Sunyoung Hwang's picture

Sunyoung Hwang PRO

sosoai

·

https://sosohajalab.com

AI & ML interests

llm, vision, transformers, megabytes

Recent Activity

liked a model about 14 hours ago

mlx-community/Qwen3.6-35B-A3B-4bit

liked a model about 14 hours ago

mlx-community/Qwen3.6-35B-A3B-mxfp4

liked a model about 15 hours ago

mlx-community/Qwen3.6-35B-A3B-nvfp4

View all activity

Organizations

upvoted a paper 2 days ago

Memento-Skills: Let Agents Design Agents

Paper • 2603.18743 • Published 29 days ago • 57

upvoted an article 15 days ago

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

+5

16 days ago

•

854

upvoted a collection 24 days ago

Qwen3.5-Claude-4.6-Opus-Reasoning-Distilled

18 items • Updated 7 days ago • 202

upvoted a collection about 1 month ago

MiroThinker-1.7

2 items • Updated Mar 11 • 55

upvoted 2 collections about 2 months ago

Qwen3.5

Qwen3.5 is Qwen's new model family including Qwen3.5 Small: 0.8B, 2B, 4B, 9B and Qwen3.5 Medium: 35B-A3B, 27B, 122B-A10B and 397B-A17B. • 26 items • Updated about 22 hours ago • 151

Qwen3.5

21 items • Updated Mar 9 • 1.53k

upvoted an article 3 months ago

Article

Open Responses: What you need to know

+2

Jan 15

•

111

upvoted 2 collections 4 months ago

DINOv3

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 15 items • Updated Mar 10 • 595

GLM-4.6V

3 items • Updated Dec 8, 2025 • 49

upvoted 2 collections 5 months ago

Ministral 3

A collection of edge models, with Base, Instruct and Reasoning variants, in 3 different sizes: 3B, 8B and 14B. All with vision capabilities. • 9 items • Updated Dec 2, 2025 • 165

OpenMMReasoner

5 items • Updated Nov 24, 2025 • 12

upvoted an article 5 months ago

Article

Supercharge your OCR Pipelines with Open Models

+5

Oct 21, 2025

•

308

upvoted a collection 6 months ago

Nemotron RAG

Set of tools to build retrieval-augmented generation (RAG) systems, improve search and ranking accuracy, and extract structured data from complex docs • 9 items • Updated 2 days ago • 86

upvoted an article 6 months ago

Article

LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR

Oct 23, 2025

•

73

upvoted a collection 6 months ago

Qwen3-VL

58 items • Updated Mar 2 • 16

upvoted 4 collections 7 months ago

Granite 4.0 Language Models

Efficient language models for multilingual generation, coding, RAG, and AI assistant workflows. • 11 items • Updated 15 days ago • 216

Qwen3-VL

37 items • Updated Dec 31, 2025 • 696

Granite Docling Models

Models for parsing complex PDFs and structured documents, designed to complement Docling. • 4 items • Updated 16 days ago • 60

Qwen3

21 items • Updated Apr 29, 2025 • 31

upvoted a paper 8 months ago

rStar2-Agent: Agentic Reasoning Technical Report

Paper • 2508.20722 • Published Aug 28, 2025 • 118