← Authors

Max Ryabinin

21 papers · 2020–2025 · 5 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) πŸƒ Academic Marathon (5) 🌈 Renaissance Researcher (8) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (41) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (5) πŸ† Keyword Champion (2) ⚑ Prolific Year (5) πŸ’Ž Century Club (21) ❓ The Questioner πŸ—ƒοΈ Keyword Collector (90) πŸ”₯ Unstoppable (6)

Conferences

NIPS (10) EMNLP (4) ICML (4) ACL (2) IJCNLP (1)

Top co-authors

Alexander Borzunov (4) Michael Diskin (4) Beidi Chen (3) Percy Liang (2) Gennady Pekhimenko (2) Anton Voronov (2) Alexey Tikhonov (2) Avner May (2) Ce Zhang (2) Eduard Gorbunov (2)

Keywords

large language model (4) distributed training (3) communication efficiency (3) distributed learning (3) neural network training (2) speculative decoding (2) decentralized learning (2) model compression (2) token generation (2) decentralized training (2) batch processing (2) cross-lingual transfer (1) probabilistic modeling (1) kl divergence (1) machine translation (1) unsupervised learning (1) graph learning (1) distributed optimization (1) text classification (1) stochastic gradient descent (1)

Papers

Multilingual Language Model Pretraining using Machine-translated Data EMNLP 2025
Refined Assessment for Translation Evaluation: Rethinking Machine Translation Evaluation in the Era of Human-Level Systems EMNLP 2025
TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference ICML 2025
SpecExec: Massively Parallel Speculative Decoding For Interactive LLM Inference on Consumer Devices NIPS 2024
RedPajama: an Open Dataset for Training Large Language Models NIPS 2024
Sequoia: Scalable and Robust Speculative Decoding NIPS 2024
Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements ACL 2024
FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU ICML 2023
Distributed Inference and Fine-tuning of Large Language Models Over The Internet NIPS 2023
Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics NIPS 2023
SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient ICML 2023
Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees NIPS 2022
RuCoLA: Russian Corpus of Linguistic Acceptability EMNLP 2022
Secure Distributed Training at Scale ICML 2022
It’s All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning IJCNLP 2021
Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targets NIPS 2021
Distributed Deep Learning In Open Collaborations NIPS 2021
Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices NIPS 2021
It’s All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning ACL 2021
Embedding Words in Non-Vector Space with Unsupervised Graph Learning EMNLP 2020
Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts NIPS 2020