Ivan Oseledets
- Papers
- 16
Cite
Notes
Only stored in your browser.
Authored papers
16GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms
arXiv 2025
Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts
arXiv 2025
Exploring the Latent Capacity of LLMs for One-Step Text Generation
arXiv 2025
Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models
arXiv 2025
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
arXiv 2025
CLEAR: Character Unlearning in Textual and Visual Modalities
arXiv 2024
OmniFusion Technical Report
arXiv 2024
ConDiff: A Challenging Dataset for Neural Solvers of Partial Differential Equations
arXiv 2024
Certification of Speaker Recognition Models to Additive Perturbations
arXiv 2024
SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layers
arXiv 2024
Your Transformer is Secretly Linear
arXiv 2024
Translate your gibberish: black-box adversarial attack on machine translation systems
arXiv 2023
General Covariance Data Augmentation for Neural PDE Solvers
arXiv 2023
Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction
arXiv 2022
Memory-Efficient Backpropagation through Large Linear Layers
arXiv 2022
NAG-GS: Semi-Implicit, Accelerated and Robust Stochastic Optimizer
arXiv 2022
Affiliations
Frequent co-authors
10from 16 papers
Oleg Y. Rogov
Andrey Kuznetsov
Anton Razzhigaev
Daniel Bershatsky
Denis Dimitrov
Dmitrii Korzh
Elena Tutubalina
Alexander Panchenko
Alexander Rudikov
Alexey Dontsov