activity
20192026
most citedAn Experimental Comparison of Old and New Decision Tree Algorithms

13 citations · 28 across the 6 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

CM-DPO: Constraint-Margin Direct Preference Optimization for LLM Planning

Rabimba Karanjai, Qun Gu, Hemanth Hegadehalli Madhavarao +8

Direct Preference Optimization (DPO) treats all constraint violations equally: a 1,000 overshoot induce the same training signal. It is also susceptible…