12 papers
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…
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…
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…
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…
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…
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…