Alexander's picture

Alexander

djalexj

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding

new activity about 2 months ago

nebius/SWE-rebench-V2:Can you add in Qwen3.5 and other series of models for testing?

new activity about 2 months ago

nebius/SWE-rebench-V2:Can you add in Qwen3.5 and other series of models for testing?

View all activity

Organizations

upvoted a paper 2 days ago

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding

Paper • 2605.10453 • Published 4 days ago • 8

upvoted 2 papers 2 months ago

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

Paper • 2602.23866 • Published Feb 27 • 89

LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding

Paper • 2602.23881 • Published Feb 27 • 18

upvoted a paper 3 months ago

Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards

Paper • 2602.10231 • Published Feb 10 • 13

upvoted an article 4 months ago

Article

TFLOPS Gap: Why FP4 MoE Kernel Engineering Matters on Blackwell

apsys

•

Jan 5

• 14

upvoted a paper 6 months ago

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

Paper • 2511.13254 • Published Nov 17, 2025 • 140

upvoted a paper 9 months ago

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

Paper • 2508.03501 • Published Aug 5, 2025 • 59

upvoted a paper 12 months ago

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

Paper • 2505.20411 • Published May 26, 2025 • 96