UCLA Artificial General Intelligence Lab

university

thughost

AI & ML interests

None defined yet.

Recent Activity

angelahzyuan authored a paper about 2 months ago

Accelerated Preference Optimization for Large Language Model Alignment

angelahzyuan authored a paper about 2 months ago

MARS: Unleashing the Power of Variance Reduction for Training Large Models

thughost authored a paper about 2 months ago

MARS: Unleashing the Power of Variance Reduction for Training Large Models

View all activity

Collections 4

spaces 1

SPIN Diffusion Demo V1

models 17

UCLA-AGI/Gemma-2-9B-It-SPPO-Iter1

Text Generation • Updated Jul 1, 2024 • 5.7k • 3

UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2

Text Generation • Updated Jul 1, 2024 • 7.99k • 2

UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3

Text Generation • Updated Jul 1, 2024 • 8.81k • 119

UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3

Text Generation • Updated Jun 28, 2024 • 6.31k • 79

UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter2

Text Generation • Updated Jun 25, 2024 • 6.39k

UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter1

Text Generation • Updated Jun 25, 2024 • 4.5k • 1

UCLA-AGI/Mistral7B-PairRM-SPPO

Text Generation • Updated May 7, 2024 • 3.98k • 6

UCLA-AGI/Mistral7B-PairRM-SPPO-Iter3

Text Generation • Updated May 7, 2024 • 6.4k • 5

UCLA-AGI/Mistral7B-PairRM-SPPO-Iter1

Text Generation • Updated May 6, 2024 • 3.26k • 2

UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2

Text Generation • Updated May 6, 2024 • 6.4k • 1

datasets 7

UCLA-AGI/data-mistral-7b-instruct-sppo-iter3

Viewer • Updated Jun 17, 2024 • 20k • 73 • 2

UCLA-AGI/data-mistral-7b-instruct-sppo-iter2

Viewer • Updated Jun 17, 2024 • 20k • 81 • 2

UCLA-AGI/data-mistral-7b-instruct-sppo-iter1

Viewer • Updated Jun 16, 2024 • 19.8k • 136 • 2

UCLA-AGI/SPIN_iter3

Viewer • Updated Apr 4, 2024 • 50.3k • 33 • 9

UCLA-AGI/SPIN_iter2

Viewer • Updated Apr 4, 2024 • 50.3k • 59 • 1

UCLA-AGI/SPIN_iter1

Viewer • Updated Apr 4, 2024 • 50.3k • 58 • 3

UCLA-AGI/SPIN_iter0

Viewer • Updated Feb 9, 2024 • 50.3k • 124 • 8