Lev: Thinking Fast and Deep with Looped Decision Models. One checkpoint, multiple depths: 3 models + LevBench, training data and results.
Dingjie Song
songdj
AI & ML interests
None yet
Recent Activity
liked a model 1 day ago
RecursiveSI/flint liked a dataset 3 days ago
datasocial/tiktok-5.6B-videos liked a model 3 days ago
songdj/Lev-2.6BOrganizations
None yet
-
Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs
Paper • 2605.09063 • Published • 82 -
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation
Paper • 2605.10813 • Published • 15 -
AutoMedBench: Towards Medical AutoResearch with Agentic AI Models
Paper • 2606.01961 • Published • 26
Lev: Thinking Fast and Deep with Looped Decision Models. One checkpoint, multiple depths: 3 models + LevBench, training data and results.
-
Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs
Paper • 2605.09063 • Published • 82 -
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation
Paper • 2605.10813 • Published • 15 -
AutoMedBench: Towards Medical AutoResearch with Agentic AI Models
Paper • 2606.01961 • Published • 26
models 8
songdj/Lev-2.6B
Updated • 76 • 2
songdj/Lev-3B
Updated • 54 • 2
songdj/Lev-1.4B
Updated • 49
songdj/m-638
Image-Text-to-Text • 3.05M • Updated • 19
songdj/m-318
3.05M • Updated • 2
songdj/m-233
Image-Text-to-Text • 3.05M • Updated • 4
songdj/m-104
Image-Text-to-Text • 3.05M • Updated • 2
songdj/m-071
Image-Text-to-Text • 3.05M • Updated • 10
datasets 7
songdj/Lev-train-v2
Viewer • Updated • 197k • 616
songdj/Lev-results
Viewer • Updated • 492k • 883
songdj/LevBench
Viewer • Updated • 8.91k • 385 • 1
songdj/ReviewFact
Viewer • Updated • 9.23k • 145 • 1
songdj/a-426
Updated • 44
songdj/ScratchMath
Viewer • Updated • 1.72k • 287 • 2
songdj/CML-Bench
Preview • Updated • 120 • 2