7 58 368

Junyeong Song

junyeong-nero

https://junyeong-nero.github.io/portfolio/

AI & ML interests

Synthetic Data / OCR / Image-Generation

Recent Activity

upvoted a paper 1 day ago

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

liked a model 4 days ago

zai-org/GLM-5.1

upvoted a paper 4 days ago

Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision

View all activity

Organizations

None yet

upvoted a paper 1 day ago

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Paper • 2604.06628 • Published 5 days ago • 240

liked a model 4 days ago

zai-org/GLM-5.1

Text Generation • 754B • Updated about 13 hours ago • 28.8k • • 1.04k

upvoted 2 papers 4 days ago

Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision

Paper • 2604.04934 • Published 7 days ago • 39

Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents

Paper • 2604.06132 • Published 6 days ago • 110

liked a dataset 5 days ago

seongsubae/KorMedMCQA-V

Viewer • Updated Feb 17 • 1.84k • 103 • 7

upvoted a paper 6 days ago

Self-Distilled RLVR

Paper • 2604.03128 • Published 10 days ago • 154

updated a model 7 days ago

junyeong-nero/tiny-sd-models

Updated 7 days ago • 1

liked a model 7 days ago

netflix/void-model

Video-to-Video • Updated 6 days ago • 770

liked a model 9 days ago

google/gemma-4-31B-it

Image-Text-to-Text • 33B • Updated 2 days ago • 2.24M • • 1.76k

liked a model 11 days ago

nvidia/nemotron-ocr-v2

Image-to-Text • Updated 2 days ago • 655 • 112

upvoted a paper 17 days ago

UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience

Paper • 2603.24533 • Published 18 days ago • 47

upvoted a paper 19 days ago

Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs

Paper • 2603.16932 • Published 29 days ago • 86

liked a model 19 days ago

baidu/Qianfan-OCR

Image-Text-to-Text • 5B • Updated 17 days ago • 44.8k • 1.14k

liked a model 20 days ago

rednote-hilab/dots.mocr

Image-Text-to-Text • 3B • Updated 23 days ago • 92.6k • 95

reactedto Shrijanagain's post with 🔥 23 days ago

Post

5461

Surya-1.1T: Scaling Beyond Human-Level Reasoning via 146 Trillion Token Pre-training
Author: SKT AI LABS
Affiliation: SKT AI Labs / Project Surya
Model Architecture: Optimized Dense Transformer
Parameters: 1.1 Trillion
Training Tokens: 146 Trillion

Wanna collaborate us Friends let's Start Journey we have Collected 146 trillon tokens and done pre training but we need to made more powerfull

Whitepaper - https://github.com/SHRIJANAGAIN/PROFF