73 citations · 91 across the 28 of their papers we have counts for
7 papers · 1 filter
\k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating
Jianghui Wang, Silong Yong, Francesco Orabona +3
Low-Rank Adaptation (LoRA) has become a widely adopted technique for efficient neural network fine-tuning, decomposing model updates into low-rank matrices. However, LoRA remains c…
Energy-Based Transfer for Reinforcement Learning
Zeyun Deng, Jasorsi Ghosh, Fiona Xie +4
Reinforcement learning remains sample inefficient, particularly when agents must adapt over time to related but distinct tasks, as in continual learning settings. Efficiency can be…
Model-Agnostic Policy Explanations with Large Language Models
Zhang Xi-Jia, Yue Guo, Shufei Chen +4
Intelligent agents, such as robots, are increasingly deployed in real-world, human-centric environments. To foster appropriate human trust and meet legal and ethical standards, the…
Personalized Decision Supports based on Theory of Mind Modeling and Explainable Reinforcement Learning
Huao Li, Yao Fan, Keyang Zheng +2
In this paper, we propose a novel personalized decision support system that combines Theory of Mind (ToM) modeling and explainable Reinforcement Learning (XRL) to provide effective…
Benchmarking and Enhancing Disentanglement in Concept-Residual Models
Renos Zabounidis, Ini Oguntola, Konghao Zhao +3
Concept bottleneck models (CBMs) are interpretable models that first predict a set of semantically meaningful features, i.e., concepts, from observations that are subsequently used…
Understanding Your Agent: Leveraging Large Language Models for Behavior Explanation
Xijia Zhang, Yue Guo, Simon Stepputtis +2
Intelligent agents such as robots are increasingly deployed in real-world, safety-critical settings. It is vital that these agents are able to explain the reasoning behind their de…
Explaining Agent Behavior with Large Language Models
Xijia Zhang, Yue Guo, Simon Stepputtis +2
Intelligent agents such as robots are increasingly deployed in real-world, safety-critical settings. It is vital that these agents are able to explain the reasoning behind their de…