RewardHacking

AI & ML interests

None defined yet.

Recent Activity

xinpeng submitted a paper 1 day ago

OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation

tongliuphysics authored a paper 12 months ago

Temperature-scaling surprisal estimates improve fit to human reading times -- but does it do so for the "right reasons"?

tongliuphysics authored a paper 12 months ago

FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings

View all activity

submitted a paper to Daily Papers 1 day ago

OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation

Paper • 2610.02781 • Published 7 days ago • 8

authored 2 papers 12 months ago

Temperature-scaling surprisal estimates improve fit to human reading times -- but does it do so for the "right reasons"?

Paper • 2311.09325 • Published Nov 15, 2023

FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings

Paper • 2501.06645 • Published Jan 11, 2025

authored a paper almost 2 years ago

Multimodal Pragmatic Jailbreak on Text-to-image Models

Paper • 2409.19149 • Published Sep 27, 2024