🔄 In a Training Loop

Sofia

sstoica12

·

sofia-stoica-6ab805325

AI & ML interests

Multimodal LLMs, VIT, NLP, Computer Vision, Deep Learning Systems.

Recent Activity

updated a model 2 days ago

sstoica12/acquisition_student_AS_deita_combine_WGM_MP_llama8b_conf_5000

published a model 2 days ago

sstoica12/acquisition_student_AS_deita_combine_WGM_MP_llama8b_conf_5000

updated a model 2 days ago

sstoica12/acquisition_generator_AS_deita_combine_WGM_MP_llama8b_conf

View all activity

Organizations

upvoted 2 papers about 1 month ago

Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI

Paper • 2609.38143 • Published Sep 29 • 53

Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training

Paper • 2609.40111 • Published Sep 30 • 31

upvoted an article about 1 year ago

Article

From GRPO to DAPO and GSPO: What, Why, and How

NormalUhr

•

Aug 9, 2025

• 147

upvoted a paper over 1 year ago

Perception-Aware Policy Optimization for Multimodal Reasoning

Paper • 2507.06448 • Published Jul 8, 2025 • 48