Sungbin Han

SungbiinHan's activity

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

upvoted an article 6 days ago

view article

Article

Design choices for Vision Language Models in 2024

• 

gigant

•

Apr 16, 2024

• 35

upvoted a paper 12 days ago

Robot Learning: A Tutorial

Paper • 2510.12403 • Published Oct 14, 2025 • 135

upvoted a paper 15 days ago

ProcessBench: Identifying Process Errors in Mathematical Reasoning

Paper • 2412.06559 • Published Dec 9, 2024 • 88

liked a dataset 20 days ago

Skylion007/openwebtext

Viewer • Updated Dec 26, 2025 • 8.01M • 71k • 514

upvoted a paper 24 days ago

Interpretable Reward Model via Sparse Autoencoder

Paper • 2508.08746 • Published Aug 12, 2025 • 2

liked 2 models 25 days ago

Schrieffer/Llama-SARM-4B-PostSAEPretrain

Feature Extraction • 5B • Updated Dec 11, 2025 • 16 • 2

Schrieffer/Llama-SARM-4B

Reinforcement Learning • 5B • Updated Dec 11, 2025 • 86 • 2

liked a model 26 days ago

Qwen/SAE-Res-Qwen3.5-27B-W80K-L0_50

Updated 20 days ago • 119 • 37

upvoted a collection 26 days ago

Qwen-Scope

Collection

16 items • Updated 19 days ago • 68

liked a model 28 days ago

Qwen/Qwen2.5-Math-PRM-7B

Text Classification • 8B • Updated Jan 17, 2025 • 181k • 89

upvoted a paper about 1 month ago

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published Mar 24, 2025 • 121

liked a model about 1 month ago

adamkarvonen/qwen_coder_32b_saes

Updated May 14, 2025 • 2

upvoted a collection about 1 month ago

Qwen SAEs

Collection

5 items • Updated Nov 8, 2025 • 2

liked 6 models about 1 month ago

adamkarvonen/qwen3-14b-saes

Updated Nov 24, 2025 • 2

adamkarvonen/qwen3-32b-saes

Updated Nov 24, 2025 • 4

caiovicentino1/Qwen3.5-4B-SAE-L18-topk

Feature Extraction • Updated Apr 18 • 1

adamkarvonen/qwen3-8b-saes

Updated Nov 24, 2025 • 6

adamkarvonen/qwen3-1.7b-saes

Updated Nov 24, 2025 • 4

andyrdt/saes-qwen2.5-7b-instruct

Updated May 26, 2025 • 2

upvoted a paper 2 months ago

FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization

Paper • 2603.19835 • Published Mar 20 • 352