Jovita Lukasik

7 papers · 2022–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird ❓ The Questioner

Venues

ICLR (3) ICML (2) AutoML (1) ECCV (1)

Top co-authors

Margret Keuper (5) Steffen Jung (3) Roman Neruda (2) Martin Pilát (2) Frank Hutter (2) Gabriela Kadlecová (2) Jan Philipp Schneider (1) Robert Geirhos (1) Paul Gavrikov (1) Julien Niklas Siems (1)

Research topics

Artificial Intelligence (4) Machine Learning (4) Deep Learning (3) Core AI (3) Application Areas (2) Architectures (2) Optimization & Theory (2) Computer Vision (1) Analysis (1) Core Methods (1) Learning Paradigms (1) Processing (1) Techniques (1)

Keywords

surrogate model (2) neural architecture search (2) transfer learning (1) hyperparameter optimization (1) interpretability (1) implicit representation (1) efficient computing (1) adversarial attack (1) adversarial corruption (1) vision-language model (1) computational cost (1) multimodal fusion (1) geometric constraint (1) search space (1) performance prediction (1) fine tuning (1) visual cue (1) jacobian matrix (1) language prompting (1) model steering (1)

Papers

Can We Talk Models Into Seeing the World Differently? ICLR 2025 Transferrable Surrogates in Expressive Neural Architecture Search Spaces AutoML 2025 Implicit Representations for Constrained Image Segmentation ICML 2024 Surprisingly Strong Performance Prediction with Neural Graph Features ICML 2024 Neural Architecture Design and Robustness: A Dataset ICLR 2023 Learning Where to Look – Generative NAS Is Surprisingly Efficient ECCV 2022 Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks ICLR 2022