MODPO

non-profit

ZHZisZZ

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

jieliu authored a paper 6 months ago

DDK: Distilling Domain Knowledge for Efficient Large Language Models

ZHZisZZ authored a paper 7 months ago

Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level

jieliu authored a paper 7 months ago

Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!

View all activity

MODPO's activity

jieliu

authored a paper 6 months ago

DDK: Distilling Domain Knowledge for Efficient Large Language Models

Paper • 2407.16154 • Published Jul 23, 2024 • 22

ZHZisZZ

authored a paper 7 months ago

Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level

Paper • 2406.11817 • Published Jun 17, 2024 • 13

jieliu

authored 4 papers 7 months ago

Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!

Paper • 2402.12343 • Published Feb 19, 2024

Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization

Paper • 2310.03708 • Published Oct 5, 2023

Inception Convolution with Efficient Dilation Search

Paper • 2012.13587 • Published Dec 25, 2020

Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level

Paper • 2406.11817 • Published Jun 17, 2024 • 13