相关论文: ACORN: Adaptive Contrastive Optimization for Safe …

The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning…

Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many computer vision tasks. However, high computational and storage demands hinder their deployment into resource-constrained environments, such as embedded…

Quadruped robots are designed to achieve agile and robust locomotion by drawing inspiration from legged animals. However, most existing control methods for quadruped robots lack a key capacity observed in animals: the ability to exhibit…

Active inference is a unifying theory for perception and action resting upon the idea that the brain maintains an internal model of the world by minimizing free energy. From a behavioral perspective, active inference agents can be seen as…

Reinforcement Learning (RL) has achieved remarkable success in sequential decision tasks. However, recent studies have revealed the vulnerability of RL policies to different perturbations, raising concerns about their effectiveness and…

Reinforcement learning is a general methodology of adaptive optimal control that has attracted much attention in various fields ranging from video game industry to robot manipulators. Despite its remarkable performance demonstrations, plain…

Real-world robotic tasks often require agents to achieve sequences of goals while respecting time-varying safety constraints. However, standard Reinforcement Learning (RL) paradigms are fundamentally limited in these settings. A natural…

Adversarial training is one of the most effective defenses against adversarial attacks, but it incurs a high computational cost. In this study, we present the first theoretical analysis suggesting that adversarially pretrained transformers…

Visual encoders have become fundamental components in modern computer vision pipelines. However, ensuring robustness against adversarial perturbations remains a critical challenge. Recent efforts have explored both supervised and…

Adaptive optimizers such as Adam have achieved great success in training large-scale models like large language models and diffusion models. However, they often generalize worse than non-adaptive methods, such as SGD on classical…

Asynchronous Advantage Actor Critic (A3C) is an effective Reinforcement Learning (RL) algorithm for a wide range of tasks, such as Atari games and robot control. The agent learns policies and value function through trial-and-error…

Multi-robot mapping with neural implicit representations enables the compact reconstruction of complex environments. However, it demands robustness against communication challenges like packet loss and limited bandwidth. While prior works…

The ability to navigate and interact with complex environments is central to real-world embodied agents, yet navigation in unseen environments remains challenging due to "experiential amnesia," where existing trajectory-driven or reactive…

Collaborative multi-agent reinforcement learning has rapidly evolved, offering state-of-the-art algorithms for real-world applications, including sensitive domains. However, a key challenge to its widespread adoption is the lack of a…

In order for reinforcement learning techniques to be useful in real-world decision making processes, they must be able to produce robust performance from limited data. Deep policy optimization methods have achieved impressive results on…

Embodied learning for object-centric robotic manipulation is a rapidly developing and challenging area in embodied AI. It is crucial for advancing next-generation intelligent robots and has garnered significant interest recently. Unlike…

Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, safety-critical environments. As these systems gain autonomy and enter domains such as…

The increasing adoption of Reinforcement Learning in safety-critical systems domains such as autonomous vehicles, health, and aviation raises the need for ensuring their safety. Existing safety mechanisms such as adversarial training,…

Deep neural networks have demonstrated their capability to learn control policies for a variety of tasks. However, these neural network-based policies have been shown to be susceptible to exploitation by adversarial agents. Therefore, there…

Control design for robotic systems is complex and often requires solving an optimization to follow a trajectory accurately. Online optimization approaches like Model Predictive Control (MPC) have been shown to achieve great tracking…