Roman Shevchuk

Rashevchuk's activity

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

upvoted 3 papers 26 days ago

AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks

Paper • 2609.38288 • Published 28 days ago • 118

MaLiang-Harness: A Programmable Path to Image and Video Generation

Paper • 2609.34309 • Published 29 days ago • 220

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Paper • 2609.36484 • Published 28 days ago • 208

upvoted a paper about 1 month ago

LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

Paper • 2609.17488 • Published Sep 15 • 318

upvoted a paper 2 months ago

FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis

Paper • 2608.18580 • Published Aug 19 • 44