Sunyoung Hwang PRO

sosoai

·

https://sosohajalab.com

AI & ML interests

llm, vision, transformers, megabytes

Recent Activity

liked a model 1 day ago

mobilint/YOLOv5x-seg

liked a model 3 days ago

burner22/numbat

liked a model 4 days ago

summerAIO/Qwen3.8-27B-Longbook27-v2

View all activity

Organizations

upvoted a collection 8 days ago

💧 LFM3

Collection of base and post-trained LFM3 models (www.liquid.ai/blog/lfm3). • 7 items • Updated 7 days ago • 259

upvoted a collection 20 days ago

Muse Spark Open

Muse Spark Open model. A 816B parameter model with 42B Active parameters. BF16 and NVFP4 Weights. • 2 items • Updated 21 days ago • 176

upvoted an article 22 days ago

Article

ColGrep-Agent: Cutting Frontier Coding Agents’ Tokens by a Third

lightonai

•

24 days ago

• 20

upvoted a collection 2 months ago

Qwen3.8-27B — MLX, multimodal preserved

Qwen3.8-27B for Apple silicon — vision tower (333 tensors, bf16) and vendor MTP head both preserved and verified. 8-bit / 6-bit / 4-bit AWQ. • 3 items • Updated Aug 16 • 2

upvoted 3 collections 3 months ago

Ornith-1.5

19 items • Updated 14 days ago • 208

Qwen3.8

4 items • Updated Aug 13 • 606

LTX-2.5

LTX-2.5 base models, quantized models and accompanying LoRAs and IC-LoRAs • 5 items • Updated Sep 9 • 77

upvoted 3 collections 4 months ago

🌟 Antares

Agentic Models for Vulnerability Localization • 2 items • Updated Jul 21 • 63

Bonsai 27B

10 items • Updated Jul 15 • 255

Ornith-1.0

Ornith-1.0 is a family of open-source LLMs specialized for agentic coding. • 8 items • Updated Sep 20 • 394

upvoted a collection 5 months ago

Cosmos3

Omnimodal World Models for Physical AI • 6 items • Updated 16 days ago • 215

upvoted a collection 7 months ago

DeepSeek-V4

11 items • Updated 19 days ago • 953

upvoted a paper 7 months ago

Memento-Skills: Let Agents Design Agents

Paper • 2603.18743 • Published Mar 19 • 60

upvoted an article 7 months ago

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

+5

merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift

•

Apr 2

• 929

upvoted 3 collections 8 months ago

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

16 items • Updated Jul 4 • 214

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. • 25 items • Updated 8 days ago • 168

Qwen3.5

21 items • Updated Mar 9 • 1.82k

upvoted an article 10 months ago

Article

Open Responses: What you need to know

+2

evalstate, burtenshaw, merve, pcuenq

•

Jan 15

• 114

upvoted 2 collections 11 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 • 869

GLM-4.6V

3 items • Updated Dec 8, 2025 • 49