Jonas Geiping

JonasGeiping

https://jonasgeiping.github.io/

AI & ML interests

Machine Learning Safety, Security and Privacy; Optimization in Deep Learning; Mathematical Optimization: Federated Learning

Recent Activity

new activity 5 days ago

tomg-group-umd/huginn-0125:Supervised fine-tuning and dpo implementation

updated a model 5 days ago

tomg-group-umd/huginn_swa_75_7_ema_0.9_merge

updated a model 5 days ago

tomg-group-umd/step-00006144-recurrence_full_512_0

View all activity

Organizations

New activity in tomg-group-umd/huginn-0125 5 days ago

Supervised fine-tuning and dpo implementation

#11 opened 3 months ago by

Vitabile

updated 13 models 5 days ago

updated a dataset 7 days ago

tomg-group-umd/huginn-dataset

Viewer • Updated 7 days ago • 274M • 13.1k • 5

New activity in tomg-group-umd/huginn-0125 12 days ago

Update paper reference and code link, and citation

#13 opened 15 days ago by

nielsr

New activity in tomg-group-umd/huginn_swa_100_10_avg_0.9_merge 15 days ago

Improve model card: Add paper and code links, update citation

#1 opened 15 days ago by

nielsr

New activity in tomg-group-umd/huginn-0125 15 days ago

Update paper reference and citation in model card

#12 opened 15 days ago by

nielsr

upvoted a collection 18 days ago

answer-matching

Collection

Free-form datasets, human annotations, and sample-level model outputs for "Answer Matching Outperforms Multiple Choice for Language Model Evaluation" • 2 items • Updated 19 days ago • 2

upvoted a paper 18 days ago

Answer Matching Outperforms Multiple Choice for Language Model Evaluation

Paper • 2507.02856 • Published 19 days ago • 8

Jonas Geiping

AI & ML interests

Recent Activity

Organizations

JonasGeiping's activity

Supervised fine-tuning and dpo implementation

Update paper reference and code link, and citation

Improve model card: Add paper and code links, update citation

Update paper reference and citation in model card