Related papers: FERERO: A Flexible Framework for Preference-Guided…

Balancing safety, efficiency, and operational costs in highway driving poses a challenging decision-making problem for heavy-duty vehicles. A central difficulty is that conventional scalar reward formulations, obtained by aggregating these…

Recent advances in Large Language Models (LLMs) have opened new avenues for sequential recommendation by enabling natural language reasoning over user behavior sequences. A common approach formulates recommendation as a language modeling…

Reinforcement Learning (RL) has demonstrated its ability to solve complex decision-making problems in a variety of domains, by optimizing reward signals obtained through interaction with an environment. However, many real-world scenarios…

Preference learning is a widely adopted post-training technique that aligns large language models (LLMs) to human preferences and improves specific downstream task capabilities. In this work we systematically investigate how specific…

Nowadays, most online services are hosted on multi-stakeholder marketplaces, where consumers and producers may have different objectives. Conventional recommendation systems, however, mainly focus on maximizing consumers' satisfaction by…

Neural Combinatorial Optimization (NCO) has emerged as a promising approach for NP-hard problems. However, prevailing RL-based methods suffer from low sample efficiency due to sparse rewards and underused solutions. We propose Best-anchored…

PRefLexOR (Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning) combines preference optimization with concepts from Reinforcement Learning to enable models to self-teach through iterative reasoning…

Preference optimization is a critical post-training technique used to align large language models (LLMs) with human preferences, typically by fine-tuning on ranked response pairs. While methods like Direct Preference Optimization (DPO) have…

Data and knowledge representation are fundamental concepts in machine learning. The quality of the representation impacts the performance of the learning model directly. Feature learning transforms or enhances raw data to structures that…

Multiple-objective optimization (MOO) aims to simultaneously optimize multiple conflicting objectives and has found important applications in machine learning, such as minimizing classification loss and discrepancy in treating different…

Algorithms with predictions} has emerged as a powerful framework to combine the robustness of traditional online algorithms with the data-driven performance benefits of machine-learned (ML) predictions. However, most existing approaches in…

Fourier Neural Operator (FNO) is a powerful and popular operator learning method. However, FNO is mainly used in forward prediction, yet a great many applications rely on solving inverse problems. In this paper, we propose an invertible…

Instruction following (IF) is a critical capability for large language models (LLMs). However, handling complex instructions with multiple constraints remains challenging. Previous methods typically select preference pairs based on the…

Recently, Pareto Set Learning (PSL) has been proposed for learning the entire Pareto set using a neural network. PSL employs preference vectors to scalarize multiple objectives, facilitating the learning of mappings from preference vectors…

Multiobjective optimization plays an increasingly important role in modern applications, where several criteria are often of equal importance. The task in multiobjective optimization and multiobjective optimal control is therefore to…

Enforcing complex (e.g., nonconvex) operational constraints is a critical challenge in real-world learning and control systems. However, existing methods struggle to efficiently enforce general classes of constraints. To address this, we…

This thesis develops theoretical frameworks and algorithms that advance constrained reinforcement learning (RL) across control, preference learning, and alignment of large language models. The first contribution addresses constrained Markov…

We analyze the problem of learning a single user's preferences in an active learning setting, sequentially and adaptively querying the user over a finite time horizon. Learning is conducted via choice-based queries, where the user selects…

Multi-objective optimization is central to many engineering and machine learning applications, where multiple objectives must be optimized in balance. While multi-gradient based optimization methods combine these objectives in each step,…

Lead optimization in drug discovery requires efficiently navigating vast chemical space through iterative cycles to enhance molecular properties while preserving structural similarity to the original lead compound. Despite recent advances,…