cs.LGcs.AIcs.NEmath.OC
ParetoPilot: Zero-Surrogate Offline Multi-Objective Optimization via Infer-Perturb-Guide Diffusion
Jun 3, 2026
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 relying on external surrogate models.
Offline multi-objective optimization (Offline MOO) aims to discover novel Pareto-optimal designs based on static datasets without expensive environment interactions. While recent generative methods have achieved notable success, they predominantly rely on external surrogate models. This dependency introduces significant computational overhead, suffers from deceptive evaluations, and deviates from the prevailing paradigm of jointly training mainstream generative models with conditions. To address these bottlenecks, we propose ParetoPilot, a novel zero-surrogate diffusion framework for offline MOO. ParetoPilot fully leverages the conditional priors inherently embedded within pre-trained diffusion models. At its core, the framework introduces the Infer-Perturb-Guide (IPG) engine, which is seamlessly interleaved within the unconditional denoising steps of the reverse generation process. First, it implicitly infers the instantaneous objective direction by matching conditional and unconditional noise predictions. Next, it mathematically orthogonalizes a parallel gravity field for strict convergence and an edgeness-aware repulsive force for mutual diversity, creating a dynamically annealed perturbation vector. Finally, this perturbed target seamlessly steers the generation process via standard Classifier-Free Guidance (CFG). Extensive experiments across 51 tasks demonstrate that ParetoPilot outperforms 14 state-of-the-art surrogate-based and inverse generative baselines. By eliminating auxiliary proxy training, our approach preserves data privacy while achieving hypervolume improvement and robust Pareto front coverage.
Efficient Post-training of LLMs for Code Generation With Offline Reinforcement Learning
This paper proposes using offline reinforcement learning (RL) as an efficient al…
A Unified Framework for Gradient Aggregation in Multi-Objective Optimization
The paper introduces a unified theoretical framework for gradient aggregation in…
Evidence-Gated LLM Priors for Multi-Objective Bayesian Optimization
The paper proposes an objective-wise reputation-market mechanism to dynamically…
Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta…
The paper proposes a novel framework combining behavior-invariant task represent…
Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation
The paper proposes TDPM, a time-aware diffusion model for generative recommendat…
Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief
The paper introduces Posterior Hybrid Bayesian Belief (PhyB), a novel framework…
U-Net-Accelerated Quality-Diversity Optimization for Climate-Adaptive Urban Layouts
The paper introduces a U-Net deep learning surrogate model to accelerate Quality…
Fine-Tuning Diffusion Models for Molecular Generation via Reinforcement Learning and Fast Sampling
The paper introduces FTDiff, a reinforcement learning fine-tuning framework that…