NeurIPS 2025 "preference modeling" Papers
4 papers found
Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs
Mehran Shakerinava, Siamak Ravanbakhsh, Adam Oberman
NeurIPS 2025spotlightarXiv:2505.12049
Efficient and Near-Optimal Algorithm for Contextual Dueling Bandits with Offline Regression Oracles
Aadirupa Saha, Robert Schapire
NeurIPS 2025poster
Generalized Top-k Mallows Model for Ranked Choices
Shahrzad Haddadan, Sara Ahmadian
NeurIPS 2025spotlightarXiv:2510.22040
Pairwise Calibrated Rewards for Pluralistic Alignment
Daniel Halpern, Evi Micha, Ariel Procaccia et al.
NeurIPS 2025posterarXiv:2506.06298