罗天蔚

Cyan666's activity

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

upvoted a paper about 10 hours ago

Post-Trained MoE Can Skip Half Experts via Self-Distillation

Paper • 2605.18643 • Published 1 day ago • 25

liked 4 models 26 days ago

deepseek-ai/DeepSeek-V4-Pro

Text Generation • 862B • Updated 13 days ago • 3.62M • • 4.06k

deepseek-ai/DeepSeek-V4-Pro-Base

1.6T • Updated 22 days ago • 11.5k • 269

deepseek-ai/DeepSeek-V4-Flash

Text Generation • 158B • Updated 13 days ago • 2M • • 1.16k

deepseek-ai/DeepSeek-V4-Flash-Base

292B • Updated 22 days ago • 13.3k • 201

upvoted a paper 2 months ago

How Far Can Unsupervised RLVR Scale LLM Training?

Paper • 2603.08660 • Published Mar 9 • 59

liked a dataset 2 months ago

RUBBISHLIKE/SpaceR-151k

Preview • Updated Jul 7, 2025 • 249 • 7

liked a model 2 months ago

yyfz233/Pi3X

Image-to-3D • Updated Mar 11 • 47.2k • 9

published a dataset 10 months ago

Cyan666/open-images_full

Updated Jul 16, 2025 • 5

upvoted a paper 11 months ago

GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Paper • 2507.01006 • Published Jul 1, 2025 • 255

authored a paper 11 months ago

GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Paper • 2507.01006 • Published Jul 1, 2025 • 255

updated a dataset about 1 year ago

Cyan666/vqasynth_sample

Viewer • Updated May 13, 2025 • 5 • 25

published 2 datasets about 1 year ago

Cyan666/vqasynth_sample

Viewer • Updated May 13, 2025 • 5 • 25

Cyan666/vqasynth_sample_processed_full

Updated May 12, 2025 • 4

liked a dataset about 1 year ago

remyxai/SpaceThinker

Viewer • Updated Apr 23, 2025 • 12.7k • 248 • 13