Ji Seunghyun

sorryhyun's activity

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

New activity in circlestone-labs/Anima 5 days ago

is `~` being tokenized to unk?

#134 opened 5 days ago by

sorryhyun

New activity in circlestone-labs/Anima 6 days ago

Proposal: Modulation Guidance — making AdaLN text-aware for quality steering

👍❤️ 15

9

#122 opened 16 days ago by

sorryhyun

commented a paper 10 days ago

Seedance 2.0: Advancing Video Generation for World Complexity

Paper • 2604.14148 • Published 12 days ago • 152 •

7

New activity in circlestone-labs/Anima 19 days ago

Artist style becomes inconsistent with multiple artists / longer prompts — detailed analysis & suggestions

🧠👍 19

25

#112 opened 21 days ago by

Henry-Yan

New activity in circlestone-labs/Anima about 1 month ago

Training LyCORIS for Anima

11

#92 opened about 1 month ago by

njs45

Suggestion: Using Karpathy’s "AutoResearch" for Anima training optimization

🤯😔 4

5

#87 opened about 1 month ago by

kdutt2000

New activity in circlestone-labs/Anima about 2 months ago

Qwen 3.5

❤️ 3

17

#67 opened about 2 months ago by

kdutt2000

What is this?

5

#68 opened about 2 months ago by

JLGY

liked a model about 2 months ago

Qwen/Qwen3.5-0.8B

Image-Text-to-Text • 0.9B • Updated Mar 2 • 2.94M • 511

upvoted a paper about 2 months ago

Imagination Helps Visual Reasoning, But Not Yet in Latent Space

Paper • 2602.22766 • Published Feb 26 • 44

New activity in circlestone-labs/Anima 2 months ago

Fine-tuned / uncensored versions of Qwen 0.6B

👍 8

46

#56 opened 2 months ago by

TeoR4eg

commented a paper 3 months ago

Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVR

Paper • 2602.05261 • Published Feb 5 • 52 •

5

liked 2 models 3 months ago

circlestone-labs/Anima

Updated 4 days ago • 357k • 1.14k

Qwen/Qwen3-TTS-12Hz-0.6B-Base

Text-to-Speech • Updated Jan 29 • 694k • 229

New activity in naver-hyperclovax/HyperCLOVAX-SEED-Think-32B 4 months ago

What Truly Korean-Capable LLM Development Should Prioritize?

👍 1

4

#7 opened 4 months ago by deleted

upvoted a paper 4 months ago

MiMo-V2-Flash Technical Report

Paper • 2601.02780 • Published Jan 6 • 38

liked 3 models 4 months ago

tencent/Youtu-LLM-2B

Text Generation • 2B • Updated Feb 24 • 879 • 226

tencent/WeDLM-8B-Instruct

Text Generation • 8B • Updated Jan 1 • 1.44k • 312

MiniMaxAI/MiniMax-M2.1

Text Generation • 229B • Updated Feb 13 • 29.5k • • 1.35k

updated a dataset 5 months ago

sorryhyun/commit_and_diffs

Viewer • Updated Dec 10, 2025 • 3.62k • 9