This paper studies a dynamic assortment problem on a two-sided service platform with incomplete information and heterogeneous customers, and develops a data-driven algorithm to learn parameters and op…

The paper proposes Reasoning-Conditioned Direct Preference Optimization (RC-DPO) to effectively mitigate hallucinations in multimodal large reasoning models by explicitly conditioning the preference o…

The paper proposes a novel, explicitly exploratory iterative Nash Learning from Human Feedback (NLHF) algorithm that achieves strong regret bounds for optimizing LLMs based on complex, non-scalar huma…

S-SPPO introduces a dual-space semantic calibration framework to stabilize Self-Play Preference Optimization (SPPO), preventing policy degeneration when preference oracles assign overly confident wins…

This paper presents a polynomial-time algorithm for recovering item values in the fractional knapsack problem using comparison queries, and provides a lower bound.

This paper analyzes Best-of-$N$ preference data, deriving explicit reward targets for independent-reference variants and establishing design principles for choosing $N$ and the base distribution to op…

The paper introduces the Markov decision contest, a new framework for reinforcement learning using pairwise preferences, and proves that stationary Markov policies are optimal and solvable efficiently…

The paper introduces Drifting Preference Optimization (DrPO), an efficient online method for preference finetuning one-step text-to-image generators that avoids complex gradient calculations and model…

The paper introduces local Preferential Bayesian Optimization (PBO) methods that adapt high-dimensional Bayesian Optimization techniques, such as trust-region and derivative-informed local search, to…

The paper introduces DPPrefSyn, a novel algorithm that generates differentially private synthetic preference data, enabling privacy-preserving alignment of large language models.

The paper introduces DPPrefSyn, a novel algorithm that generates differentially private synthetic preference data, enabling privacy-preserving alignment of large language models.

The paper analyzes preference-shaped expected improvement criteria for Bayesian multiobjective optimization, precisely characterizing when transformations preserve key properties like exact computatio…

The paper proposes In-Context Reward Adaptation, a transformer-based framework that uses in-context learning and auxiliary signals (like human response time) to robustly model diverse and unseen human…

The paper establishes conditions for QUBO formulations of combinatorial optimization problems that guarantee valid binary and feasible local minimizers using gradient-based methods.

This paper presents PermR, a lightweight algorithm for reranking search results in e-commerce platforms to maximize revenue while preserving relevance and other constraints.

The paper develops a general framework for dynamic consistent submodular maximization, achieving constant-factor approximations with sublinear consistency for both cardinality and rank-$k$ matroid con…