Mikołaj Małkiński

4 papers · 2024–2025 · 3 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 (11) 🏆 Keyword Champion (3)

Venues

IJCAI (2) AAAI (1) ICML (1)

Top co-authors

Jacek Mańdziuk (4) Szymon Pawlonka (1)

Research topics

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

Keywords

abstract visual reasoning (3) raven's progressive matrice (3) visual reasoning (2) transfer learning (2) out-of-distribution generalization (1) neural architecture (1) multimodal large language model (1) progressive matrice (1) generalization assessment (1) abstract reasoning (1) group convolution (1) real-world image (1) neural network (1) self-configurable model (1) bongard problem (1) shared concepts (1) benchmark evaluation (1) synthetic bps (1) multi-task learning (1) scene understanding (1)

Papers

Advancing Generalization Across a Variety of Abstract Visual Reasoning Tasks IJCAI 2025 A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoning IJCAI 2025 Reasoning Limitations of Multimodal Large Language Models. A case study of Bongard Problems ICML 2025 One Self-Configurable Model to Solve Many Abstract Visual Reasoning Problems AAAI 2024