kansal's picture

7 5

kansal PRO

akansal

·

AI & ML interests

None yet

Recent Activity

upvoted an article 3 days ago

NanoVDR: A 70M Text-Only Model That Retrieves Visual Documents as Well as a 2B VLM

upvoted an article 13 days ago

Introducing Modular Diffusers - Composable Building Blocks for Diffusion Pipelines

upvoted an article about 1 month ago

Training Design for Text-to-Image Models: Lessons from Ablations

View all activity

Organizations

liked a model about 2 months ago

WithAnyone/WithAnyone

Text-to-Image • Updated Oct 20, 2025 • 26

liked a Space 2 months ago

FinePDFs: Liberating 3T of the finest tokens from PDFs

liked a model 4 months ago

jingheya/Lotus-2

Depth Estimation • Updated Dec 10, 2025 • 9

liked 2 models 5 months ago

PaddlePaddle/PaddleOCR-VL

Image-Text-to-Text • 1.0B • Updated 2 days ago • 8.16k • 1.57k

nvidia/omni-embed-nemotron-3b

Feature Extraction • 5B • Updated Oct 9, 2025 • 2.35k • 97