Boris Yangel

borisyangel's activity

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

upvoted 4 collections 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 • 22

Infinity-Instruct-Completions

Collection

Training data for speculative decoding draft models, containing model-generated responses for 660K prompts from Infinity-Instruct-0625. • 6 items • Updated Mar 13 • 4

Openhands Trajectories

Collection

Dataset of 67,074 OpenHands trajectories collected with Qwen3-Coder-480B-A35B-Instruct and two RFT checkpoints trained on the data • 3 items • Updated Dec 23, 2025 • 9

LK-Speculators

Collection

High-performance speculative decoding draft models trained using LK losses, a novel training objectives that directly optimize acceptance rate • 9 items • Updated Mar 3 • 6

upvoted a paper 7 months ago

SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale

Paper • 2602.23866 • Published Feb 27 • 92

upvoted a paper about 1 year ago

Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning

Paper • 2508.03501 • Published Aug 5, 2025 • 59