Related papers: Multi-Objective Hull Form Optimization with CAD En…

Constrained environments are common in practical applications of manipulating deformable linear objects (DLOs), where movements of both DLOs and robots should be constrained. This task is high-dimensional and highly constrained owing to the…

Designing deep learning-based solutions is becoming a race for training deeper models with a greater number of layers. While a large-size deeper model could provide competitive accuracy, it creates a lot of logistical challenges and…

This letter presents a method to reduce the computational demands of including second-order dynamics sensitivity information into the Differential Dynamic Programming (DDP) trajectory optimization algorithm. An approach to DDP is developed…

Computational fluid dynamics (CFD) is a powerful tool for modeling turbulent flow and is commonly used for urban microclimate simulations. However, traditional CFD methods are computationally intensive, requiring substantial hardware…

We propose DiFFPO, Diffusion Fast and Furious Policy Optimization, a unified framework for training masked diffusion large language models (dLLMs) to reason not only better (furious), but also faster via reinforcement learning (RL). We…

Topology optimization has emerged as a popular approach to refine a component's design and increase its performance. However, current state-of-the-art topology optimization frameworks are compute-intensive, mainly due to multiple finite…

Post-alignment of large language models (LLMs) is critical in improving their utility, safety, and alignment with human intentions. Direct preference optimisation (DPO) has become one of the most widely used algorithms for achieving this…

In Bayesian inference, the most probable explanation (MPE) problem requests a variable instantiation with the highest probability given some evidence. Since a Bayesian network can be encoded as a literal-weighted CNF formula $\varphi$, we…

Aligning large language models with human preferences is essential for improving interaction quality and safety by ensuring outputs better reflect human values. A promising strategy involves Reinforcement Learning from Human Feedback…

The thesis arises in the context of deep learning applications to particle physics. The dissertation follows two main parallel streams: the development of hardware-accelerated tools for event simulation in high-energy collider physics, and…

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,…

Deep Reinforcement Learning (DRL) has recently spread into a range of domains within physics and engineering, with multiple remarkable achievements. Still, much remains to be explored before the capabilities of these methods are well…

Nowadays, the shipbuilding industry is facing a radical change towards solutions with a smaller environmental impact. This can be achieved with low emissions engines, optimized shape designs with lower wave resistance and noise generation,…

Designing metamaterials for extreme mechanical behavior involves the optimal selection of design parameters. However, identifying these optimal parameters through topology optimization (TO) across a large parametric space requires extensive…

Deep-learning-based video processing has yielded transformative results in recent years. However, the video analytics pipeline is energy-intensive due to high data rates and reliance on complex inference algorithms, which limits its…

Deriving governing equations of complex physical systems based on first principles can be quite challenging when there are certain unknown terms and hidden physical mechanisms in the systems. In this work, we apply a deep learning…

This work addresses the challenge of adapting dynamic deadline requirements for LiDAR object detection deep neural networks (DNNs). The computing latency of object detection is critically important to ensure safe and efficient navigation.…

Direct Preference Optimization (DPO) is a powerful paradigm for aligning Large Language Models (LLMs) to human preferences in Machine Translation (MT), but current methods are hindered by two fundamental challenges: (1) flawed reward…

Data-based optimization (DBO) offers a promising approach for efficiently optimizing shape for better aerodynamic performance by leveraging a pretrained surrogate model for offline evaluations during iterations. However, DBO heavily relies…

As large language models (LLMs) become more capable, fine-tuning techniques for aligning with human intent are increasingly important. A key consideration for aligning these models is how to most effectively use human resources, or model…