Lev: Thinking Fast and Deep with Looped Decision Models. One checkpoint, multiple depths: 3 models + LevBench, training data and results.
James Dingjie Song PRO
songdj
AI & ML interests
None yet
Recent Activity
updated a Space 6 days ago
OpenLair/README published a Space 11 days ago
OpenLair/README liked a model 16 days ago
nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16Organizations
-
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 • 133 • 2
songdj/Lev-3B
Updated • 92 • 3
songdj/Lev-1.4B
Updated • 93
songdj/m-638
Image-Text-to-Text • 3.05M • Updated • 12
songdj/m-318
3.05M • Updated • 9
songdj/m-233
Image-Text-to-Text • 3.05M • Updated • 8
songdj/m-104
Image-Text-to-Text • 3.05M • Updated • 7
songdj/m-071
Image-Text-to-Text • 3.05M • Updated • 15
datasets 7
songdj/Lev-train-v2
Viewer • Updated • 197k • 719
songdj/Lev-results
Viewer • Updated • 492k • 1.13k
songdj/LevBench
Viewer • Updated • 8.91k • 554 • 1
songdj/ReviewFact
Viewer • Updated • 9.23k • 220 • 1
songdj/a-426
Updated • 111
songdj/ScratchMath
Viewer • Updated • 1.72k • 476 • 4
songdj/CML-Bench
Preview • Updated • 85 • 2