Ivan Ilin

12 papers A* 2Journal 8Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
MMAI Gym for Science: Training Liquid Foundation Models for Drug Discovery.
CoRR
Maksim Kuznetsov, Zulfat Miftahutdinov, Rim Shayakhmetov, Mikolaj Mizera, Roman Schutski, Bogdan Zagribelnyy, Ivan Ilin, Nikita Bondarev, Thomas MacDougall, Mathieu Reymond, Mihir Bafna, Kaeli Kaymak-Loveless, Eugene Babin, Maxim Malkov, Mathias Lechner, Ramin M. Hasani, Alexander Amini, Vladimir Aladinskiy, Alex Aliper, Alex Zhavoronkov
2026 J jnl
When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs.
CoRR
Bogdan Zagribelnyy, Ivan Ilin, Maksim Kuznetsov, Nikita Bondarev, Roman Schutski, Thomas MacDougall, Rim Shayakhmetov, Zulfat Miftakhutdinov, Mikolaj Mizera, Vladimir Aladinskiy, Alex Aliper, Alex Zhavoronkov
2025 — conf
HIGGS: Pushing the Limits of Large Language Model Quantization via the Linearity Theorem.
NAACL (Long Papers)
Vladimir Malinovskii, Andrei Panferov, Ivan Ilin, Han Guo, Peter Richtárik, Dan Alistarh
2025 J jnl
Hessian of Perplexity for Large Language Models by PyTorch autograd (Open Source).
CoRR
Ivan Ilin
2025 J jnl
Thanos: A Block-wise Pruning Algorithm for Efficient Large Language Model Compression.
CoRR
Ivan Ilin, Peter Richtárik
2024 A* conf
PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression.
NeurIPS
Vladimir Malinovskii, Denis Mazur, Ivan Ilin, Denis Kuznedelev, Konstantin Burlachenko, Kai Yi, Dan Alistarh, Peter Richtárik
2024 J jnl
PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression.
CoRR
Vladimir Malinovskii, Denis Mazur, Ivan Ilin, Denis Kuznedelev, Konstantin Burlachenko, Kai Yi, Dan Alistarh, Peter Richtárik
2024 J jnl
Pushing the Limits of Large Language Model Quantization via the Linearity Theorem.
CoRR
Vladimir Malinovskii, Andrei Panferov, Ivan Ilin, Han Guo, Peter Richtárik, Dan Alistarh
2024 A* conf
Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity.
NeurIPS
Alexander Tyurin, Marta Pozzi, Ivan Ilin, Peter Richtárik
2024 J jnl
Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity.
CoRR
Alexander Tyurin, Marta Pozzi, Ivan Ilin, Peter Richtárik
2023 — conf
Kimad: Adaptive Gradient Compression with Bandwidth Awareness.
DistributedML@CoNEXT
Jihao Xin, Ivan Ilin, Shunkang Zhang, Marco Canini, Peter Richtárik
2023 J jnl
Kimad: Adaptive Gradient Compression with Bandwidth Awareness.
CoRR
Jihao Xin, Ivan Ilin, Shunkang Zhang, Marco Canini, Peter Richtárik