Maksim Sapronov

sapromak's activity

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

upvoted 2 papers 2 months ago

The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation

Paper • 2510.23393 • Published Oct 27, 2025 • 20

The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management

Paper • 2508.21433 • Published Aug 29, 2025 • 7

upvoted a paper 3 months ago

On Pretraining for Project-Level Code Completion

Paper • 2510.13697 • Published Oct 15, 2025 • 6

upvoted a collection 3 months ago

📁 Repository-Level Pre-Trained OpenCoder 🧩

Collection

All the checkpoints from Table 3 of the paper “On Pretraining for Project-Level Code Completion.” • 33 items • Updated Oct 17, 2025 • 3

upvoted a paper 3 months ago

PIPer: On-Device Environment Setup via Online Reinforcement Learning

Paper • 2509.25455 • Published Sep 29, 2025 • 37

upvoted a collection 7 months ago

OpenCoder

Collection

OpenCoder is an open and reproducible code LLM family which matches the performance of top-tier code LLMs. • 8 items • Updated Nov 23, 2024 • 88