Behrooz Azarkhalili

ermiaazarkhalili's activity

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

upvoted a paper 5 days ago

DeepCode: Open Agentic Coding

Paper • 2512.07921 • Published 12 days ago • 30

upvoted an article 10 days ago

view article

Article

How We Use Claude Code Skills to Run 1,000+ ML Experiments a Day

• 

12 days ago

•

45

upvoted 3 articles 16 days ago

view article

Article

Building Deep Research: How we Achieved State of the Art

• 

26 days ago

•

28

view article

Article

Smol2Operator: Post-Training GUI Agents for Computer Use

• 
• 
• +3

Sep 23

•

133

view article

Article

We Got Claude to Fine-Tune an Open Source LLM

• 
• 

17 days ago

•

521

upvoted an article 17 days ago

view article

Article

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

• 

17 days ago

•

60

upvoted an article 20 days ago

view article

Article

Building Jobly: Semantic Job Matching with RAG and Vector Embeddings

• 

22 days ago

•

12

upvoted an article 2 months ago

view article

Article

Supercharge your OCR Pipelines with Open Models

• 
• 
• +5

Oct 21

•

279

upvoted a collection 3 months ago

ExGRPO

Collection

Model collections trained using ExGRPO. • 7 items • Updated Oct 3 • 1

upvoted a paper 4 months ago

Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs

Paper • 2508.14896 • Published Aug 20 • 22

upvoted 4 articles 4 months ago

view article

Article

Upskill your LLMs With Gradio MCP Servers

• 

Jul 9

•

20

view article

Article

Generate Images with Claude and Hugging Face

• 

Aug 19

•

36

view article

Article

Multimodal RAG with Colpali, Milvus and VLMs

• 

Dec 10, 2024

•

10

view article

Article

How I Built 7 Custom Gradio Components in Just 12 Days!

• 

Aug 12

•

7

upvoted an article 5 months ago

view article

Article

Vision Language Model Alignment in TRL ⚡️

• 
• 
• +3

Aug 7

•

102

upvoted a collection 5 months ago

Qwen3-MegaScience

Collection

Qwen3-MegaScience • 5 items • Updated Jul 23 • 4

upvoted a paper 5 months ago

MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning

Paper • 2507.16812 • Published Jul 22 • 63

upvoted an article 5 months ago

view article

Article

Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face

• 
• 
• +3

Jul 29

•

205

upvoted a collection 5 months ago

Kimi-K2

Collection

Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence • 5 items • Updated Nov 14 • 160

upvoted an article 6 months ago

view article

Article

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

• 

Feb 11

•

92