Zhilin Wang

zhilinw's activity

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

updated a Space 3 days ago

Running

3

3

ProfBench

🦀

Human-annotated rubrics in Professional Tasks

New activity in nvidia/ProfBench 3 days ago

Full Set of Tasks and Rubrics

1

#3 opened 9 days ago by

post-train

updated a dataset 9 days ago

nvidia/HelpSteer3

Viewer • Updated 9 days ago • 99k • 2.28k • 83

updated a model 9 days ago

nvidia/Qwen3-Nemotron-32B-RLBFF

Text Generation • 33B • Updated 9 days ago • 940 • 25

liked a Space 9 days ago

Running

3

3

ProfBench

🦀

Human-annotated rubrics in Professional Tasks

updated a dataset 9 days ago

nvidia/ProfBench

Viewer • Updated 9 days ago • 40 • 916 • 13

published a Space 9 days ago

Running

3

3

ProfBench

🦀

Human-annotated rubrics in Professional Tasks

updated a collection 9 days ago

Reward Models 10-2025

Collection

A collection of great reward models for research and production • 6 items • Updated 3 days ago • 4

upvoted a collection 9 days ago

Reward Models 10-2025

Collection

A collection of great reward models for research and production • 6 items • Updated 3 days ago • 4

updated a model 10 days ago

nvidia/Qwen3-Nemotron-32B-GenRM-Principle

Text Generation • 33B • Updated 10 days ago • 112 • 6

upvoted an article 11 days ago

view article

Article

Can Your LLM Think Like a Professional? Introducing ProfBench

By and 7 others •

11 days ago

• 15

published an article 11 days ago

view article

Article

Can Your LLM Think Like a Professional? Introducing ProfBench

By and 7 others •

11 days ago

• 15

authored a paper 14 days ago

ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge

Paper • 2510.18941 • Published 18 days ago • 7

upvoted a paper 15 days ago

ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge

Paper • 2510.18941 • Published 18 days ago • 7

published a dataset 17 days ago

nvidia/ProfBench

Viewer • Updated 9 days ago • 40 • 916 • 13

updated a model 28 days ago

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

Text Generation • 71B • Updated 10 days ago • 877 • 2

authored a paper about 1 month ago

RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards

Paper • 2509.21319 • Published Sep 25 • 4

upvoted a paper about 1 month ago

RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards

Paper • 2509.21319 • Published Sep 25 • 4

commented a paper about 1 month ago

RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards

Paper • 2509.21319 • Published Sep 25 • 4 •

2

updated a dataset 4 months ago

nvidia/HelpSteer3

Viewer • Updated 9 days ago • 99k • 2.28k • 83