Mykola Pechenizkiy

Affiliations

TU Eindhoven

papers

496

total citations

papers (14)

Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity

ICML 2024arXiv

152

citations

Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective

AAAI 2025arXiv

citations

Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach

NEURIPS 2023arXiv

citations

Dynamic Sparsity Is Channel-Level Sparsity Learner

NEURIPS 2023arXiv

citations

Where to Pay Attention in Sparse Training for Feature Selection?

NEURIPS 2022arXiv

citations

Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning

ICLR 2024arXiv

citations

Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness

ICLR 2025arXiv

citations

HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents

ICLR 2025arXiv

citations

REOBench: Benchmarking Robustness of Earth Observation Foundation Models

NEURIPS 2025arXiv

citations

Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling

ICML 2024arXiv

citations

COOM: A Game Benchmark for Continual Reinforcement Learning

NEURIPS 2023

citations

Mykola Pechenizkiy

Affiliations

papers (14)

Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity

Sparse Training via Boosting Pruning Plasticity with Neuroregeneration

Large Language Models Are Neurosymbolic Reasoners

Dynamic Sparse Network for Time Series Classification: Learning What to “See”

Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective

Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach

Dynamic Sparsity Is Channel-Level Sparsity Learner

Where to Pay Attention in Sparse Training for Feature Selection?

Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning

Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness

HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents

REOBench: Benchmarking Robustness of Earth Observation Foundation Models

Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling

COOM: A Game Benchmark for Continual Reinforcement Learning

papers (14)

Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity

Sparse Training via Boosting Pruning Plasticity with Neuroregeneration

Large Language Models Are Neurosymbolic Reasoners

Dynamic Sparse Network for Time Series Classification: Learning What to “See”

Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective

Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach

Dynamic Sparsity Is Channel-Level Sparsity Learner

Where to Pay Attention in Sparse Training for Feature Selection?

Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning

Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness

HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents

REOBench: Benchmarking Robustness of Earth Observation Foundation Models

Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling

COOM: A Game Benchmark for Continual Reinforcement Learning