv.org/content/10.1...

2/🧪 Approach
 We benchmarked diverse video models, each with a different pretraining objective.
 Then: tested how well they predict human fMRI responses to natural movies.
 🧠 ~10,000 voxels, whole visual system.

🧠 NEW PREPRINT Many-Two-One: Diverse Representations Across Visual Pathways Emerge from A Single Objective www.biorxiv.org/content/10.1...

🚨 New research: Can the brain's complex visual system — ventral & dorsal processing streams — arise from a single goal? We study dynamic vision and reveal how object and motion recognition — long thought to be separate — could emerge from the same underlying goal.