Oliver Lemon
@oliverlemon.bsky.social
Prof in CS; Academic Lead of National Robotarium; ELLIS Fellow; Edinburgh Centre for Robotics; Heriot-Watt, Edinburgh. Postdocs at Stanford and Edinburgh. Research in NLP, dialogue, conversational AI, multimodality, robots, embodied AI, collaborative AI
"Learnings" and "advancements", both common in AI papers
August 4, 2025 at 7:14 AM
"Learnings" and "advancements", both common in AI papers
Reposted by Oliver Lemon
Oh yes, here's the link to the actual pre-print: arxiv.org/abs/2504.08590
Playpen: An Environment for Exploring Learning Through Conversational Interaction
Interaction between learner and feedback-giver has come into focus recently for post-training of Large Language Models (LLMs), through the use of reward models that judge the appropriateness of a mode...
arxiv.org
May 29, 2025 at 8:41 PM
Oh yes, here's the link to the actual pre-print: arxiv.org/abs/2504.08590