Alexander

djalexj's activity

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

upvoted a paper 10 days ago

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

Paper • 2602.23866 • Published 14 days ago • 83

upvoted a paper 11 days ago

LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding

Paper • 2602.23881 • Published 14 days ago • 18

upvoted a paper 29 days ago

Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards

Paper • 2602.10231 • Published about 1 month ago • 13

upvoted an article 2 months ago

view article

Article

TFLOPS Gap: Why FP4 MoE Kernel Engineering Matters on Blackwell

• 

Jan 5

•

14

upvoted a paper 4 months ago

Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance

Paper • 2511.13254 • Published Nov 17, 2025 • 136

upvoted a paper 7 months ago

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

Paper • 2508.03501 • Published Aug 5, 2025 • 59

upvoted a paper 10 months ago

SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents

Paper • 2505.20411 • Published May 26, 2025 • 93