Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning
Paper β’ 2606.18831 β’ Published β’ 8
π Open to Work
Rasmus Rasmussen
theprint
AI & ML interests
Agentic and small language model experiments, data sets and tools.
Recent Activity
updated a collection 2 days ago
TextSynth updated a model 2 days ago
theprint/TextSynth-4B-0926-GGUF published a model 2 days ago
theprint/TextSynth-4B-0926-GGUFOrganizations
upvoted a paper 3 months ago
upvoted an article 9 months ago
Article
Create Mixtures of Experts with MergeKit
mlabonne
β’ β’ 27 upvoted a collection 11 months ago
upvoted a collection almost 2 years ago