Jiachen Ma

krystal7's activity

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

upvoted a paper 4 days ago

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 7 days ago • 203

updated 2 models about 2 months ago

krystal7/llama-8b-reflect-sft

Text Generation • 8B • Updated Jun 23 • 10

krystal7/Reflector-Internalizing-Safety-Llama-3.1-8B-RL

Text Generation • 8B • Updated Jun 23 • 14 • 1

upvoted a paper 3 months ago

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation

Paper • 2605.31264 • Published May 29 • 125

published a model 3 months ago

krystal7/Reflector-Internalizing-Safety-Llama-3.1-8B-RL

Text Generation • 8B • Updated Jun 23 • 14 • 1

upvoted a paper 5 months ago

AI Can Learn Scientific Taste

Paper • 2603.14473 • Published Mar 15 • 433

updated a model 7 months ago

krystal7/llama-8b-reflect-rl-segmented-math-knowledge-en-t-krystal7-reflectbonus-gs93

8B • Updated Jan 22 • 4

published a model 7 months ago

krystal7/llama-8b-reflect-rl-segmented-math-knowledge-en-t-krystal7-reflectbonus-gs93

8B • Updated Jan 22 • 4

updated a model 7 months ago

krystal7/llama-8b-reflect-rl-segmented-math-knowledge-en-t-krystal7-gs93

8B • Updated Jan 22 • 4

published 3 models 7 months ago

krystal7/llama-8b-reflect-rl-segmented-math-knowledge-en-t-krystal7-gs93

8B • Updated Jan 22 • 4

krystal7/llama-8b-reflect-sft

Text Generation • 8B • Updated Jun 23 • 10

krystal7/llama-8b-reflect-cot

Updated Jan 4

upvoted a paper about 1 year ago

OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation

Paper • 2506.02397 • Published Jun 3, 2025 • 36

updated a model almost 3 years ago

krystal7/airplane_cifar

Updated Oct 17, 2023