arxiv:2603.25268
In a Training Loop 🔄
Abhijnan Nath
Abhijnan
AI & ML interests
None yet
Recent Activity
updated a dataset about 9 hours ago
Abhijnan/craft-benchmark-lean published a dataset about 9 hours ago
Abhijnan/craft-benchmark-lean updated a model about 12 hours ago
Abhijnan/llama-8b-r32-dpoOrganizations
models 21
Abhijnan/llama-8b-r32-dpo
Text Generation • Updated • 11
Abhijnan/qwen7b-r32-dpo
Text Generation • Updated • 14
Abhijnan/llama-8b-r32-ipo
Text Generation • Updated • 10
Abhijnan/qwen7b-r32-ipo
Text Generation • Updated • 14
Abhijnan/llama-8b-r32-sft
Text Generation • Updated • 9
Abhijnan/qwen7b-r32-sft
Text Generation • Updated • 17
Abhijnan/Delidata_friction_agent
Updated • 1
Abhijnan/WTD_IPO_friction_agent
Updated • 2
Abhijnan/intervention_agent_2
Updated • 1
Abhijnan/intervention_agent
Updated
datasets 5
Abhijnan/craft-benchmark-lean
Viewer • Updated • 5.95k • 3
Abhijnan/delidata_wasoncard_friction_data
Viewer • Updated • 69.1k • 8
Abhijnan/wtd_simulated_data
Viewer • Updated • 53.7k • 8
Abhijnan/wtd_original_data
Viewer • Updated • 5.27k • 12
Abhijnan/weights_task_friction_preferences
Preview • Updated • 9