AMPO: Active Multi-Preference Optimization
Paper
•
2502.18293
•
Published
•
1
Taneesh Gupta
gupta-tanish
·
AI & ML interests
Post-Training @MicrosoftResearch
Recent Activity
updated
a dataset
about 6 hours ago
gupta-tanish/llama3-8b-instruct-on-policy-noise-std-2.0
updated
a dataset
about 6 hours ago
gupta-tanish/llama3-8b-instruct-on-policy-noise-std-1.0
updated
a dataset
about 6 hours ago
gupta-tanish/llama3-8b-instruct-on-policy-noise-std-0.5
Organizations
None yet
upvoted
a
paper
5 months ago