Md Imbesat Hassan Rizvi

imbesat-rizvi's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a collection 9 days ago

SPARE-PRM

Collection

Process Reward Models (PRMs) trained using Single-Pass Annotation with Reference-Guided Evaluation (SPARE) methodology proposed in our AAAI-2026 paper • 2 items • Updated 9 days ago

updated a model 4 months ago

UKPLab/Qwen2.5-3b-spare-prm-math

Text Generation • 3B • Updated Aug 21 • 7

published a model 4 months ago

UKPLab/Qwen2.5-3b-spare-prm-math

Text Generation • 3B • Updated Aug 21 • 7

updated a model 6 months ago

UKPLab/Llama-3-8b-spare-prm-math

Text Generation • 8B • Updated Jun 19 • 22

updated a dataset 7 months ago

UKPLab/sparp

Viewer • Updated Jun 5 • 417k • 125 • 1

published a model 7 months ago

UKPLab/Llama-3-8b-spare-prm-math

Text Generation • 8B • Updated Jun 19 • 22

updated a dataset 12 months ago

pensieves/math

Viewer • Updated Dec 28, 2024 • 12.5k • 58

updated a dataset about 1 year ago

pensieves/gsm8k

Viewer • Updated Sep 30, 2024 • 8.79k • 76

updated a dataset over 1 year ago

pensieves/alpha

Viewer • Updated Sep 26, 2024 • 22.4k • 124

updated 2 datasets over 3 years ago

pensieves/newsgroups

Updated May 13, 2022 • 46

pensieves/mimicause

Updated Mar 29, 2022 • 76 • 3