Max Ryabinin

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 34

Top Topics

Training Documents

Variational Inequalities

Top Venues

Publications

Zhuoming Chen, Avner May, Ruslan Svirschevski, Yuhsun Huang, Max Ryabinin, Zhihao Jia, Beidi Chen
Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding. CoRR (2024)
Anton Voronov, Lena Wolf, Max Ryabinin
Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements. ACL (Findings) (2024)
Anton Voronov, Lena Wolf, Max Ryabinin
Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements. CoRR (2024)
Giwon Hong, Aryo Pradipta Gema, Rohit Saxena, Xiaotang Du, Ping Nie, Yu Zhao, Laura Perez-Beltrachini, Max Ryabinin, Xuanli He, Clémentine Fourrier, Pasquale Minervini
The Hallucinations Leaderboard - An Open Effort to Measure Hallucinations in Large Language Models. CoRR (2024)
Ruslan Svirschevski, Avner May, Zhuoming Chen, Beidi Chen, Zhihao Jia, Max Ryabinin
SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices. CoRR (2024)
Ying Sheng, Lianmin Zheng, Binhang Yuan, Zhuohan Li, Max Ryabinin, Daniel Y. Fu, Zhiqiang Xie, Beidi Chen, Clark W. Barrett, Joseph E. Gonzalez, Percy Liang, Christopher Ré, Ion Stoica, Ce Zhang
High-throughput Generative Inference of Large Language Models with a Single GPU. CoRR (2023)
Anton Voronov, Mikhail Khoroshikh, Artem Babenko, Max Ryabinin
Is This Loss Informative? Speeding Up Textual Inversion with Deterministic Objective Evaluation. CoRR (2023)
Ying Sheng, Lianmin Zheng, Binhang Yuan, Zhuohan Li, Max Ryabinin, Beidi Chen, Percy Liang, Christopher Ré, Ion Stoica, Ce Zhang
FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU. ICML (2023)
Anton Voronov, Mikhail Khoroshikh, Artem Babenko, Max Ryabinin
Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics. NeurIPS (2023)
Max Ryabinin, Tim Dettmers, Michael Diskin, Alexander Borzunov
SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient. ICML (2023)
Max Ryabinin, Tim Dettmers, Michael Diskin, Alexander Borzunov
SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient. CoRR (2023)
Anton Baryshnikov, Max Ryabinin
Hypernymy Understanding Evaluation of Text-to-Image Models via WordNet Hierarchy. CoRR (2023)
Alexander Borzunov, Max Ryabinin, Artem Chumachenko, Dmitry Baranchuk, Tim Dettmers, Younes Belkada, Pavel Samygin, Colin A. Raffel
Distributed Inference and Fine-tuning of Large Language Models Over The Internet. NeurIPS (2023)
Alexander Borzunov, Max Ryabinin, Artem Chumachenko, Dmitry Baranchuk, Tim Dettmers, Younes Belkada, Pavel Samygin, Colin Raffel
Distributed Inference and Fine-tuning of Large Language Models Over The Internet. CoRR (2023)
Aleksandr Beznosikov, Peter Richtárik, Michael Diskin, Max Ryabinin, Alexander V. Gasnikov
Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees. NeurIPS (2022)
Vladislav Mikhailov, Tatiana Shamardina, Max Ryabinin, Alena Pestova, Ivan Smurov, Ekaterina Artemova
RuCoLA: Russian Corpus of Linguistic Acceptability. EMNLP (2022)
Eduard Gorbunov, Alexander Borzunov, Michael Diskin, Max Ryabinin
Secure Distributed Training at Scale. ICML (2022)
Vladislav Mikhailov, Tatiana Shamardina, Max Ryabinin, Alena Pestova, Ivan Smurov, Ekaterina Artemova
RuCoLA: Russian Corpus of Linguistic Acceptability. CoRR (2022)
Alexander Borzunov, Dmitry Baranchuk, Tim Dettmers, Max Ryabinin, Younes Belkada, Artem Chumachenko, Pavel Samygin, Colin Raffel
Petals: Collaborative Inference and Fine-tuning of Large Models. CoRR (2022)
Alexander Borzunov, Max Ryabinin, Tim Dettmers, Quentin Lhoest, Lucile Saulnier, Michael Diskin, Yacine Jernite, Thomas Wolf
Training Transformers Together. CoRR (2022)
Michael Diskin, Alexey Bukhtiyarov, Max Ryabinin, Lucile Saulnier, Quentin Lhoest, Anton Sinitsin, Dmitriy Popov, Dmitry Pyrkin, Maxim Kashirin, Alexander Borzunov, Albert Villanova del Moral, Denis Mazur, Ilia Kobelev, Yacine Jernite, Thomas Wolf, Gennady Pekhimenko
Distributed Deep Learning in Open Collaborations. CoRR (2021)
Max Ryabinin, Andrey Malinin, Mark J. F. Gales
Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targets. NeurIPS (2021)
Michael Diskin, Alexey Bukhtiyarov, Max Ryabinin, Lucile Saulnier, Quentin Lhoest, Anton Sinitsin, Dmitry Popov, Dmitry V. Pyrkin, Maxim Kashirin, Alexander Borzunov, Albert Villanova del Moral, Denis Mazur, Ilia Kobelev, Yacine Jernite, Thomas Wolf, Gennady Pekhimenko
Distributed Deep Learning In Open Collaborations. NeurIPS (2021)
Max Ryabinin, Eduard Gorbunov, Vsevolod Plokhotnyuk, Gennady Pekhimenko
Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices. CoRR (2021)
Alexey Tikhonov, Max Ryabinin
It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning. CoRR (2021)
Alexander Borzunov, Max Ryabinin, Tim Dettmers, Quentin Lhoest, Lucile Saulnier, Michael Diskin, Yacine Jernite, Thomas Wolf
Training Transformers Together. NeurIPS (Competition and Demos) (2021)
Max Ryabinin, Andrey Malinin, Mark J. F. Gales
Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targets. CoRR (2021)
Aleksandr Beznosikov, Peter Richtárik, Michael Diskin, Max Ryabinin, Alexander V. Gasnikov
Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees. CoRR (2021)
Max Ryabinin, Eduard Gorbunov, Vsevolod Plokhotnyuk, Gennady Pekhimenko
Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices. NeurIPS (2021)
Eduard Gorbunov, Alexander Borzunov, Michael Diskin, Max Ryabinin
Secure Distributed Training at Scale. CoRR (2021)
Alexey Tikhonov, Max Ryabinin
It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning. ACL/IJCNLP (Findings) (2021)
Max Ryabinin, Sergei Popov, Liudmila Prokhorenkova, Elena Voita
Embedding Words in Non-Vector Space with Unsupervised Graph Learning. CoRR (2020)
Max Ryabinin, Anton Gusev
Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts. NeurIPS (2020)
Max Ryabinin, Sergei Popov, Liudmila Prokhorenkova, Elena Voita
Embedding Words in Non-Vector Space with Unsupervised Graph Learning. EMNLP (1) (2020)