Max Ryabinin's picture

2 4

Max Ryabinin

mryab

·

https://mryab.github.io/

AI & ML interests

Distributed training, natural language generation, efficient architectures for DL

Recent Activity

upvoted a paper 1 day ago

When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs

upvoted a paper 3 months ago

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

authored a paper 7 months ago

Towards Best Practices for Open Datasets for LLM Training

View all activity

Organizations

upvoted a paper 1 day ago

When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs

Paper • 2508.11383 • Published 6 days ago • 35

upvoted a paper 3 months ago

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

Paper • 2505.14669 • Published May 20 • 78

upvoted a paper about 1 year ago

SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices

Paper • 2406.02532 • Published Jun 4, 2024 • 13

upvoted a paper almost 2 years ago

Hypernymy Understanding Evaluation of Text-to-Image Models via WordNet Hierarchy

Paper • 2310.09247 • Published Oct 13, 2023 • 3