Junyeong Song

junyeong-nero's activity

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

upvoted a paper about 17 hours ago

Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL

Paper • 2610.33512 • Published 4 days ago • 29

liked a model about 17 hours ago

RedHatAI/GLM-5.3-Flash-NVFP4

Image-Text-to-Text • 169B • Updated 38 minutes ago • 23.8k • 47

liked a model 8 days ago

deepseek-ai/DeepSeek-V4.1-Flash-1017

Image-Text-to-Text • 763B • Updated 11 days ago • 106k • • 3.36k

liked a model 12 days ago

meta-models/Muse-Spark-Open-816B-A42B

Image-Text-to-Text • 822B • Updated 12 days ago • 7.77k • • 712

upvoted a paper 13 days ago

KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization

Paper • 2610.14448 • Published 18 days ago • 49

updated 2 datasets 26 days ago

junyeong-nero/synthetic-ocr-images-ja

Viewer • Updated 26 days ago • 1k • 68

junyeong-nero/synthetic-ocr-images-ko

Viewer • Updated 26 days ago • 1k • 65

updated a dataset 27 days ago

junyeong-nero/synthetic-ocr-images-ko-1M

Viewer • Updated 26 days ago • 1M • 741

published a dataset 27 days ago

junyeong-nero/synthetic-ocr-images-ko-1M

Viewer • Updated 26 days ago • 1M • 741

upvoted a paper 28 days ago

Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR

Paper • 2609.37868 • Published 29 days ago • 65

liked a model 28 days ago

schift-io/schift-ocr-1-beta

Image-Text-to-Text • 4B • Updated 27 days ago • 821 • 18

liked 3 models about 1 month ago

jinaai/jina-ocr-v1

Image-Text-to-Text • 3B • Updated Sep 18 • 3.53k • 202

openbmb/MiniCPM5-2B

Text Generation • 3B • Updated 29 days ago • 1.22M • 1.82k

Edge0/Edge0-35B-A3B-preview

Text Generation • 35B • Updated 27 days ago • 4.8k • 1.08k

upvoted a paper about 1 month ago

Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills

Paper • 2609.02749 • Published Sep 2 • 465

upvoted a paper about 2 months ago

SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem

Paper • 2609.07064 • Published Sep 7 • 87

liked a model about 2 months ago

XHToken/Spark-X2.5-4B

Text Generation • 4B • Updated Sep 15 • 33.8k • 1.44k

upvoted a paper about 2 months ago

LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes

Paper • 2609.03796 • Published Sep 3 • 114

liked a model about 2 months ago

zai-org/GLM-5.3

Text Generation • 753B • Updated 13 days ago • 2.18M • • 2.33k

upvoted a paper about 2 months ago

WHALE: A Simple Recipe for Joint Harness-Weight Optimization

Paper • 2609.00196 • Published Aug 31 • 40