ucyang (Unchun Yang)

upvoted a paper 6 days ago

Watermark Anything with Localized Messages

Paper • 2411.07231 • Published 10 days ago • 19

upvoted an article 7 days ago

Article

Releasing the largest multilingual open pretraining dataset

By

•

8 days ago

• 94

upvoted a paper 9 days ago

Large Scale Transfer Learning for Tabular Data via Language Modeling

Paper • 2406.12031 • Published Jun 17 • 9

upvoted a collection 9 days ago

TabuLa-8B

Collection

Training, eval suite, and model from the paper "Large Scale Transfer Learning for Tabular Data via Language Modeling" https://arxiv.org/abs/2406.12031 • 4 items • Updated Jun 19 • 10

upvoted a paper 9 days ago

MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens

Paper • 2406.11271 • Published Jun 17 • 20

upvoted 4 collections 9 days ago

upvoted a paper 9 days ago

Baichuan-Omni Technical Report

Paper • 2410.08565 • Published Oct 11 • 84

upvoted a collection 11 days ago

Switch-Transformers release

Collection

This release included various MoE (Mixture of expert) models, based on the T5 architecture . The base models use from 8 to 256 experts. • 9 items • Updated Jul 31 • 15

upvoted a paper 15 days ago

Adaptive Caching for Faster Video Generation with Diffusion Transformers

Paper • 2411.02397 • Published 17 days ago • 20

upvoted a paper 17 days ago

JudgeBench: A Benchmark for Evaluating LLM-based Judges

Paper • 2410.12784 • Published Oct 16 • 42

upvoted a collection 17 days ago

OuteTTS

Collection

2 items • Updated 17 days ago • 10

upvoted a paper 19 days ago

LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning

Paper • 2410.02884 • Published Oct 3 • 50

upvoted a collection 19 days ago

Model Depot

Collection

Leading generative models packaged in OpenVino format optimized for use on AI PCs • 50 items • Updated 24 days ago • 5

upvoted a collection 20 days ago

Functionary V3.2

Collection

Fine-tuning Llama-3.1 using own our prompt template for function calling • 3 items • Updated Oct 16 • 1

upvoted a collection 21 days ago

SmolLM2

Collection

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 8 items • Updated 17 days ago • 171

upvoted a paper 21 days ago

Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages

Paper • 2410.16153 • Published about 1 month ago • 42

upvoted a collection 21 days ago

Pangea

Collection

A Fully Open Multilingual Multimodal LLM for 39 Languages • 18 items • Updated 19 days ago • 17

Unchun Yang

AI & ML interests

Organizations

ucyang's activity

Watermark Anything with Localized Messages

Releasing the largest multilingual open pretraining dataset

Large Scale Transfer Learning for Tabular Data via Language Modeling

TabuLa-8B

MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens

🍃 MINT-1T

🍷 FineWeb datasets

📚 FineWeb-Edu

INTELLECT-1 Dataset

Baichuan-Omni Technical Report

Switch-Transformers release

Adaptive Caching for Faster Video Generation with Diffusion Transformers

JudgeBench: A Benchmark for Evaluating LLM-based Judges

OuteTTS

LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning

Model Depot

Functionary V3.2

SmolLM2

Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages

Pangea