Gyanateet Dutta's picture

Gyanateet Dutta

Ryukijano

·

https://ryukijano.github.io

AI & ML interests

Computer Graphics, General Artificial Intelligence,model merging, massive ASR for data collection, 3D ML, on-device ML, quantization, model judging, ML in browser, healthcare applications, education, intersection of art and ML.

Recent Activity

upvoted a paper 3 days ago

Reinforcement Learning for Reasoning in Large Language Models with One Training Example

liked a model 7 days ago

cognitivecomputations/dolphin-2.8-gemma-7b

upvoted a paper 14 days ago

WORLDMEM: Long-term Consistent World Simulation with Memory

View all activity

Organizations

Ryukijano's activity

upvoted a paper 3 days ago

Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Paper • 2504.20571 • Published 4 days ago • 74

upvoted a paper 14 days ago

WORLDMEM: Long-term Consistent World Simulation with Memory

Paper • 2504.12369 • Published 17 days ago • 30

upvoted a paper 21 days ago

DDT: Decoupled Diffusion Transformer

Paper • 2504.05741 • Published 25 days ago • 73

upvoted a paper 25 days ago

VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks

Paper • 2504.05118 • Published 26 days ago • 25

upvoted a collection 27 days ago

TxGemma Release

Collection of open models to accelerate the development of therapeutics. • 5 items • Updated about 1 month ago • 52

upvoted a paper 29 days ago

Differential Transformer

Paper • 2410.05258 • Published Oct 7, 2024 • 178

upvoted a paper about 1 month ago

Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data

Paper • 2503.21694 • Published Mar 27 • 16

upvoted a collection about 1 month ago

💫StarVector Models

StarVector is a multimodal LLM for Scalable Vector Graphics (SVG) generation, producing structured SVG code directly from images and text. • 2 items • Updated Mar 20 • 93

upvoted an article 3 months ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.23k

upvoted a collection 3 months ago

Eagle 2

Eagle 2 is a family of frontier vision-language models with vision-centric design. The model supports 4K HD input, long-context video, and grounding. • 9 items • Updated 10 days ago • 35

upvoted a collection 5 months ago

VILA: On Pre-training for Visual Language Models

10 items • Updated 17 days ago • 53

upvoted a paper 5 months ago

LLaVA-o1: Let Vision Language Models Reason Step-by-Step

Paper • 2411.10440 • Published Nov 15, 2024 • 125

upvoted a paper 6 months ago

Grounding Image Matching in 3D with MASt3R

Paper • 2406.09756 • Published Jun 14, 2024 • 1

upvoted 3 collections 6 months ago

Sparsh

Models and datasets for Sparsh: Self-supervised touch representations for vision-based tactile sensing • 15 items • Updated Oct 24, 2024 • 12

MobileLLM

Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905 • 9 items • Updated Nov 27, 2024 • 113

Stable Diffusion 3.5

6 items • Updated Jan 9 • 158

upvoted a paper 7 months ago

Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention

Paper • 2410.10774 • Published Oct 14, 2024 • 26