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
11

l3lab/L1-Qwen3-8B-Max
8B
•
Updated
•
146

l3lab/L1-Qwen3-8B-Exact
8B
•
Updated
•
45
•
1

l3lab/L1-Qwen-7B-Max
8B
•
Updated
•
204

l3lab/L1-Qwen-7B-Exact
8B
•
Updated
•
12
•
1

l3lab/L1-1.5B-Short
2B
•
Updated
•
6.84k

l3lab/all-distilroberta-v1-lr2e-4-bs256-nneg3-ml-ne2
Updated
•
4

l3lab/L1-Qwen-1.5B-Exact
2B
•
Updated
•
4.86k
•
6

l3lab/L1-Qwen-1.5B-Max
2B
•
Updated
•
4.95k
•
15

l3lab/ntp-mathlib-context-deepseek-coder-1.3b
Text Generation
•
Updated
•
10
•
3

l3lab/ntp-mathlib-st-deepseek-coder-1.3b
Text Generation
•
Updated
•
6
datasets
9
l3lab/miniCTX-v2
Viewer
•
Updated
•
668
•
103
•
3
l3lab/miniCTX-v2-data
Updated
•
6
l3lab/Massive-Math-455K-Verified
Viewer
•
Updated
•
455k
•
86
•
1
l3lab/lean-premises
Updated
•
9
•
1
l3lab/miniCTX
Viewer
•
Updated
•
662
•
174
•
3
l3lab/ntp-mathlib-instruct-context-fullproof
Viewer
•
Updated
•
144k
•
26
•
1
l3lab/ntp-mathlib-instruct-context
Viewer
•
Updated
•
614k
•
47
•
1
l3lab/ntp-mathlib
Viewer
•
Updated
•
213k
•
48
•
2
l3lab/ntp-mathlib-instruct-st
Viewer
•
Updated
•
307k
•
68