Adina Yakefu

AdinaY's activity

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

updated a collection about 1 hour ago

2026 January⛄️ - China Open Source Highlights

Collection

34 items • Updated about 1 hour ago • 2

liked a model about 1 hour ago

OpenMOSS-Team/MOVA-360p

Updated about 5 hours ago • 2

updated a collection about 2 hours ago

2026 January⛄️ - China Open Source Highlights

Collection

34 items • Updated about 1 hour ago • 2

liked a model about 2 hours ago

PaddlePaddle/PaddleOCR-VL-1.5

Image-Text-to-Text • 1.0B • Updated about 2 hours ago • 20

upvoted a collection about 4 hours ago

FLUX-Makeup

Collection

We propose FLUX-Makeup, a high-fidelity, identityconsistent, and robust makeup transfer framework that eliminates the need for any auxiliary face-cont • 2 items • Updated about 5 hours ago • 1

liked a dataset about 18 hours ago

unitreerobotics/G1_Clean_Table

Viewer • Updated about 9 hours ago • 266k • 2 • 3

liked a model about 18 hours ago

Skywork/SkyReels-V3-A2V-19B

Image-to-Video • Updated 1 day ago • 17 • 14

updated a collection about 19 hours ago

2026 January⛄️ - China Open Source Highlights

Collection

34 items • Updated about 1 hour ago • 2

liked a model about 19 hours ago

Skywork/SkyReels-V3-R2V-14B

Image-to-Video • Updated 1 day ago • 8

liked a Space about 19 hours ago

Running

7

SkyReels V3

🖼

7

Multimodal Video Generation Model

updated a collection about 19 hours ago

2026 January⛄️ - China Open Source Highlights

Collection

34 items • Updated about 1 hour ago • 2

liked a model about 19 hours ago

robbyant/lingbot-world-base-cam

Image-to-Video • Updated about 10 hours ago • 43

posted an update about 19 hours ago

view post

Post

94

LongCat-Flash-Lite🔥 a non-thinking MoE model released by Meituan LongCat team.

meituan-longcat/LongCat-Flash-Lite

✨ Total 68.5B / 3B active - MIT license
✨ 256k context
✨ Faster inference with N-gram embeddings

See translation

• 

Reply

updated a collection about 19 hours ago

2026 January⛄️ - China Open Source Highlights

Collection

34 items • Updated about 1 hour ago • 2

liked a model about 19 hours ago

meituan-longcat/LongCat-Flash-Lite

Text Generation • 100B • Updated about 20 hours ago • 2 • 68

reacted to danielhanchen's post with 🚀 about 20 hours ago

view post

Post

1324

You can now run Kimi K2.5 locally! 🔥

We shrank the 1T model to 240GB (-60%) via Dynamic 1-bit.
Get >40 tok/s on 242GB or 622GB VRAM/RAM for near full precision.

GGUF: unsloth/Kimi-K2.5-GGUF

Guide: https://unsloth.ai/docs/models/kimi-k2.5

See translation

• 
• 

🚀

8

8

😎

3

3

👀

1

1

+

Reply

posted an update 1 day ago

view post

Post

126

Ant Group is going big on robotics 🤖

They just dropped their first VLA and depth perception foundation model on huggingface.

✨ LingBot-VLA :
- Trained on 20k hours of real-world robot data
- 9 robot embodiments
- Clear no-saturation scaling laws
- Apache 2.0

Model: https://huggingface.co/collections/robbyant/lingbot-vla
Paper:
A Pragmatic VLA Foundation Model (2601.18692)

✨ LingBot-Depth:
- Metric-accurate 3D from noisy, incomplete depth
- Masked Depth Modeling (self-supervised)
- RGB–depth alignment, works with <5% sparse depth
- Apache 2.0

Model: https://huggingface.co/collections/robbyant/lingbot-depth
Paper:
Masked Depth Modeling for Spatial Perception (2601.17895)

See translation

Reply

replied to their post 1 day ago

view reply

Feel free to share your thoughts in the comment on the blog

upvoted 2 papers 1 day ago

A Pragmatic VLA Foundation Model

Paper • 2601.18692 • Published 3 days ago • 37

Masked Depth Modeling for Spatial Perception

Paper • 2601.17895 • Published 4 days ago • 20