Zhilin Wang

zhilinw's activity

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

updated a dataset 3 days ago

nvidia/HelpSteer3

Viewer • Updated 3 days ago • 99k • 2.36k • 54

updated 6 models 9 days ago

nvidia/Llama-3_3-Nemotron-Super-49B-GenRM

Text Generation • 50B • Updated 9 days ago • 20 • 5

nvidia/Llama-3_3-Nemotron-Super-49B-GenRM-Multilingual

Text Generation • 50B • Updated 9 days ago • 40 • 5

nvidia/Llama-3.3-Nemotron-70B-Reward

Text Generation • 71B • Updated 9 days ago • 17 • 2

nvidia/Llama-3.3-Nemotron-70B-Reward-Multilingual

Text Generation • 71B • Updated 9 days ago • 64 • 3

nvidia/Qwen-2.5-Nemotron-32B-Reward

Text Classification • 32B • Updated 9 days ago • 9 • 1

nvidia/Qwen-3-Nemotron-32B-Reward

Text Classification • 32B • Updated 9 days ago • 36 • 3

New activity in nvidia/Llama-3.1-Nemotron-70B-Reward-HF about 1 month ago

Comparability of the results for different prompts

1

#9 opened about 1 month ago by

treehugg3

New activity in nvidia/HelpSteer3 about 1 month ago

Request access to ground-truth helpfulness scores for training Generative Reward Models (non-BT)

2

#5 opened about 1 month ago by

andy-pi

The HelpSteer datasets don't overlap, right?

2

#2 opened 3 months ago by

treehugg3

For the data on Edit_quality, how to map the relationship between response and feedback?

1

#4 opened about 1 month ago by

bittersweet

authored a paper about 2 months ago

HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages

Paper • 2505.11475 • Published May 16 • 3

upvoted a paper about 2 months ago

HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages

Paper • 2505.11475 • Published May 16 • 3

commented a paper about 2 months ago

HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages

Paper • 2505.11475 • Published May 16 • 3 •

2

New activity in nvidia/HelpSteer3 about 2 months ago

Add task category, update paper link

1

#3 opened about 2 months ago by

nielsr

commented a paper 4 months ago

Dedicated Feedback and Edit Models Empower Inference-Time Scaling for Open-Ended General-Domain Tasks

Paper • 2503.04378 • Published Mar 6 • 7 •

4

published a dataset 4 months ago

nvidia/HelpSteer3

Viewer • Updated 3 days ago • 99k • 2.36k • 54

published 3 models 4 months ago

nvidia/Llama-3.3-Nemotron-70B-Select

Text Generation • 71B • Updated Mar 18 • 2.05k • • 9

nvidia/Llama-3.3-Nemotron-70B-Edit

Text Generation • 71B • Updated Mar 18 • 83 • 3

nvidia/Llama-3.3-Nemotron-70B-Feedback

Text Generation • 71B • Updated Mar 18 • 99 • 7