Related papers: Balancing Multi-modal Sensor Learning via Multi-ob…
This paper presents an iterative data-driven algorithm for solving dynamic multi-objective (MO) optimal control problems arising in control of nonlinear continuous-time systems. It is first shown that the Hamiltonian functional…
Two-class classification problems are often characterized by an imbalance between the number of majority and minority datapoints resulting in poor classification of the minority class in particular. Traditional approaches, such as…
Solving constrained optimization problems by multi-objective evolutionary algorithms has scored tremendous achievements in the last decade. Standard multi-objective schemes usually aim at minimizing the objective function and also the…
Multi-Objective Reinforcement Learning (MORL) presents significant challenges and opportunities for optimizing multiple objectives in Large Language Models (LLMs). We introduce a MORL taxonomy and examine the advantages and limitations of…
Bayesian optimization (BO) is a sample efficient approach to automatically tune the hyperparameters of machine learning models. In practice, one frequently has to solve similar hyperparameter tuning problems sequentially. For example, one…
Multimodal learning models have become increasingly important as they surpass single-modality approaches on diverse tasks ranging from question-answering to autonomous driving. Despite the importance of multimodal learning, existing efforts…
Imitation learning provides a powerful framework for goal-conditioned visual navigation in mobile robots, enabling obstacle avoidance while respecting human preferences and social norms. However, its effectiveness depends critically on the…
Modality representation learning is an important problem for multimodal sentiment analysis (MSA), since the highly distinguishable representations can contribute to improving the analysis effect. Previous works of MSA have usually focused…
Using multimodal sensory data can enhance communications systems by reducing the overhead and latency in beam training. However, processing such data incurs high computational complexity, and continuous sensing results in significant power…
Multimodal language models now integrate text, audio, and video for unified reasoning. Yet existing RL post-training pipelines treat all input signals as equally relevant, ignoring which modalities each task actually requires. This…
This paper studies adaptive algorithms for simultaneous regulation (i.e., control) and estimation (i.e., learning) of Multiple Input Multiple Output (MIMO) linear dynamical systems. It proposes practical, easy to implement control policies…
Realizing high-throughput aberration-corrected Scanning Transmission Electron Microscopy (STEM) exploration of atomic structures requires rapid tuning of multipole probe correctors while compensating for the inevitable drift of the optical…
Human perception of the empirical world involves recognizing the diverse appearances, or 'modalities', of underlying objects. Despite the longstanding consideration of this perspective in philosophy and cognitive science, the study of…
Localization is a key requirement for mobile robot autonomy and human-robot interaction. Vision-based localization is accurate and flexible, however, it incurs a high computational burden which limits its application on many…
This paper presents a novel optimization method for maximizing generalization over tasks in meta-learning. The goal of meta-learning is to learn a model for an agent adapting rapidly when presented with previously unseen tasks. Tasks are…
Cross-modal alignment aims to map heterogeneous modalities into a shared latent space, as exemplified by models like CLIP, which benefit from large-scale image-text pretraining for strong recognition capabilities. However, when operating in…
Role-playing agents (RPAs) require balancing multiple objectives, such as instruction following, persona consistency, and stylistic fidelity, which are not always perfectly aligned across different dimensions. While prior work has primarily…
The deep learning trend has recently impacted a variety of fields, including communication systems, where various approaches have explored the application of neural networks in place of traditional designs. Neural networks flexibly allow…
A novel multiscale consensus-based optimization (CBO) algorithm for solving bi- and tri-level optimization problems is introduced. Existing CBO techniques are generalized by the proposed method through the employment of multiple interacting…
Effectively integrating diverse sensory modalities is crucial for robotic manipulation. However, the typical approach of feature concatenation is often suboptimal: dominant modalities such as vision can overwhelm sparse but critical signals…