83%Must read
?Must readVote to see the score
The two clocks and the innovation window: When and how generative models learn rules
Generative models learn rules at τ_rule and memorize at τ_mem, defining an innovation window that widens with dataset size but narrows with rule complexity across diffusion and autoregressive architectures.
Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026
– ReadersNo votes yet
13/20 AI panelreviewers recommend it
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
AI panel: 13 of 20 reviewers recommend it
lenient 4/5
medium 6/10
strict 3/5