KyujinHan

kyujinpy

·

https://kyujinpy.tistory.com/

KyujinHan

AI & ML interests

Diffusion, LLM, 3D vision

Recent Activity

liked a model 6 days ago

Lightricks/LTX-2.5-22b-IC-LoRA-Ingredients

liked a model 6 days ago

larryvrh/MiniMax-H3-Turbo-Lora

liked a model 8 days ago

TencentARC/GAE-D64-1B

View all activity

Organizations

upvoted 2 papers 11 days ago

Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation

Paper • 2609.20744 • Published 17 days ago • 53

GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation

Paper • 2609.24981 • Published 13 days ago • 72

upvoted a paper 23 days ago

Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation

Paper • 2609.08084 • Published 26 days ago • 72

upvoted a paper about 2 months ago

Count Anything

Paper • 2605.30846 • Published May 29 • 10

upvoted 3 papers 2 months ago

ID-V2V: Identity-Preserving Video Restylization

Paper • 2607.22830 • Published Jul 24 • 11

Explicit Layer Modeling for Video Object Insertion and Layer Decomposition

Paper • 2607.25802 • Published Jul 28 • 8

Native and Compact Structured Latents for 3D Generation

Paper • 2512.14692 • Published Dec 16, 2025 • 7

upvoted a paper 3 months ago

AVControl: Efficient Framework for Training Audio-Visual Controls

Paper • 2603.24793 • Published Mar 25 • 30

upvoted a paper 4 months ago

HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos

Paper • 2605.17543 • Published May 19 • 13

upvoted a collection over 1 year ago

Gukbap-Series LMM

6 items • Updated Apr 2, 2025 • 1

upvoted a collection almost 2 years ago

Ovis1.6

With 29B parameters, Ovis1.6-Gemma2-27B achieves exceptional performance in the OpenCompass benchmark, ranking among the top-tier open-source MLLMs. • 5 items • Updated Nov 26, 2024 • 13

upvoted a collection about 2 years ago

Gukbap-Series-LLM

General Korean LLM • 5 items • Updated Apr 2, 2025 • 2

upvoted 3 collections over 2 years ago

State-Of-The-Art Korean-RAG LM

Markr AI's RAG LLM (based on Ko-Mixtral) • 5 items • Updated Feb 11, 2024 • 2

Korean Corpus (merge ver.)

1 item • Updated Feb 3, 2024 • 1

Korean-Corpus lists

11 items • Updated Feb 4, 2024 • 1