Ivan Oseledets

Feature Drift: How Fine-Tuning Repurposes Representations in LLMs EACL 2026 I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders AAAI 2026 One Task Vector is not Enough: A Large-Scale Study for In-Context Learning ACL 2026 MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding WACV 2026 Confidence Leaps in LLM Reasoning: Early Stopping and Cross-Model Transfer EACL 2026 AI Diagnostic Assistant (AIDA): A Predictive Model for Diagnoses from Health Records in Clinical Decision Support Systems IJCAI 2025 Associative memory and dead neurons ICLR 2025 Certification of Speaker Recognition Models to Additive Perturbations AAAI 2025 Run LoRA Run: Faster and Lighter LoRA Implementations ACL 2025 CLEAR: Character Unlearning in Textual and Visual Modalities ACL 2025 Exploring the Hidden Capacity of LLMs for One-Step Text Generation EMNLP 2025 CLARITY: Clinical Assistant for Routing, Inference, and Triage EMNLP 2025 LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers NAACL 2025 Anatomical Positional Embeddings MICCAI 2024 Probabilistically Robust Watermarking of Neural Networks IJCAI 2024 The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models EACL 2024 Quantization of Large Language Models with an Overdetermined Basis UAI 2024 SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layers EMNLP 2024 Neural operators meet conjugate gradients: The FCG-NO method for efficient PDE solving ICML 2024 Your Transformer is Secretly Linear ACL 2024 Layerwise universal adversarial attack on NLP models ACL 2023 Neural Harmonics: Bridging Spectral Embedding and Matrix Completion in Self-Supervised Learning NIPS 2023 Constructive TT-representation of the tensors given as index interaction functions with applications ICLR 2023 Few-bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction ICML 2023 Understanding DDPM Latent Codes Through Optimal Transport ICLR 2023 PROTES: Probabilistic Optimization with Tensor Sampling NIPS 2023 General Covariance Data Augmentation for Neural PDE Solvers ICML 2023 Smoothed Embeddings for Certified Few-Shot Learning NIPS 2022 TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learning NIPS 2022 CC-CERT: A Probabilistic Approach to Certify General Robustness of Neural Networks AAAI 2022 Hyperbolic Vision Transformers: Combining Improvements in Metric Learning CVPR 2022 Geometry-Inspired Top-K Adversarial Perturbations WACV 2022 Survey on Efficient Training of Large Neural Networks IJCAI 2022 Adversarial Turing Patterns from Cellular Automata AAAI 2021 Latent Transformations via NeuralODEs for GAN-Based Image Editing ICCV 2021 Functional Space Analysis of Local GAN Convergence ICML 2021 Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs NIPS 2020 The Shape of Data: Intrinsic Distance for Data Distributions ICLR 2020 Tensor Train Decomposition on TensorFlow (T3F) JMLR 2020 Tensorized Embedding Layers EMNLP 2020 Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network ECCV 2020 Hyperbolic Image Embeddings CVPR 2020 PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach ICML 2019 Generalized Tensor Models for Recurrent Neural Networks ICLR 2019 Geometry Score: A Method For Comparing Generative Adversarial Networks ICML 2018 Art of Singular Vectors and Universal Adversarial Perturbations CVPR 2018 Expressive power of recurrent neural networks ICLR 2018 Quadrature-based features for kernel approximation NIPS 2018 Riemannian Optimization for Skip-Gram Negative Sampling ACL 2017