Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning
Paper • 2606.18831 • Published • 7
Rasmus Rasmussen
theprint
AI & ML interests
Agentic and small language model experiments, data sets and tools.
Recent Activity
upvoted a paper 4 days ago
Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning updated a dataset 5 days ago
theprint/h4xx0r published a dataset 5 days ago
theprint/h4xx0rOrganizations
upvoted a paper 4 days ago
upvoted an article 6 months ago
Article
Create Mixtures of Experts with MergeKit
mlabonne
• • 27 upvoted a collection 8 months ago
upvoted a collection over 1 year ago