collaborators

12 papers

cs.AI2026

Self-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QA

Ekaterina Alimaskina, Denis Shveykin, Gleb Molodtsov +3

Language models are increasingly taught from synthetic question--answer (QA) supervision: a model generates questions about a document, answers them from the same text, and the res…

cs.LG2026

Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning

Dmitriy Bystrov, Daniil Medyakov, Dmitry Bylinkin +1

Fine-tuning large language models (LLMs) has become a central application of modern optimization, enabling pretrained models to adapt to diverse downstream tasks and domain-specifi…

cs.LG2026

LionMuon: Alternating Spectral and Sign Descent for Efficient Training

Arman Bolatov, Artem Riabinin, Nikita Kornilov +6

In large-scale optimization, the cheapness and effectiveness of update steps are the most crucial factors for a successful optimizer. Sign-based optimizers like Lion or Signum prod…

cs.LG2026

Analyzing Stream Collapse in Hyper-Connections: From Diagnosis to Mitigation

Ekaterina Alimaskina, Gleb Molodtsov, Aleksandr Beznosikov

Hyper-Connections (HC) replace the single Transformer residual stream with multiple streams, introducing a permutation symmetry over stream indices. We study how this symmetry is r…

cs.LG2026

Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression

Artur Zagitov, Alexander Miasnikov, Maxim Krutikov +5

Post-training compression is essential for deploying large language models (LLMs) under tight resource constraints. Tensor decompositions have emerged as a promising direction, off…

cs.AI2026

Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery

Ekaterina Alimaskina, Darya Rudas, Denis Shveykin +3

Large Reasoning Models (LRMs) rely on long reasoning traces, making inference expensive. While low-bit quantization reduces per-token decoding cost, we show that aggressive 2-bit i…