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 conducts a runtime analysis of the Strength Pareto Evolutionary Algorithm 2 (SPEA2) and proposes an improved variant, SPEA2$^+$, to address its limitations in handling dominated solutions.

The paper introduces hybrid neural world models that provide fast, multi-horizon predictions for complex physical dynamics, implicitly handling sharp events like shocks and contacts without explicit t…

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 a unified theoretical framework for gradient aggregation in multi-objective optimization, establishing convergence rates and sufficient conditions for achieving Pareto stationarit…

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

The paper proposes a feasible-reward-set framework to perform Inverse Reinforcement Learning (IRL) when data comes from multiple imperfect demonstrators, providing theoretical guarantees and practical…

The paper demonstrates that Low-Rank Adaptation (LoRA) is an effective and superior method for adapting large, pretrained Transformer surrogates for automotive aerodynamics to new vehicle families usi…

This paper demonstrates that a complex deep reinforcement learning policy for power grid control can be successfully distilled into a lightweight, auditable decision tree and random forest surrogate t…

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…

This review surveys advanced techniques—including generative models, multimodal learning, and closed-loop workflows—for automated inverse materials design, enabling the targeted discovery of novel cry…

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…

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 unified, constrained optimization framework using KL divergence and likelihood constraints to achieve effective and principled unlearning in diffusion models.

DASH introduces a dual-branch distillation framework to effectively compress class-conditional diffusion models by independently supervising both score branches, significantly preserving guidance fide…

The paper introduces Multifidelity Proper Orthogonal Decomposition (MFPOD), a method that significantly reduces the computational cost of dimension reduction by intelligently combining data from cheap…

The paper introduces a U-Net deep learning surrogate model to accelerate Quality-Diversity optimization for urban layout design, demonstrating that this spatial approach enables highly accurate climat…

The paper proposes FOAM, an adaptive damping method that stabilizes the Shampoo optimization algorithm by dynamically controlling damping and eigendecomposition frequency, thereby reducing staleness-i…