8 papers
Hierarchical Resource Rationality Explains Human Reading Behavior
Yunpeng Bai, Xiaofu Jin, Shengdong Zhao +1
Reading is a pervasive and cognitively demanding activity that underpins modern human culture. It is a prime instance of a class of tasks where eye movements are coordinated for th…
ChartOptimiser: Task-driven Optimisation of Chart Designs
Yao Wang, Jiarong Pan, Danqing Shi +3
Automated chart design has seen significant advancements with the emergence of Large-Language Models (LLMs), which offer a practical solution for generating charts. However, LLMs f…
Interactive Groupwise Comparison for Reinforcement Learning from Human Feedback
Jan Kompatscher, Danqing Shi, Giovanna Varni +2
Reinforcement learning from human feedback (RLHF) has emerged as a key enabling technology for aligning AI behaviour with human preferences. The traditional way to collect data in…
DxHF: Providing High-Quality Human Feedback for LLM Alignment via Interactive Decomposition
Danqing Shi, Furui Cheng, Tino Weinkauf +2
Human preferences are widely used to align large language models (LLMs) through methods such as reinforcement learning from human feedback (RLHF). However, the current user interfa…
WigglyEyes: Inferring Eye Movements from Keypress Data
Yujun Zhu, Danqing Shi, Hee-Seung Moon +1
We present a model for inferring where users look during interaction based on keypress data only. Given a key log, it outputs a scanpath that tells, moment-by-moment, how the user…
AgentForge: A Flexible Low-Code Platform for Reinforcement Learning Agent Design
Francisco Erivaldo Fernandes Junior, Antti Oulasvirta
Developing a reinforcement learning (RL) agent often involves identifying values for numerous parameters, covering the policy, reward function, environment, and agent-internal arch…