14 accepted papers
Reinforcement learning (RL) is a fundamental framework for sequential decision-making, in which an agent learns an optimal policy through interactions with an unknown environment. In settings with function approximation, many existing RL algorithms achieve favorable sample complexity, but often rely…
Prompt engineering has become central to eliciting the capabilities of large language models (LLMs). At its core lies prompt selection - efficiently identifying the most effective prompts. However, most prior investigations overlook a key challenge: the inherently multi-faceted nature of prompt perf…
Recent text-to-image (T2I) diffusion models have achieved impressive progress in generating high-fidelity images, yet they often fail to faithfully follow complex user prompts, especially in attribute binding, negation, and compositional reasoning. To address this limitation, we propose PromptEnhanc
Threaded insert assembly is a critical process in automotive manufacturing, with its installation quality directly determining the structural integrity of vehicle components. Due to the complexity of the industrial scenarios, threaded insert assembly faces two major challenges: peg-hole misalignment
Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for aligning artificial intelligence systems with human values, achieving remarkable success in fine-tuning large language models. However, existing RLHF frameworks often assume that human preferences are relatively…
This paper investigates a hybrid learning framework for reinforcement learning (RL) in which the agent can leverage both an offline dataset and online interactions to learn the optimal policy. We present a unified algorithm and analysis and show that augmenting confidence-based online RL algorithms
Federated Learning (FL) is a promising approach for training machine learning models on decentralized data while preserving privacy. However, privacy risks, particularly Membership Inference Attacks (MIAs), which aim to determine whether a specific data point belongs to a target client's training se…
This letter introduces a novel control method for the underactuated triple pendulum robot (UTPR), allowing it to maintain balance while controlling the end-effector motion in the operational space. The UTPR is influenced by gravity in the vertical plane, with the first joint being passive (underactu
The rapid development of language models (LMs) brings unprecedented accessibility and usage for both models and users. On the one hand, powerful LMs achieve state-of-the-art performance over numerous downstream NLP tasks. On the other hand, more and more attention is paid to unrestricted model acces…
Here we present the development of an autonomous modular swimming robot. This robot, named µBot 2.0, was upgraded from our previous robot platform µBot and features onboard computing, sensing, and power. Its compact size and modularity render the robot an ideal platform for studying bio-inspired rob…
This paper investigates conservative exploration in reinforcement learning where the performance of the learning agent is guaranteed to be above a certain threshold throughout the learning process. It focuses on the tabular episodic Markov Decision Process (MDP) setting that has finite states and ac…
In this work, we developed a mathematical model and a simulation platform for a fish-inspired robotic template, namely Magnetic, Modular, Undulatory Robot (\mu \text{Bot})(\mu \text{Bot}). Through this platform, we systematically explored the effects of robot design and fluid parameters on swimming…
Here we developed an experimental platform with a magnetic, modular, undulatory robot (μBot) for studying fish-inspired underwater locomotion. This platform will enable us to systematically explore the relationship between body morphology, swimming gaits, and swimming performance via reinforcement l…
Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error. However, compressive networks are desired in many real world applications and direct training of small networks may be trapp…