Sungbin Han

SungbiinHan's activity

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

upvoted a paper 14 days ago

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

Paper • 2603.19835 • Published 26 days ago • 337

liked a model 16 days ago

allenai/Olmo-3-1025-7B

Text Generation • 7B • Updated Feb 26 • 128k • 61

liked a model 18 days ago

allenai/OLMo-2-1124-7B

7B • Updated Jan 6, 2025 • 49.7k • 65

upvoted a paper 29 days ago

How Far Can Unsupervised RLVR Scale LLM Training?

Paper • 2603.08660 • Published Mar 9 • 58

liked 2 datasets about 1 month ago

zhuzilin/dapo-math-17k

Viewer • Updated Jul 25, 2025 • 17.4k • 2.91k • 5

BytedTsinghua-SIA/DAPO-Math-17k

Viewer • Updated Apr 18, 2025 • 1.79M • 9.23k • 166

upvoted 3 papers about 2 months ago

Rethinking the Trust Region in LLM Reinforcement Learning

Paper • 2602.04879 • Published Feb 4 • 37

Your Group-Relative Advantage Is Biased

Paper • 2601.08521 • Published Jan 13 • 158

Experiential Reinforcement Learning

Paper • 2602.13949 • Published Feb 15 • 72

upvoted a paper 3 months ago

Group-in-Group Policy Optimization for LLM Agent Training

Paper • 2505.10978 • Published May 16, 2025 • 20

liked a model 3 months ago

math-similarity/Bert-MLM_arXiv-MP-class_zbMath

Sentence Similarity • Updated Jun 6, 2024 • 2.61k • • 9

liked 2 datasets 3 months ago

DigitalLearningGmbH/MATH-lighteval

Viewer • Updated Jan 15, 2025 • 25k • 33.3k • 65

qwedsacf/competition_math

Viewer • Updated Jan 28, 2023 • 12.5k • 11.3k • 119

liked 2 models 3 months ago

Qwen/Qwen3-Embedding-8B

Feature Extraction • 8B • Updated Jul 7, 2025 • 1.76M • • 652

Qwen/Qwen3-Embedding-4B

Feature Extraction • Updated Jun 20, 2025 • 1.89M • 249

liked 2 datasets 5 months ago

nlile/hendrycks-MATH-benchmark

Viewer • Updated Jan 28, 2025 • 12.5k • 10.7k • 31

lime-nlp/DeepScaleR_Difficulty

Viewer • Updated Apr 10, 2025 • 5.06M • 121 • 11

liked a Space 5 months ago

Running on CPU Upgrade

Featured

3.1k

The Smol Training Playbook

📚

3.1k

The secrets to building world-class LLMs

liked a model 8 months ago

Qwen/Qwen3-Embedding-0.6B

Feature Extraction • 0.6B • Updated Jun 20, 2025 • 6.09M • • 979

liked a dataset 8 months ago

zwhe99/DeepMath-103K

Viewer • Updated May 29, 2025 • 103k • 7.24k • 357