arxiv:2603.25268
🔄 In a Training Loop
Abhijnan Nath
Abhijnan
AI & ML interests
None yet
Recent Activity
updated a dataset 1 day ago
Abhijnan/clue-selector-game-echo published a dataset 1 day ago
Abhijnan/clue-selector-game-echo updated a dataset 3 months ago
Abhijnan/craft-benchmark-leanOrganizations
models 21
Abhijnan/llama-8b-r32-dpo
Text Generation • Updated • 1
Abhijnan/qwen7b-r32-dpo
Text Generation • Updated • 5
Abhijnan/llama-8b-r32-ipo
Text Generation • Updated • 1
Abhijnan/qwen7b-r32-ipo
Text Generation • Updated • 5
Abhijnan/llama-8b-r32-sft
Text Generation • Updated • 4
Abhijnan/qwen7b-r32-sft
Text Generation • Updated • 6
Abhijnan/Delidata_friction_agent
Updated • 2
Abhijnan/WTD_IPO_friction_agent
Updated • 6
Abhijnan/intervention_agent_2
Updated • 12
Abhijnan/intervention_agent
Updated
datasets 6
Abhijnan/clue-selector-game-echo
Viewer • Updated • 45.8k • 14 • 1
Abhijnan/craft-benchmark-lean
Viewer • Updated • 5.95k • 202
Abhijnan/delidata_wasoncard_friction_data
Viewer • Updated • 69.1k • 53
Abhijnan/wtd_simulated_data
Viewer • Updated • 53.7k • 32
Abhijnan/wtd_original_data
Viewer • Updated • 5.27k • 122
Abhijnan/weights_task_friction_preferences
Preview • Updated • 41