Unchun Yang's picture

Unchun Yang

ucyang

·

https://ucyang.com/

AI & ML interests

None yet

Recent Activity

liked a dataset about 12 hours ago

KETI-AIR/kor_ag_news

liked a dataset about 12 hours ago

fancyzhx/ag_news

upvoted an article about 12 hours ago

ScreenSuite - The most comprehensive evaluation suite for GUI Agents!

View all activity

Organizations

ucyang's activity

upvoted an article about 12 hours ago

Article

ScreenSuite - The most comprehensive evaluation suite for GUI Agents!

1 day ago

• 18

upvoted 2 collections about 14 hours ago

Comma v0.1 Artifacts

A collection of artifacts related to Comma v0.1—a 7B parameter LLM trained on public domain and openly licensed text • 3 items • Updated 1 day ago • 3

Common Pile v0.1 Filtered Data

An LLM pre-training dataset produced by filtering and deduplicating the raw text collected in the Common Pile v0.1 • 31 items • Updated 1 day ago • 7

upvoted a paper about 14 hours ago

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

Paper • 2506.05209 • Published 1 day ago • 25

upvoted a collection about 14 hours ago

Common Pile v0.1

All resources related to Common Pile v0.1, an 8TB dataset of public domain and openly licensed text • 4 items • Updated 1 day ago • 13

upvoted an article about 14 hours ago

Article

Announcing the Common Pile and Comma v0.1

By

•

about 19 hours ago

• 12

upvoted 2 collections 1 day ago

Qwen3-Reranker

3 items • Updated 1 day ago • 36

Qwen3-Embedding

6 items • Updated 1 day ago • 59

upvoted a collection 2 days ago

GRMR V3 Models

An improved set of models for grammar correction. (Chat template should work, no "responding as an LLM" anymore, that kind of stuff). • 6 items • Updated 3 days ago • 9

upvoted an article 2 days ago

Article

KV Cache from scratch in nanoVLM

By

and 4 others •

3 days ago

• 55

upvoted a collection 3 days ago

Teuken-7B-v0.4

OpenGPT-X Teuken 7B models trained on 4 trillion tokens • 4 items • Updated Dec 6, 2024 • 4

upvoted a collection 5 days ago

Gemma 3n Preview

2 items • Updated 8 days ago • 111

upvoted 3 collections 7 days ago

Pinecone Inference

Models available in the Inference API • 2 items • Updated Sep 9, 2024 • 2

MiMo

6 items • Updated 8 days ago • 5

MiMo-VL

2 items • Updated 8 days ago • 25

upvoted a paper 9 days ago

Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Paper • 2504.19413 • Published Apr 28 • 17

upvoted a paper 11 days ago

Shifting AI Efficiency From Model-Centric to Data-Centric Compression

Paper • 2505.19147 • Published 13 days ago • 144

upvoted a paper 14 days ago

Emerging Properties in Unified Multimodal Pretraining

Paper • 2505.14683 • Published 18 days ago • 129

upvoted an article 14 days ago

Article

🥬 LettuceDetect Goes Multilingual: Fine-tuning EuroBERT on Synthetic Translations

By

and 1 other •

19 days ago

• 9

upvoted a collection 14 days ago

RAGTruth LLM Translations

This collection includes our translated training data that we've used to create multilingual hallucination detection models. • 8 items • Updated 20 days ago • 3