Gyanateet Dutta's picture

Gyanateet Dutta

Ryukijano

·

https://ryukijano.github.io

AI & ML interests

Computer Vision, Robotics, Generative modelling,ML in browser, healthcare applications, intersection of art and ML.

Recent Activity

liked a dataset 3 days ago

builddotai/Egocentric-10K

liked a model 11 days ago

CompVis/DisMo

upvoted an article 15 days ago

Why You Should Care About Partial Differential Equations (PDEs)

View all activity

Organizations

liked a dataset 3 days ago

builddotai/Egocentric-10K

Updated 14 days ago • 103k • 285

liked a model 11 days ago

CompVis/DisMo

Updated 26 days ago • 4

upvoted an article 15 days ago

Article

Why You Should Care About Partial Differential Equations (PDEs)

16 days ago

•

33

liked a model 26 days ago

polymathic-ai/walrus

Updated Nov 20 • 16

updated a model 28 days ago

Ryukijano/vjepa-nested-agent-l40

Robotics • 0.3B • Updated 28 days ago • 17

published a model 28 days ago

Ryukijano/vjepa-nested-agent-l40

Robotics • 0.3B • Updated 28 days ago • 17

liked a model about 2 months ago

moonshotai/Kimi-K2-Thinking

Text Generation • Updated Nov 8 • 396k • • 1.57k

upvoted a paper about 2 months ago

Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning

Paper • 2510.27606 • Published Oct 31 • 28

liked a model about 2 months ago

nvidia/Lyra

Updated Sep 24 • 65 • 31

updated a collection about 2 months ago

Deep Reinforcement Learning

Features implementations and paces of popular RL algorithms and new paradigms on a variety of environments. • 7 items • Updated Nov 4

upvoted a paper about 2 months ago

π_RL: Online RL Fine-tuning for Flow-based Vision-Language-Action Models

Paper • 2510.25889 • Published Oct 29 • 64

liked a model 2 months ago

vandijklab/C2S-Scale-Gemma-2-27B

Text Generation • 28B • Updated Oct 31 • 863 • 154

upvoted a paper 2 months ago

Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training

Paper • 2510.12586 • Published Oct 14 • 108

liked a Space 3 months ago

Wan2.2 14B Fast

generate a video from an image with a text prompt

liked 3 models 3 months ago

facebook/map-anything

Image-to-3D • 1B • Updated 8 days ago • 29.6k • 66

facebook/cwm

33B • Updated Oct 15 • 134k • 253

nvidia/AMPLIFY_350M

Fill-Mask • 0.4B • Updated Sep 26 • 81 • 7

updated a collection 3 months ago

LLMs

42 items • Updated Sep 25

liked a model 3 months ago

facebook/cwm-pretrain

33B • Updated Oct 15 • 19 • 20

upvoted an article 4 months ago

Article

SAIR: Accelerating Pharma R&D with AI-Powered Structural Intelligence

Sep 2

•

35