Lattice AI Research

Research focus

Eval Frameworks & Benchmarks (2)Natural Language Processing (2)Recommendation & Information Retrieval (1)Data Curation & Synthetic Data (1)

Frequent co-authors

Marek Šuppa (1)Andrej Ridzik (1)Andrej Ridzik (1)D. Hládek (1)

Papers (2)

Jun 11, 2026

Marek Šuppa +94d ago

SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation

Large multilingual models outperform Slovak-specific embeddings, but new compact models offer a local deployment solution without sacrificing performance.

Marek Šuppa, Marek vSuppa, Andrej Ridzik +7

Eval Frameworks & Benchmarks Natural Language Processing Recommendation & Information Retrieval

Apr 14, 2026

UWApr 14, 2026·also Alpinference, Ben-Gurion University of the Negev

Universal NER v2: Towards a Massively Multilingual Named Entity Recognition Benchmark

Massively multilingual NER just got easier: UNER v2 offers a standardized benchmark for evaluating LLMs across diverse languages.

Terra Blevins, Stephen Mayhew, Marek vSuppa +11

Data Curation & Synthetic Data Eval Frameworks & Benchmarks Natural Language Processing

Search

Marek vSuppa

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)