🔄 In a Training Loop

Gyanateet Dutta

Ryukijano

·

https://ryukijano.github.io

AI & ML interests

Computer Vision, Robotics, Generative modelling, AI for Sciences.

Recent Activity

updated a Space 1 day ago

Ryukijano/CatCon-One-Shot-Controlnet-SD-1-5-b2

upvoted a paper 4 days ago

Vision Pretraining for Dense Spatial Perception

liked a model 7 days ago

SEU-PAISys/Embodied.cpp

View all activity

Organizations

upvoted a paper 4 days ago

Vision Pretraining for Dense Spatial Perception

Paper • 2607.05247 • Published 7 days ago • 42

upvoted 5 papers 14 days ago

UniSurg: A Video-Native Foundation Model for Universal Understanding of Surgical Videos

Paper • 2602.05638 • Published Feb 5 • 9

PhysVideoGenerator: Towards Physically Aware Video Generation via Latent Physics Guidance

Paper • 2601.03665 • Published Jan 7 • 1

Action100M: A Large-scale Video Action Dataset

Paper • 2601.10592 • Published Jan 15 • 33

Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers

Paper • 2509.24317 • Published Sep 29, 2025 • 12

JEPA-VLA: Video Predictive Embedding is Needed for VLA Models

Paper • 2602.11832 • Published Feb 12 • 1

upvoted a paper 24 days ago

Kairos: A Native World Model Stack for Physical AI

Paper • 2606.16533 • Published 27 days ago • 38

upvoted a collection 28 days ago

VLA-JEPA

VLA-JEPA model checkpoints (LIBERO, Pretrain, SimplerEnv) • 3 items • Updated May 28 • 15

upvoted a paper about 1 month ago

SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer

Paper • 2605.30409 • Published May 28 • 42

upvoted a paper about 2 months ago

World Action Models: The Next Frontier in Embodied AI

Paper • 2605.12090 • Published May 12 • 69

upvoted 3 papers 2 months ago

Generative Modeling with Orbit-Space Particle Flow Matching

Paper • 2605.02222 • Published May 4 • 9

JEPA-T: Joint-Embedding Predictive Architecture with Text Fusion for Image Generation

Paper • 2510.00974 • Published Oct 1, 2025 • 1

PDE-Transformer: Efficient and Versatile Transformers for Physics Simulations

Paper • 2505.24717 • Published May 30, 2025 • 1

upvoted 3 collections 2 months ago

P3D

Datasets and pre-trained P3D models. • 3 items • Updated Apr 11 • 1

MolmoAct2 Models

Collection of the base models for MolmoAct2 • 6 items • Updated May 5 • 23

MolmoAct2 Datasets

Collection of robotics datasets for MolmoAct2 • 10 items • Updated Jun 9 • 13

upvoted 4 collections 3 months ago

Lyra

Project Lyra: Open Generative 3D World Models • 6 items • Updated Jun 12 • 12

NVIDIA Ising

NVIDIA Ising is a new Model Family to enable building useful Quantum Computers with AI. • 4 items • Updated Jun 12 • 27

SigLino: Vision Foundation Models (SigLIP2 + DINOv3)

Vision encoders distilled from DINOv3 and SigLIP2 (MoE & Dense). CVPR 2026. • 6 items • Updated Apr 10 • 17

WildDet3D

This is the collection of WildDet3D artifacts, including demos, model checkpoints and data. https://github.com/allenai/WildDet3D • 8 items • Updated Apr 13 • 20