Maksim Velikanov

19 papers A* 4A 2Journal 13

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers. CoRR Maksim Velikanov, Ilyas Chahed, Jingwei Zuo, Dhia Eddine Rhaiem, Younes Belkada, Hakim Hacid
2025	J	`jnl`	Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance. CoRR Jingwei Zuo, Maksim Velikanov, Ilyas Chahed, Younes Belkada, Dhia Eddine Rhayem, Guillaume Kunsch, Hakim Hacid, Hamza Yous, Brahim Farhat, Ibrahim Khadraoui, Mugariya Farooq, Giulia Campesan, Ruxandra Cojocaru, Yasser Dahou, Shi Hu, Iheb Chaabane, Puneesh Khanna, Mohamed El Amine Seddik, Ngoc Dung Huynh, Phuc H. Le-Khac, Leen Al Qadi, Billel Mokeddem, Mohamed Chami, Abdalgader Abubaker, Mikhail Lubinets, Kacper Piskorski, Slim Frikha
2025	A*	`conf`	SGD with memory: fundamental properties and stochastic acceleration. ICLR Dmitry Yarotsky, Maksim Velikanov
2024	A	`conf`	Efficient Conformal Prediction under Data Heterogeneity. AISTATS Vincent Plassier, Nikita Kotelevskii, Aleksandr Rubashevskii, Fedor Noskov, Maksim Velikanov, Alexander Fishkov, Samuel Horváth, Martin Takác, Eric Moulines, Maxim Panov
2024	J	`jnl`	Falcon Mamba: The First Competitive Attention-free 7B Language Model. CoRR Jingwei Zuo, Maksim Velikanov, Dhia Eddine Rhaiem, Ilyas Chahed, Younes Belkada, Guillaume Kunsch, Hakim Hacid
2024	J	`jnl`	Falcon2-11B Technical Report. CoRR Quentin Malartic, Nilabhra Roy Chowdhury, Ruxandra Cojocaru, Mugariya Farooq, Giulia Campesan, Yasser Abdelaziz Dahou Djilali, Sanath Narayan, Ankit Singh, Maksim Velikanov, Basma El Amel Boussaha, Mohammed Al-Yafeai, Hamza Alobeidli, Leen Al Qadi, Mohamed El Amine Seddik, Kirill Fedyanin, Réda Alami, Hakim Hacid
2024	A*	`conf`	Generalization error of spectral algorithms. ICLR Maksim Velikanov, Maxim Panov, Dmitry Yarotsky
2024	J	`jnl`	Generalization error of spectral algorithms. CoRR Maksim Velikanov, Maxim Panov, Dmitry Yarotsky
2024	J	`jnl`	SGD with memory: fundamental properties and stochastic acceleration. CoRR Dmitry Yarotsky, Maksim Velikanov
2024	J	`jnl`	Tight Convergence Rate Bounds for Optimization Under Power Law Spectral Conditions. J. Mach. Learn. Res. Maksim Velikanov, Dmitry Yarotsky
2023	A*	`conf`	A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta. ICLR Maksim Velikanov, Denis Kuznedelev, Dmitry Yarotsky
2023	J	`jnl`	Comparing the robustness of modern no-reference image- and video-quality metrics to adversarial attacks. CoRR Anastasia Antsiferova, Khaled Abud, Aleksandr Gushchin, Sergey Lavrushkin, Ekaterina Shumitskaya, Maksim Velikanov, Dmitriy S. Vatolin
2023	J	`jnl`	Efficient Conformal Prediction under Data Heterogeneity. CoRR Vincent Plassier, Nikita Kotelevskii, Aleksandr Rubashevskii, Fedor Noskov, Maksim Velikanov, Alexander Fishkov, Samuel Horváth, Martin Takác, Eric Moulines, Maxim Panov
2022	J	`jnl`	A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta. CoRR Maksim Velikanov, Denis Kuznedelev, Dmitry Yarotsky
2022	J	`jnl`	Embedded Ensembles: Infinite Width Limit and Operating Regimes. CoRR Maksim Velikanov, Roman Kail, Ivan Anokhin, Roman Vashurin, Maxim Panov, Alexey Zaytsev, Dmitry Yarotsky
2022	A	`conf`	Embedded Ensembles: infinite width limit and operating regimes. AISTATS Maksim Velikanov, Roman V. Kail, Ivan Anokhin, Roman Vashurin, Maxim Panov, Alexey Zaytsev, Dmitry Yarotsky
2022	J	`jnl`	Tight Convergence Rate Bounds for Optimization Under Power Law Spectral Conditions. CoRR Maksim Velikanov, Dmitry Yarotsky
2021	A*	`conf`	Explicit loss asymptotics in the gradient descent training of neural networks. NeurIPS Maksim Velikanov, Dmitry Yarotsky
2021	J	`jnl`	Universal scaling laws in the gradient descent training of neural networks. CoRR Maksim Velikanov, Dmitry Yarotsky