The paper proposes an objective-wise reputation-market mechanism to dynamically calibrate and gate LLM-generated expert priors in multi-objective Bayesian optimization, showing that dynamic calibratio…

The paper introduces Posterior Hybrid Bayesian Belief (PhyB), a novel framework that reformulates policy optimization in Bayesian Offline RL by approximating expectations as a convex combination over…

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 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 proposes BaSE, a multi-armed bandit approach, to optimally allocate a fixed budget of LLM calls across parallel evolutionary search trajectories, significantly improving mean fitness and rel…

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 proposes graph-coupled causal Bayesian optimization, a method that improves efficiency by sharing information across related interventions through a shared set of causal parameters.

The paper proposes S2L-PO, a framework that uses smaller, naturally diverse models as structured explorers to enhance the policy-level diversity and performance of larger language models during traini…

The paper proposes a novel Bayesian framework to learn the optimal decision strategy for the stochastic shortest path problem by directly constructing the posterior beliefs for the action-value functi…

The paper proposes ProRL, an effective Reinforcement Learning framework that rectifies gradient estimation deficiencies to optimize proactive recommendation paths, significantly outperforming existing…

Taiji is a novel LLM-as-Enhancer framework that optimizes recommender systems by addressing the challenges of generating high-quality reasoning data and balancing semantic and ID-based rewards.

The paper proposes a novel online learning algorithm that achieves an interval regret bound scaling with gradient variation, providing strong theoretical guarantees for non-stationary environments.

ParetoPilot introduces a novel zero-surrogate diffusion framework for offline multi-objective optimization, achieving state-of-the-art performance by directly guiding the generation process without re…

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…

The paper proposes Hysteretic Policy Optimization (HPO) and its adaptive variant (A-HPO) to stabilize reinforcement learning training in sparse-reward environments by better balancing positive and neg…

The paper proposes FedVPA-GP, a federated learning framework that uses a Gumbel-Softmax prior and orthogonal loss to personalize LLM alignment by disentangling conflicting user preferences while maint…

The paper proposes 2FFS, a two-fidelity tree-search algorithm that efficiently identifies the best action in stochastic minimax trees by adaptively combining cheap, biased heuristic evaluations with e…

The paper analyzes the performance of an annealed softmax policy in a Bayesian bandit setting, proving that under specific prior conditions, it achieves near-optimal regret rates by effectively sampli…