Related papers: The Offline-Frontier Shift: Diagnosing Distributio…
Data-driven black-box model-based optimization (MBO) problems arise in a great number of practical application scenarios, where the goal is to find a design over the whole space maximizing a black-box target function based on a static…
Autonomous navigation and exploration in unmapped environments remains a significant challenge in robotics due to the difficulty robots face in making commonsense inference of unobserved geometries. Recent advancements have demonstrated…
In general, a multi-objective optimization problem does not have a single optimal solution but a set of Pareto optimal solutions, which forms the Pareto front in the objective space. Various evolutionary algorithms have been proposed to…
Offline model-based optimization (MBO) refers to the task of optimizing a black-box objective function using only a fixed set of prior input-output data, without any active experimentation. Recent work has introduced quantum extremal…
Modern machine learning models are often constructed taking into account multiple objectives, e.g., minimizing inference time while also maximizing accuracy. Multi-objective hyperparameter optimization (MHPO) algorithms return such…
This work tackles two critical challenges related to the development of metaheuristics for Multi-Objective Optimization Problems (MOOPs): the exponential growth of non-dominated solutions and the tendency of metaheuristics to…
Reliability assessment of engineering systems often requires repeated evaluations of limit-state functions that may rely on computationally expensive high-fidelity models, rendering direct sampling-based reliability analysis impractical. An…
We study a federated version of multi-objective optimization (MOO), where a single model is trained to optimize multiple objective functions. MOO has been extensively studied in the centralized setting but is less explored in federated or…
Learning-enabled control systems increasingly rely on multiple sensing modalities (e.g., vision, audio, language, etc.) for perception and decision support. A key challenge is that multi-modal sensor training dynamics are often imbalanced:…
Reliable traversable area segmentation in unstructured environments is critical for planning and decision-making in autonomous driving. However, existing data-driven approaches often suffer from degraded segmentation performance in…
Text-to-image generation models have achieved remarkable progress in preference optimization, yet achieving robust alignment across diverse reward models remains a significant challenge. Existing multi-reward fusion approaches rely on…
In recent years, the field of image generation has witnessed significant advancements, particularly in fine-tuning methods that align models with universal human preferences. This paper explores the critical role of preference data in the…
Learning at the edges has become increasingly important as large quantities of data are continually generated locally. Among others, this paradigm requires algorithms that are simple (so that they can be executed by local devices), robust…
Post-training of LLMs with RLHF, and subsequently preference optimization algorithms such as DPO, IPO, etc., made a big difference in improving human alignment. However, all such techniques can only work with a single (human) objective. In…
Flow Matching (FM) generative models offer efficient simulation-free training and deterministic sampling, but their practical deployment is challenged by high-precision parameter requirements. We adapt optimal transport (OT)-based…
Offline-to-online Reinforcement Learning (O2O RL) aims to perform online fine-tuning on an offline pre-trained policy to minimize costly online interactions. Existing work used offline datasets to generate data that conform to the online…
Offline pretraining with a static dataset followed by online fine-tuning (offline-to-online, or OtO) is a paradigm well matched to a real-world RL deployment process. In this scenario, we aim to find the best-performing policy within a…
This paper is concerned with a recently developed paradigm for population-based optimization, termed particle filter optimization (PFO). This paradigm is attractive in terms of coherence in theory and easiness in mathematical analysis and…
Distribution shift in imitation learning refers to the problem that the agent cannot plan proper actions for a state that has not been visited during the training. This problem can be largely attributed to the inherently narrow state-action…
Recent research has made significant progress in optimizing diffusion models for downstream objectives, which is an important pursuit in fields such as graph generation for drug design. However, directly applying these models to graph…