Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning
Paper
•
2512.20605
•
Published
•
61
Johannes von Oswald
voswaldj
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
almost 2 years ago
Griffin: Mixing Gated Linear Recurrences with Local Attention for
Efficient Language Models
authored
a paper
almost 2 years ago
Linear Transformers are Versatile In-Context Learners
Organizations
None yet
upvoted
a
paper
28 days ago