Long Tran-Thanh

To Ask or Not to Ask: A User Annoyance Aware Preference Elicitation Framework for Social Robots

2020

In this paper we investigate how social robots can efficiently gather user preferences without exceeding the allowed user annoyance threshold. To do so, we use a Gazebo based simulated office environment with a TIAGo Steel …

Class Similarity Weighted Knowledge Distillation for Continual Semantic Segmentation

2022 · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Deep learning models are known to suffer from the problem of catastrophic forgetting when they incrementally learn new classes. Continual learning for semantic segmentation (CSS) is an emerging field in computer vision. We identify a …

Revisiting LARS for Large Batch Training Generalization of Neural Networks

2023 · arXiv (Cornell University)

This paper explores Large Batch Training techniques using layer-wise adaptive scaling ratio (LARS) across diverse settings, uncovering insights. LARS algorithms with warm-up tend to be trapped in sharp minimizers early on due to redundant ratio …

Sparse Offline Reinforcement Learning with Corruption Robustness

2025 · Warwick Research Archive Portal (University of Warwick)

We investigate robustness to strong data corruption in offline sparse reinforcement learning (RL). In our setting, an adversary may arbitrarily perturb a fraction of the collected trajectories from a high-dimensional but sparse Markov decision process, …