Improving Test-Time Scaling with Adaptive Looped Transformers
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
ActionOPD: Distilling Decisions, Not Tokens
TokenRouter: Efficient Serving System for Token-Level LLM Routing
models 25
nics-efc/Qwen3-8B-ActionOPD-DeepSeek-V4-Flash
Text Generation • 8B • Updated • 304
nics-efc/Qwen3-8B-ActionOPD-Qwen3.7-Flash
Text Generation • 8B • Updated • 293
nics-efc/Qwen3-4B-ActionOPD-DeepSeek-V4-Flash
Text Generation • 4B • Updated • 177
nics-efc/Qwen3-4B-ActionOPD-Qwen3.7-Flash
Text Generation • 4B • Updated • 208
nics-efc/TaH2-1.7B-max2
Text Generation • 2B • Updated • 241
nics-efc/TaH2-1.7B-Standard
Text Generation • 2B • Updated • 230
nics-efc/VPR-Qwen3-4B-Minesweeper
Text Generation • 4B • Updated • 18
nics-efc/VPR-Qwen3-4B-Base-Math-Mixed
Text Generation • 4B • Updated • 21
nics-efc/VPR-Qwen3-4B-Sudoku
Text Generation • 4B • Updated • 39 • 1
nics-efc/VPR-Qwen3-4B-Sokoban
Text Generation • 4B • Updated • 25 • 1
datasets 11
nics-efc/TaH2-amteam-tool
Viewer • Updated • 2.19M • 596
nics-efc/TaH-openr1-math-75k
Updated • 77
nics-efc/R2R_Router_Training_Qwen3-0.6B_Qwen3-30B-A3B
Viewer • Updated • 9.3M • 46
nics-efc/R2R_Router_Training_Qwen3-4B_Qwen3-32B
Viewer • Updated • 18.3M • 113
nics-efc/R2R_Router_Training_Qwen3-1.7B_Qwen3-8B
Viewer • Updated • 21.9M • 87
nics-efc/R2R_Router_Training_Qwen3-0.6B_Qwen3-8B
Viewer • Updated • 22.2M • 154
nics-efc/TaH-openr1-mixture-100k
Updated • 69
nics-efc/R2R_query
Viewer • Updated • 2.93k • 88
nics-efc/R2R_Router_Training
Viewer • Updated • 8.19M • 452 • 4
nics-efc/MoA_Long_HumanQA
Viewer • Updated • 3.5k • 98 • 4