Dmitrii Stoianov

heylimon's activity

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

upvoted a paper about 2 months ago

Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents

Paper • 2604.10674 • Published Apr 12 • 2

upvoted a paper 6 months ago

F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare

Paper • 2602.06717 • Published Feb 6 • 76

upvoted a paper 8 months ago

T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground

Paper • 2512.10430 • Published Dec 11, 2025 • 121

upvoted a paper 12 months ago

Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success

Paper • 2508.04280 • Published Aug 6, 2025 • 35

upvoted 2 papers about 1 year ago

OpenThoughts: Data Recipes for Reasoning Models

Paper • 2506.04178 • Published Jun 4, 2025 • 56

MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space

Paper • 2504.13835 • Published Apr 18, 2025 • 39

upvoted 4 papers over 1 year ago

CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom

Paper • 2503.01836 • Published Mar 3, 2025 • 16

System Message Generation for User Preferences using Open-Source Models

Paper • 2502.11330 • Published Feb 17, 2025 • 15

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Paper • 2502.03032 • Published Feb 5, 2025 • 59

How to Synthesize Text Data without Model Collapse?

Paper • 2412.14689 • Published Dec 19, 2024 • 52

upvoted a collection over 1 year ago

RL/Alignment

Collection

202 items • Updated Jan 15 • 27

upvoted 2 papers over 1 year ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published Feb 3, 2025 • 113

Phi-4 Technical Report

Paper • 2412.08905 • Published Dec 12, 2024 • 124

upvoted a paper almost 2 years ago

Instruction Pre-Training: Language Models are Supervised Multitask Learners

Paper • 2406.14491 • Published Jun 20, 2024 • 96

upvoted a paper about 2 years ago

Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian

Paper • 2405.13929 • Published May 22, 2024 • 55

upvoted a paper over 2 years ago

Learn Your Reference Model for Real Good Alignment

Paper • 2404.09656 • Published Apr 15, 2024 • 91