• Sky Chenwei Wan, Yifei Y. WANG, Tianjun Hou, Xiqing Chang, Aymeric Jan: “Grammar of the Wave: Towards Explainable Multivariate Time Series Event Detection via Neuro-Symbolic VLM Agents”

• Tianjun Hou, Xiqing Chang, Sky Chenwei Wan: “Language Guided Time-Series Event Detection with Zero-Shot Cross-Modal Grounding”

• Fabian M. Suchanek, Thomas Bonald, Nikola Dobričić, Marc Jeanmougin, Margherita Necchi: “YAGO 4.6: A Logically Consistent Subset of Wikidata”

• Pierre-Henri Paris, François Amat, Paolo Papotti, Fabian M. Suchanek: “MARITA: Mining Approximate Rules in Tables”

Our researchers investigate this question in a paper accepted at the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026):

• “From Disclosure to Evaluability: an NLP-Based Analysis of Corporate Transition Plans”

Tom Calamai, Oana Bălălău, Théo Le Guenedal, and Fabian M. Suchanek

• “Two-dimensional Taxonomy for N-ary Knowledge Representation Learning Methods”

Xiaohua Lu, Liubov Tupikina, and Mehwish Alam

• “LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptation”, accepted at ISWC 2026.

Samy Haffoudhi, Fabian M. Suchanek, and Nils Holzenberger

• “A Benchmark for Hierarchical Link Prediction”, accepted at ISWC 2026.

Lukas Ketzer, Franziska Kuch, Tim Schwabe, Mehwish Alam, and Maribel Acosta

• “WiCleanData: Guaranteeing the Type Consistency of Wikidata by Taxonomy Refinement and Constraint Enforcement”

Yiwen Peng, Thomas Bonald and Marc Jeanmougin

• “How Benchmarks and Evaluation Protocols Shape Conclusions in Provenance-Based Intrusion Detection”. Lorenzo Guerra, Thomas Chapuis, Guillaume Duc, Pavlo Mozharovskyi, and Van-Tam Nguyen

The paper examines how benchmark datasets and evaluation protocols shape the conclusions drawn about provenance-based intrusion detection systems. It also highlights how the limitations of currently available data affect progress in the field and discusses how future datasets could better support the development and evaluation of new approaches.

• “DELICATE: Diachronic Entity Linking using Classes and Temporal Evidence”, accepted in the ACM Journal on Computing and Cultural Heritage. Cristian Santini, Sebastian Barzaghi, Paolo Sernani, Emanuele Frontoni, and Mehwish Alam

• “Analysing Lightweight Large Language Models for Biomedical Named Entity Recognition on Diverse Output Formats”, accepted at LREC 2026. Pierre Epron, Adrien Coulet, and Mehwish Alam

• “ENEIDE: A High Quality Silver Standard Dataset for Named Entity Recognition and Linking in Historical Italian”, accepted at LREC 2026. Cristian Santini, Emanuele Frontini, Sebastian Barzaghi, Laura Melosi, and Mehwish Alam

Come visit us again!

Thank you for coming by, Julia!