Kshitiz Khanal

kshitizkhanal7's activity

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

upvoted an article about 8 hours ago

view article

Article

Docmatix - a huge dataset for Document Visual Question Answering

• 
• 

Jul 18, 2024

•

78

upvoted an article 5 days ago

view article

Article

LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family

• 

7 days ago

•

64

liked a Space 7 days ago

Running

38

FunctionGemma Tuning Lab

📊

38

How to fine-tune FunctionGemma for tool calling

authored a paper about 1 month ago

Refining Graphical Neural Network Predictions Using Flow Matching for Optimal Power Flow with Constraint-Satisfaction Guarantee

Paper • 2512.11127 • Published Dec 11, 2025 • 1

upvoted an article about 2 months ago

view article

Article

We Got Claude to Fine-Tune an Open Source LLM

• 
• 

Dec 4, 2025

•

582

upvoted an article 2 months ago

view article

Article

We’re open-sourcing our text-to-image model and the process behind it

• 

Nov 12, 2025

•

76

liked a Space 2 months ago

Running on Zero

51

HuMo [Local]

👩

51

Reference based video generation

upvoted an article 3 months ago

view article

Article

Evaluate Your Own RAG: Why Best Practices Failed Us

• 

Nov 5, 2025

•

14

liked a model 3 months ago

merve/smol-vision

Image-Text-to-Text • Updated Nov 5, 2025 • 191

upvoted 2 articles 3 months ago

view article

Article

Building the Open Agent Ecosystem Together: Introducing OpenEnv

• 
• 
• +8

Oct 23, 2025

•

145

view article

Article

Supercharge your OCR Pipelines with Open Models

• 
• 
• +5

Oct 21, 2025

•

300

liked a model 3 months ago

PaddlePaddle/PaddleOCR-VL

Image-Text-to-Text • 1.0B • Updated Dec 11, 2025 • 15.7k • 1.51k

liked a model 4 months ago

opendatalab/MinerU2.5-2509-1.2B

Image-Text-to-Text • 1B • Updated Sep 29, 2025 • 805k • 316

liked a Space 4 months ago

Running

Featured

152

Granite Docling 258M WebGPU

🐣

152

Convert document images to HTML

upvoted a collection 4 months ago

PP-OCRv5

Collection

PP-OCRv5 is the latest text recognition solution, supporting Simplified Chinese, Chinese Pinyin, Traditional Chinese, English, and Japanese • 13 items • Updated Sep 15, 2025 • 51

upvoted an article 4 months ago

view article

Article

Model Quality: Hugging Face Is All You Need

• 

Sep 26, 2025

•

23

liked a Space 5 months ago

Running on Zero

Featured

31

Finegrain Product Placement LoRA

📚

31

Flux Kontext extended with product placement capabilities

upvoted an article 5 months ago

view article

Article

Tricks from OpenAI gpt-oss YOU 🫵 can use with transformers

• 
• 
• +5

Sep 11, 2025

•

178

liked a Space 5 months ago

Running on Zero

MCP

18

POINTS Reader OCR

📖

18

Vision-Language Models for Document Conversion

liked a model 5 months ago

tencent/POINTS-Reader

Image-Text-to-Text • 4B • Updated Sep 12, 2025 • 608k • 97