TaekHyunPark

Thrillcrazyer's activity

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

updated a model about 19 hours ago

Thrillcrazyer/LoopUS_Qwen3-1.7B_Ver2.1_SFT

2B • Updated about 6 hours ago • 71

upvoted a paper 5 days ago

Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning

Paper • 2605.14386 • Published 6 days ago • 56

published a model 5 days ago

Thrillcrazyer/LoopUS_Qwen3-1.7B_Ver2.1_SFT

2B • Updated about 6 hours ago • 71

updated a model 6 days ago

Thrillcrazyer/LoopUS_Qwen3-1.7B_Ver2.1

2B • Updated 5 days ago • 64

New activity in Thrillcrazyer/Qwen3-8B_LoopUS 7 days ago

Add pipeline tag and improve model card

#1 opened 7 days ago by

nielsr

New activity in Thrillcrazyer/TinyLlama_v1.1_LoopUS 7 days ago

Add pipeline tag and improve model card

#1 opened 7 days ago by

nielsr

New activity in Thrillcrazyer/Qwen3_1.7B_LoopUS 7 days ago

Add pipeline tag and improve documentation

#1 opened 7 days ago by

nielsr

New activity in Thrillcrazyer/Qwen3-4B_LoopUS 7 days ago

Improve model card: add pipeline tag, paper link, and code link

#1 opened 7 days ago by

nielsr

New activity in Thrillcrazyer/Phi4_LoopUS 7 days ago

Add pipeline tag and improve model card

#1 opened 7 days ago by

nielsr

upvoted a collection 7 days ago

WTF GENIUS PAPERS

Collection

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 138 items • Updated 1 day ago • 27

updated a collection 7 days ago

LoopUS

Collection

8 items • Updated 7 days ago

authored a paper 7 days ago

LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models

Paper • 2605.11011 • Published 10 days ago • 9

updated a model 7 days ago

Thrillcrazyer/Qwen3_1.7B_LoopUS

Text Generation • 2B • Updated 7 days ago • 87 • 1