xziayro

xziayro's activity

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

upvoted an article about 8 hours ago

view article

Article

KV Caching Explained: Optimizing Transformer Inference Efficiency

• 

Jan 30

•

190

liked a model about 10 hours ago

jbilcke-hf/hunyan-video-lora-rickroll

Updated Jan 8 • 1

liked a Space about 11 hours ago

Running

MCP

Featured

43

Anim Lab AI

🔥

43

Turn boring math into engaging animation videos

upvoted 2 papers about 12 hours ago

RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards

Paper • 2512.00473 • Published 9 days ago • 10

Joint 3D Geometry Reconstruction and Motion Generation for 4D Synthesis from a Single Image

Paper • 2512.05044 • Published 4 days ago • 12

liked a model about 12 hours ago

X-GenGroup/PaCo-Reward-7B-Lora

Image-Text-to-Text • Updated about 12 hours ago • 1

upvoted 3 papers about 12 hours ago

EditThinker: Unlocking Iterative Reasoning for Any Image Editor

Paper • 2512.05965 • Published 3 days ago • 30

SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling

Paper • 2512.05343 • Published 4 days ago • 8

TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows

Paper • 2512.05150 • Published 5 days ago • 43

upvoted an article 1 day ago

view article

Article

Tensor Parallelism (TP) in Transformers: 5 Minutes to Understand

• 

5 days ago

•

52

liked a model 2 days ago

apple/starflow

Updated 7 days ago • 245

upvoted an article 2 days ago

view article

Article

We Got Claude to Fine-Tune an Open Source LLM

• 
• 

5 days ago

•

349

reacted to csabakecskemeti's post with 🚀 2 days ago

view post

Post

1170

FYI: Mistral.Ministral-3 dequantizer FP8->BF16

https://github.com/csabakecskemeti/ministral-3_dequantizer_fp8-bf16

(The instruct model weights are in FP8)

See translation

🚀

2

2

👍

1

1

+

Reply

liked a model 3 days ago

meituan-longcat/LongCat-Image

Text-to-Image • Updated about 8 hours ago • 99 • • 140

upvoted 5 papers 3 days ago

PixelDiT: Pixel Diffusion Transformers for Image Generation

Paper • 2511.20645 • Published 13 days ago • 25

Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression

Paper • 2512.05081 • Published 4 days ago • 27

LATTICE: Democratize High-Fidelity 3D Generation at Scale

Paper • 2512.03052 • Published 15 days ago • 9

Generative Neural Video Compression via Video Diffusion Prior

Paper • 2512.05016 • Published 4 days ago • 8

TV2TV: A Unified Framework for Interleaved Language and Video Generation

Paper • 2512.05103 • Published 4 days ago • 12

liked a Space 3 days ago

Running on Zero

MCP

Featured

47

LongCat Image Edit

👁

47

Generate or edit images using text prompts