Vatsal Agarwal

vatsalag's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 7 days ago

OneVision-Encoder

Collection

HEVC-Style Vision Transformer • 2 items • Updated 10 days ago • 3

upvoted a paper 8 days ago

Implicit Neural Representation Facilitates Unified Universal Vision Encoding

Paper • 2601.14256 • Published about 1 month ago • 7

upvoted a collection 8 days ago

HUVR

Collection

Vision unified representation model with standard and compressed features for classification, generation, and more: https://arxiv.org/abs/2601.14256 • 4 items • Updated 27 days ago • 5

upvoted a paper 7 months ago

Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognition

Paper • 2508.03695 • Published Aug 5, 2025 • 1

commented a paper 7 months ago

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor

Paper • 2507.07106 • Published Jul 9, 2025 • 2 •

1

authored 4 papers 7 months ago

Do text-free diffusion models learn discriminative visual representations?

Paper • 2311.17921 • Published Nov 29, 2023 • 1

Diffusion Models Beat GANs on Image Classification

Paper • 2307.08702 • Published Jul 17, 2023 • 19

LEIA: Latent View-invariant Embeddings for Implicit 3D Articulation

Paper • 2409.06703 • Published Sep 10, 2024 • 3

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor

Paper • 2507.07106 • Published Jul 9, 2025 • 2

updated a model over 1 year ago

vatsalag/romeo-the-dog

Text-to-Image • Updated Oct 26, 2024

updated a dataset over 1 year ago

vatsalag/tech_research2024

Viewer • Updated Oct 26, 2024 • 3 • 10

updated 2 models over 2 years ago

vatsalag/bob-the-bagel-guy

Text-to-Image • Updated Oct 22, 2023

vatsalag/bagel-guy

Text-to-Image • Updated Oct 21, 2023