Kirill Gelvan

Kirili4ik's activity

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

upvoted a paper 2 days ago

OpenThoughts-Agent: Data Recipes for Agentic Models

Paper • 2606.24855 • Published 4 days ago • 43

liked a Space 5 days ago

Running

27

Weight-Space Geometry of Offline Reasoning Training

🧭

27

Interactive weight-space geometry of six reasoning losses

upvoted a collection 26 days ago

Mellum 2

Collection

Mellum2 model weights • 6 items • Updated 26 days ago • 123

authored a paper about 1 month ago

On Problems of Implicit Context Compression for Software Engineering Agents

Paper • 2605.11051 • Published May 11

commented a paper about 1 month ago

On Problems of Implicit Context Compression for Software Engineering Agents

Paper • 2605.11051 • Published May 11 •

1

updated a model about 1 month ago

Kirili4ik/ICAE-for-SWE-agents

Updated May 14

upvoted a collection 3 months ago

SWE-rebench-V2

Collection

SWE-rebench-V2 is a curated dataset of software-engineering tasks derived from real GitHub issues and pull requests. • 3 items • Updated Mar 3 • 18

upvoted 2 articles 3 months ago

view article

Article

Mixture of Experts (MoEs) in Transformers

• 
• 
• +5

ariG23498, pcuenq, merve, IlyasMoutawwakil, ArthurZ, sergiopaniego, Molbap

•

Feb 26

• 169

view article

Article

Mixture of Experts Explained

• 
• 
• +4

osanseviero, lewtun, philschmid, smangrul, ybelkada, pcuenq

•

Dec 11, 2023

• 1.15k

upvoted an article 6 months ago

view article

Article

We Got Claude to Fine-Tune an Open Source LLM

• 
• 

burtenshaw, evalstate

•

Dec 4, 2025

• 630

published a model 7 months ago

Kirili4ik/ICAE-for-SWE-agents

Updated May 14

liked a Space 8 months ago

Running on CPU Upgrade

Featured

3.22k

The Smol Training Playbook

📚

3.22k

The secrets to building world-class LLMs

upvoted an article 8 months ago

view article

Article

Granite 4.0 Nano: Just how small can you go?

• 

ibm-granite

•

Oct 28, 2025

• 125

upvoted a collection 8 months ago

🦫 PIPer

Collection

All the resources for our paper "PIPer: On-Device Environment Setup via Online Reinforcement Learning"! • 9 items • Updated Oct 1, 2025 • 3

upvoted a paper 9 months ago

PIPer: On-Device Environment Setup via Online Reinforcement Learning

Paper • 2509.25455 • Published Sep 29, 2025 • 38

liked a dataset 10 months ago

nebius/SWE-rebench

Viewer • Updated Dec 23, 2025 • 27.9k • 13.2k • 65

liked a model about 1 year ago

sggetao/icae

Updated Mar 30, 2024 • 5

upvoted an article about 1 year ago

view article

Article

CircleGuardBench: New Standard for Evaluating AI Moderation Models

• 

whitecircle

•

May 7, 2025

• 59

upvoted a paper about 1 year ago

Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers

Paper • 2504.20752 • Published Apr 29, 2025 • 96

liked a model about 1 year ago

Qwen/Qwen2.5-7B-Instruct

Text Generation • 8B • Updated Jan 12, 2025 • 12.7M • • 1.39k