Matvey

ANDREEV03

3 9

·

AI & ML interests

Building AI tools for small businesses

Recent Activity

liked a model about 21 hours ago

Phocinae/Phocinae-Largha-150M-v1

liked a model about 21 hours ago

autotrust/GEV-26B-Decide

upvoted a paper about 21 hours ago

Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?

View all activity

Organizations

None yet

upvoted 2 papers about 21 hours ago

Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?

Paper • 2610.08215 • Published 3 days ago • 131

STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

Paper • 2609.38169 • Published 12 days ago • 117

upvoted a paper about 1 month ago

Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models

Paper • 2608.25518 • Published Aug 26 • 56