L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
L3 Lab
university
AI & ML interests
None defined yet.
Recent Activity
models 12
l3lab/VTR-2B
2B • Updated • 125
l3lab/L1-Qwen3-8B-Max
8B • Updated • 52
l3lab/L1-Qwen3-8B-Exact
8B • Updated • 38 • 1
l3lab/L1-Qwen-7B-Max
8B • Updated • 49
l3lab/L1-Qwen-7B-Exact
8B • Updated • 165 • 1
l3lab/L1-1.5B-Short
2B • Updated • 10
l3lab/all-distilroberta-v1-lr2e-4-bs256-nneg3-ml-ne2
Updated • 174
l3lab/L1-Qwen-1.5B-Exact
2B • Updated • 178 • 6
l3lab/L1-Qwen-1.5B-Max
2B • Updated • 187 • 15
l3lab/ntp-mathlib-context-deepseek-coder-1.3b
Text Generation • Updated • 194 • 3
datasets 10
l3lab/far-explorer-2026-09-30
Viewer • Updated • 103k • 49
l3lab/miniCTX-v2
Viewer • Updated • 668 • 363 • 3
l3lab/miniCTX-v2-data
Updated • 23
l3lab/Massive-Math-455K-Verified
Viewer • Updated • 455k • 88 • 1
l3lab/lean-premises
Updated • 247 • 3
l3lab/miniCTX
Viewer • Updated • 662 • 1.06k • 3
l3lab/ntp-mathlib-instruct-context-fullproof
Viewer • Updated • 144k • 52 • 2
l3lab/ntp-mathlib-instruct-context
Viewer • Updated • 614k • 174 • 2
l3lab/ntp-mathlib
Viewer • Updated • 213k • 215 • 2
l3lab/ntp-mathlib-instruct-st
Viewer • Updated • 307k • 146