Shravan Venkatraman

shravvvv

·

https://shravfolio.vercel.app

AI & ML interests

None yet

Recent Activity

updated a model 12 days ago

authored a paper 14 days ago

Perception Before Supervision: Self-Contained Visual Distillation from Counterfactual Blind Spots

authored a paper 22 days ago

Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models

View all activity

Organizations

None yet

Papers 6

arxiv:2608.09931

arxiv:2606.27376

arxiv:2606.27373

arxiv:2511.16672

spaces 1

SAG ViT

Scale-Aware, High-Fidelity Patching with GAT for ViTs

models 3

shravvvv/CVPD

Image-Text-to-Text • Updated 12 days ago • 12

shravvvv/VISE

Image-Text-to-Text • Updated Jun 26 • 50

shravvvv/SAG-ViT

Image Classification • 6.74M • Updated Dec 8, 2024 • 21 • 1

datasets 2

shravvvv/3184

Viewer • Updated Apr 9 • 3.18k • 18

shravvvv/test_dataset

Viewer • Updated Oct 15, 2025 • 248k • 8