Publications

Analyzing the Generalization and Reliability of Steering Vectors
Steering vectors (SVs) are a new approach to efficiently adjust language model behaviour at inference time by intervening on …
Daniel Tan, David Chanin, Aengus Lynch, Dimitrios Kanoulas, Brooks Paige, Adria Garriga-Alonso, Robert Kirk
Cite DOI URL
Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning
In many Reinforcement Learning (RL) papers, learning curves are useful indicators to measure the effectiveness of RL algorithms. …
Shengyi Huang, Quentin Gallouédec, Florian Felten, Antonin Raffin, Rousslan Fernand Julien Dossa, Yanxiao Zhao, Ryan Sullivan, Viktor Makoviychuk, Denys Makoviichuk, Mohamad H. Danesh, Cyril Roumégous, Jiayi Weng, Chufan Chen, Md Masudur Rahman, João G. M. Araújo, Guorui Quan, Daniel Tan, Timo Klein, Rujikorn Charakorn, Mark Towers, Yann Berthelot, Kinal Mehta, Dipam Chakraborty, Arjun KG, Valentin Charraut, Chang Ye, Zichen Liu, Lucas N. Alegre, Alexander Nikulin, Xiao Hu, Tianlin Liu, Jongwook Choi, Brent Yi
Cite DOI URL
Value Functions Are Control Barrier Functions: Verification of Safe Policies Using Control Theory
Guaranteeing safe behaviour of reinforcement learning (RL) policies poses significant challenges for safety-critical applications, …
Daniel C. H. Tan, Fernando Acero, Robert McCarthy, Dimitrios Kanoulas, Zhibin Li
Cite DOI URL
Perceptive Locomotion with Controllable Pace and Natural Gait Transitions Over Uneven Terrains
This work developed a learning framework for perceptive legged locomotion that combines visual feedback, proprioceptive information, …
Daniel Chee Hian Tan, Jenny Zhang, Michael, Chuah, Zhibin Li
Cite DOI URL
Using Deep Learning with Large Aggregated Datasets for COVID-19 Classification from Cough
The Covid-19 pandemic has been one of the most devastating events in recent history, claiming the lives of more than 5 million people …
Esin Darici Haritaoglu, Nicholas Rasmussen, Daniel C. H. Tan, Jennifer Ranjani J., Jaclyn Xiao, Gunvant Chaudhari, Akanksha Rajput, Praveen Govindan, Christian Canham, Wei Chen, Minami Yamaura, Laura Gomezjurado, Aaron Broukhim, Amil Khanzada, Mert Pilanci
Cite DOI URL