IO
Ivan Oseledets
cs.LGcs.NAmath.NAcs.AIcs.CVstat.MLcs.CLmath.OCcs.IRcs.NE
On Valency
published · living versionsW_suhpf5n3·v1 · currentpublished
TensorSpectra: Bridging the Spectral and Tensor Worlds for High-Dimensional PDEs
with Bingcheng Hu, Tianchi Yu, Zhaoxiang Li
1 version
W_5yem3vg9·v1published
W_5khfgb7z·v1published
Preprints & journals
249 papers in the corpus · 2010–2026From Stories to Features: Scaling Concept Vectors for AI Alignment & Interpretability2610.24556v1 · Dmitry Scherbakov, Oleg Chernikov, Victoria Khamash et al.2026 · 0 citationsarXivon Valency
AI Consilium: a Benchmark of LLM Clinical Multidisciplinary Second Opinions2610.22298v1 · Alexey A. Bokov, Ivan I. Panin, Nikolay B. Nechaev et al.2026 · 0 citationsarXiv
What Limits Recursive Reasoning Models: Optimization, Architecture and Test-Time Scaling2609.39967v1 · Yuliana Shakhvalieva, Dmitrii Kharchev, Viacheslav Bezrukov et al.2026 · 0 citationsarXiv
Reasoning on the Simplex: Geometric Fixed-Point Models2609.33540v1 · Talgat Daulbaev, Ilya Glazkov, Maxim Rakhuba et al.2026 · 0 citationsarXiv
LANTERN: Illuminating Hidden Mathematical Knowledge in Language Models2609.32264v1 · Pavel Tikhonov, Elena Tutubalina, Ivan Oseledets et al.2026 · 0 citationsarXiv
Change the Product, Keep the Parameters: Associative Algebra Layers for Transformers2609.32814v1 · Ilya Koziev, Ivan Oseledets2026 · 0 citationsarXiv
Evaluating Losslessness in Speculative Decoding Under Finite-Precision Inference2609.15504v2 · Ilya Koziev, Leonid Sinev, Ivan Oseledets2026 · 0 citationsarXiv
Structured Transforms for Low-Overhead Quantization of Language Models2609.11687v1 · Daria Cherniuk, Alexander Rudikov, Boris Kashin et al.2026 · 0 citationsarXiv
EvoMem: Memory-Augmented Evolution for Code Optimization2608.10795v1 · Viktor Volkov, Valentin Khrulkov, Andrey V. Galichin et al.2026 · 0 citationsarXiv
Exploring specialization and sensitivity of convolutional neural networks under simultaneous image augmentations.42914941 · Kharyuk, Pavel, Matveev, Sergey, Oseledets, Ivan2026 · 1 citationNeural networks : the official journal of the International Neural Network Society. 2026;206(Pt A):109502
Spectral-Informed Neural Networks Outperform Spectral Methods in High-dimensional PDEs2607.13566v1 · Tianchi Yu, Ivan Oseledets2026 · 0 citationsarXiv
Search, Fail, Recover: A Training Framework for Correction-Aware Reasoning2607.07492v1 · Dmitry Beresnev, Vladimir Makharev, Roman Khalikov et al.2026 · 0 citationsarXiv
TheoremBench: Evaluating LLMs on Theorem Proving in Formal Mathematics2606.09450v1 · QuocViet Pham, Elvir Karimov, Andrey Galichin et al.2026 · 0 citationsarXiv
OCC-RAG: Optimal Cognitive Core for Faithful Question Answering2606.00683v1 · Maksim Savkin, Mikhail Goncharov, Alexander Gambashidze et al.2026 · 0 citationsarXiv
Harnessing non-adversarial robustness in large language models2605.29816v1 · Qinghua Zhou, Ellina Aleshina, Andrey Lovyagin et al.2026 · 0 citationsarXiv
TUBE: Tangent Upper Bound on Evidence for Discrete Diffusion Language Models2605.24292v1 · Arseny Ivanov, Sergei Kholkin, Vladislav Gromadskii et al.2026 · 0 citationsarXiv
Sinc Kolmogorov-Arnold network and its application for solving PDEs with singularities.42061189 · Yu, Tianchi, Qiu, Jingwei, Yang, Jiang et al.2026 · 6 citationsNeural networks : the official journal of the International Neural Network Society. 2026;202:109033
OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models2604.05183v1 · Ali Aliev, Kamil Garifullin, Nikolay Yudin et al.2026 · 0 citationsarXiv
LLM-Guided Evolutionary Search for Algebraic T-Count Optimization2603.29894v2 · Daniil Fisher, Valentin Khrulkov, Mikhail Saygin et al.2026 · 0 citationsarXiv
Marchuk: Efficient Global Weather Forecasting from Mid-Range to Sub-Seasonal Scales via Flow Matching2603.24428v1 · Arsen Kuzhamuratov, Mikhail Zhirnov, Andrey Kuznetsov et al.2026 · 0 citationsarXiv
IDLM: Inverse-distilled Diffusion Language Models2602.19066v2 · David Li, Nikita Gushchin, Dmitry Abulkhanov et al.2026 · 0 citationsarXiv
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?2602.14111v1 · Anton Korznikov, Andrey Galichin, Alexey Dontsov et al.2026 · 0 citationsarXiv
ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search2602.10233v2 · Alexey Kravatskiy, Valentin Khrulkov, Ivan Oseledets2026 · 0 citationsarXiv
Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities2602.05281v2 · Pengyi Li, Elizaveta Goncharova, Andrey Kuznetsov et al.2026 · 0 citationsarXiv
Global Optimization of Atomic Clusters via Physically-Constrained Tensor Train Decomposition2601.18592v1 · Konstantin Sozykin, Nikita Rybin, Andrei Chertkov et al.2026 · 0 citationsarXiv
Quantum annealing for inverse kinematics in robotics.41476188 · Salloum, Hadi, Savin, Sergei, Kholodov, Yaroslav et al.2026 · 2 citationsScientific reports. 2025;16(1):4244
Bento: Benchmarking Classical and AI Docking on Drug Design-Relevant Data10.64898/2025.12.30.696741v1 · Pak, M. A., Frolova, D., Nikolenko, S. A. et al.2025 · 1 citationbioRxiv
Ky Fan Norms and Beyond: Dual Norms and Combinations for Matrix Optimization2512.09678v2 · Alexey Kravatskiy, Ivan Kozyrev, Nikolai Kozlov et al.2025 · 0 citationsarXiv
Multi-Agent GraphRAG: A Text-to-Cypher Framework for Labeled Property Graphs2511.08274v1 · Anton Gusarov, Anastasia Volkova, Valentin Khrulkov et al.2025 · 0 citationsarXiv
FMMI: Flow Matching Mutual Information Estimation2511.08552v2 · Ivan Butakov, Alexander Semenenko, Valeriya Kirova et al.2025 · 0 citationsarXiv
T-MLA: A targeted multiscale log-exponential attack framework for neural image compression2511.01079v2 · Nikolay I. Kalmykov, Razan Dibo, Kaiyu Shen et al.2025 · 0 citationsInformation Sciences 738 (2026) 123143
CLARITY: Clinical Assistant for Routing, Inference, and Triage2510.02463v2 · Vladimir Shaposhnikov, Aleksandr Nesterov, Ilia Kopanichuk et al.2025 · 1 citationarXiv
Deep Learning for Subspace Regression2509.23249v4 · Vladimir Fanaskov, Vladislav Trifonov, Alexander Rudikov et al.2025 · 0 citationsarXiv
Low-rank surrogate modeling and stochastic zero-order optimization for training of neural networks with black-box layers2509.15113v2 · Andrei Chertkov, Artem Basharin, Mikhail Saygin et al.2025 · 0 citationsarXiv
Quasi-Random Physics-informed Neural Networks2507.08121v1 · Tianchi Yu, Ivan Oseledets2025 · 0 citationsarXiv
Listener-Rewarded Thinking in VLMs for Image Preferences2506.22832v3 · Alexander Gambashidze, Li Pengyi, Matvey Skripkin et al.2025 · 0 citationsarXiv
Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models2506.06751v2 · Mikhail Salnikov, Dmitrii Korzh, Ivan Lazichny et al.2025 · 2 citationsarXiv
Geological Field Restoration through the Lens of Image Inpainting2506.04869v2 · Vladislav Trifonov, Ivan Oseledets, Ekaterina Muravleva2025 · 0 citationsarXiv
Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts2506.05229v1 · Danil Sivtsov, Ivan Rodkin, Gleb Kuzmin et al.2025 · 0 citationsarXiv
Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models2506.06395v3 · Pengyi Li, Matvey Skripkin, Alexander Zubrey et al.2025 · 0 citationsarXiv
Curse of Slicing: Why Sliced Mutual Information is a Deceptive Measure of Statistical Dependence2506.04053v3 · Alexander Semenenko, Ivan Butakov, Alexey Frolov et al.2025 · 0 citationsarXiv
One Task Vector is not Enough: A Large-Scale Study for In-Context Learning2505.23911v1 · Pavel Tikhonov, Ivan Oseledets, Elena Tutubalina2025 · 0 citationsarXiv
Exploring the Hidden Capacity of LLMs for One-Step Text Generation2505.21189v2 · Gleb Mezentsev, Ivan Oseledets2025 · 0 citationsarXiv
Locally Subspace-Informed Neural Operators for Efficient Multiscale PDE Solving2505.16030v2 · Alexander Rudikov, Vladimir Fanaskov, Sergei Stepanov et al.2025 · 0 citationsarXiv
MULAN: multimodal protein language model for sequence and structure encoding.40989496 · Frolova, Daria, Pak, Marina, Litvin, Anna et al.2025 · 12 citationsBioinformatics advances. 2025;5(1):vbaf117
High-dimensional Optimization with Low Rank Tensor Sampling and Local Search2505.12383v1 · Konstantin Sozykin, Andrei Chertkov, Anh-Huy Phan et al.2025 · 0 citationsarXiv
Binding threshold units with artificial oscillatory neurons2505.03648v1 · Vladimir Fanaskov, Ivan Oseledets2025 · 0 citationsarXiv
On the Spatial Structure of Mixture-of-Experts in Transformers2504.04444v1 · Daniel Bershatsky, Ivan Oseledets2025 · 0 citationsarXiv
Test-Time Reasoning Through Visual Human Preferences with VLMs and Soft Rewards2503.19948v2 · Alexander Gambashidze, Konstantin Sobolev, Andrey Kuznetsov et al.2025 · 0 citationsarXiv
Bayesian Inverse Problems Meet Flow Matching: Efficient and Flexible Inference via Transformers2503.01375v2 · Daniil Sherki, Ivan Oseledets, Ekaterina Muravleva2025 · 1 citationarXiv
Career total: 429 works. 249 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.