xziayro

xziayro's activity

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

upvoted an article about 3 hours ago

view article

Article

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

• 

4 days ago

•

45

liked a model about 21 hours ago

apple/starflow

Updated 6 days ago • 237

upvoted an article about 21 hours ago

view article

Article

We Got Claude to Fine-Tune an Open Source LLM

• 
• 

4 days ago

•

270

reacted to csabakecskemeti's post with 🚀 about 22 hours ago

view post

Post

1104

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 2 days ago

meituan-longcat/LongCat-Image

Text-to-Image • Updated about 9 hours ago • • 111

upvoted 5 papers 2 days ago

PixelDiT: Pixel Diffusion Transformers for Image Generation

Paper • 2511.20645 • Published 12 days ago • 25

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

Paper • 2512.05081 • Published 3 days ago • 19

LATTICE: Democratize High-Fidelity 3D Generation at Scale

Paper • 2512.03052 • Published 14 days ago • 7

Generative Neural Video Compression via Video Diffusion Prior

Paper • 2512.05016 • Published 3 days ago • 7

TV2TV: A Unified Framework for Interleaved Language and Video Generation

Paper • 2512.05103 • Published 3 days ago • 10

liked a Space 2 days ago

Running on Zero

MCP

39

LongCat Image Edit

👁

39

Generate or edit images using text prompts

liked a model 2 days ago

ostris/Flex.2-preview

Text-to-Image • Updated Apr 25 • 888 • 382

upvoted 3 papers 2 days ago

Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation

Paper • 2512.04678 • Published 3 days ago • 32

UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformers

Paper • 2512.04504 • Published 4 days ago • 13

NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation

Paper • 2512.05106 • Published 3 days ago • 11

upvoted 2 papers 3 days ago

Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model

Paper • 2512.01030 • Published 7 days ago • 16

Accelerating Streaming Video Large Language Models via Hierarchical Token Compression

Paper • 2512.00891 • Published 7 days ago • 14

liked a Space 3 days ago

Running on Zero

14

ViBT

🐠

14

Transform video style with text prompts

liked a model 3 days ago

Yuanshi/ViBT

Any-to-Any • Updated about 7 hours ago • 16

upvoted a paper 3 days ago

CookAnything: A Framework for Flexible and Consistent Multi-Step Recipe Image Generation

Paper • 2512.03540 • Published 4 days ago • 11