L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

L3 Lab
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
models
5
datasets
7
l3lab/lean-premises
Updated
•
49
•
1
l3lab/miniCTX-v2
Viewer
•
Updated
•
668
•
57
•
1
l3lab/miniCTX
Viewer
•
Updated
•
662
•
409
•
3
l3lab/ntp-mathlib-instruct-context-fullproof
Viewer
•
Updated
•
144k
•
42
•
1
l3lab/ntp-mathlib-instruct-context
Viewer
•
Updated
•
614k
•
56
•
1
l3lab/ntp-mathlib
Viewer
•
Updated
•
213k
•
136
•
2
l3lab/ntp-mathlib-instruct-st
Viewer
•
Updated
•
307k
•
63