neuralnoise.com

Selected Research Grants

Beyond the Airlock: TRANspect, Securing AI Transformer Models for Free-Text Safe Release in TREs. Medical Research Council, April 2026–March 2027. Co-Investigator (PI: Arlene Casey). [DARE UK project page]
Answering Complex Questions at Scale. Edinburgh-Huawei Joint Laboratory, September 2024–September 2027. Principal Investigator.
Gradient-based Learning of Complex Latent Structures. Edinburgh Laboratory for Integrated Artificial Intelligence (ELIAI), January 2023–January 2025. Principal Investigator, with Antonio Vergari and Edoardo Ponti.
CLARIFY: Cancer Long Survivors Artificial Intelligence Follow Up. European Commission Horizon 2020, January 2020–December 2022. Co-Principal Investigator at UCL.

Patents

Minervini, Costabello, Muñoz, Nováček, Vandenbussche - Method and Apparatus for Completing a Knowledge Graph. United States Patent: US11341417B2, Japan Patent: JP6954049B2, Current Assignee: Fujitsu Ltd.

Tutorials

Lecue, Giannotti, Guidotti, Minervini - On Explainable AI: From Theory to Motivation, Industrial Applications, XAI Coding & Engineering Practices. Tutorial for the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023)
Lecue, Giannotti, Guidotti, Minervini - On Explainable AI: From Theory to Motivation, Industrial Applications, XAI Coding & Engineering Practices. Tutorial for the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022)
Lecue, Minervini, Giannotti, Guidotti - On Explainable AI: From Theory to Motivation, Industrial Applications and Coding Practices. Tutorial for the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021)
Lecue, Gade, Geyik, Kenthapadi, Mithal, Taly, Guidotti, Minervini - On Explainable AI: Foundations, Industrial Applications, Practical Challenges, and Lessons Learned. Tutorial for the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020)
Costabello, Lecue, Giannotti, Guidotti, Hitzler, Minervini, Sarker - On Explainable AI: From Theory to Motivation, Applications and Limitations. Half-day (3.5 hours) Tutorial for the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI 2019)
Guidotti, Minervini, Monreale, Rinzivillo - Tutorial on Explainable Knowledge Discovery in Data Mining. Tutorial for the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2019)
Riedel, Minervini - Differentiable Program Interpreters. Lecture at the Summer School on Statistical Relational Artificial Intelligence (ACAI 2018)

A more up-to-date and exhaustive list of my publications is available on my Google Scholar page.

Publications

Saxena, Suglia, Minervini - VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Models. International Conference on Machine Learning (ICML 2026) [bibtex]
Zhao, Chen, Inan, Kessler, Wang, Wutschitz, Yang, Zhang, Minervini, Rajmohan, Sim - Learning GUI Grounding with Spatial Reasoning from Visual Feedback. International Conference on Machine Learning (ICML 2026) [bibtex]
Grivas, Loconte, van Krieken, Nawrot, Zhao, Wielewski, Minervini, Ponti, Vergari - Fast and Expressive Multi-Token Prediction with Probabilistic Circuits. International Conference on Machine Learning (ICML 2026) [bibtex]
Leang, Zhao, Gema, Yang, Kwan, He, Li, Minervini, Giunchiglia, Cohen - PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains. 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026, Findings) [bibtex]
Du, Hong, Kwan, Saxena, Titov, Minervini, Allaway - Analyzing LLM Instruction Optimization for Tabular Fact Verification. Findings of the Association for Computational Linguistics: EACL 2026 [bibtex]
Gema, Hägele, Chen, Arditi, Goldman-Wetzler, Fraser-Taliente, Sleight, Petrini, Michael, Alex, Minervini, Chen, Benton, Perez - Inverse Scaling in Test-Time Compute. Transactions on Machine Learning Research (TMLR 2026) [bibtex]
Dileo, Minervini, Zignani, Gaito - Tensor Factorization for Temporal Knowledge Graph Forecasting. Neurocomputing 674 (2026) [bibtex]
Zignani, Minervini, Interdonato, Dileo - Learning and Reasoning on Knowledge and Heterogeneous Graphs in the era of Graph Foundation and Large Language Models. ESANN 2026 [bibtex]
Sundrani, Tudisco, Minervini - Low-Rank Compression of Language Models via Differentiable Rank Selection. Language Resources and Evaluation Conference (LREC 2026) [bibtex]
Gema, Alex, Minervini - Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads. Mechanistic Interpretability Workshop (Mech Interp @ ICML 2026, virtual poster) [bibtex]
Kaddour, Patel, Dovonon, Richter, Minervini, Kusner - Agentic Uncertainty Reveals Agentic Overconfidence. Post-AGI Science and Society Workshop (P-AGI @ ICLR 2026) [bibtex]
Kwan, Gema, Leang, Minervini - SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks. CoRR abs/2605.31433 (2026) [bibtex]
Li, Wang, Zhao, Du, Li, Ren, Wong, See, Luo, Duan, Minervini, Song - Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models. CoRR abs/2605.27243 (2026) [bibtex]
Attimonelli, De Bellis, Gema, Saxena, Sekoyan, Kwan, Pomo, Suglia, Jannach, Di Noia, Minervini - Do Composed Image Retrieval Benchmarks Require Multimodal Composition?. CoRR abs/2605.14787 (2026) [bibtex]
Sayin, Vo Hong, Baris Schlicht, Staiano, Minervini, Allievi, Susca, Osti, Maino, Racanelli, Passerini - Human-LLM Dialogue Improves Diagnostic Accuracy in Emergency Care. CoRR abs/2605.08533 (2026) [bibtex]
Miller-Golub, Coil, Faber, Pietron, Zheng, Minervini, Corizzo - Rethinking the Harmonic Loss via Non-Euclidean Distance Layers. CoRR abs/2603.10225 (2026) [bibtex]
Lee, Yates, Minervini, Simpson - Process-Supervised Multi-Agent Reinforcement Learning for Reliable Clinical Reasoning. CoRR abs/2602.14160 (2026) [bibtex]
Wani, Suglia, Saxena, Gema, Kwan, Barez, Bucarelli, Silvestri, Minervini - Same Answer, Different Representations: Hidden Instability in VLMs. CoRR abs/2602.06652 (2026) [bibtex]
Hong, van Krieken, Ponti, Malkin, Minervini - Mixtures of In-Context Learners. 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025, SAC Highlights Award) [bibtex]
He, Wang, Xu, Minervini, Stenetorp, Rubinstein, Cohn - TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning. 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025) [bibtex]
Zheng, Gema, Hong, He, Minervini, Sun, Xu - GRADA: Graph-based Reranking against Adversarial Documents Attack. The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025) [bibtex]
Arakelyan, Minervini, Verga, Lewis, Augenstein - FLARE: Faithful Logic-Aided Reasoning and Exploration. The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025) [bibtex]
Gema, Jin, Abdulaal, Diethe, Teare, Alex, Minervini, Saseendran - DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations. The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025) [bibtex]
van Krieken, Minervini, Ponti, Vergari - Neurosymbolic Diffusion Models. Thirty-Ninth Conference on Neural Information Processing Systems (NeurIPS 2025) [bibtex]
Wang, Yu, Ren, Zhang, Zhao, Saxena, Cheng, Wong, See, Minervini, Song, Steedman - MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly. Thirty-Ninth Conference on Neural Information Processing Systems (NeurIPS 2025, spotlight) [bibtex]
Richter, He, Minervini, Kusner - An Auditing Test to Detect Behavioral Shift in Language Models. 13th International Conference on Learning Representations (ICLR 2025) [bibtex]
Gregucci, Xiong, Hernández, Loconte, Minervini, Staab, Vergari - Is Complex Query Answering Really Complex?. International Conference on Machine Learning (ICML 2025) Spotlight, top 2.6% of accepted papers [bibtex]
Zhu, de Souza, Shi, Yang, Minervini, D'Amour, Kusner - When Can Proxies Improve the Sample Complexity of Preference Learning?. International Conference on Machine Learning (ICML 2025) [bibtex]
Zhao, Devoto, Hong, Du, Gema, Wang, He, Wong, Minervini – Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering. The 2025 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2025) [bibtex]
Gema, Jun Leang, Hong, Devoto, Mancino, Saxena, He, Zhao, Du, Ghasemi Madani, Barale, McHardy, Harris, Kaddour, van Krieken, Minervini - Are We Done with MMLU?. The 2025 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2025) [bibtex]
Luo, Gema, He, van Krieken, Lesci, Minervini - Self-Training Large Language Models for Tool-Use Without Demonstrations. The 2025 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2025, Findings) [bibtex]
Wójcik, Devoto, Pustelnik, Minervini, Scardapane – Adaptive Computation Modules: Granular Conditional Computation for Efficient Inference. The 39th AAAI Conference on Artificial Intelligence (AAAI 2025) [bibtex]
Ghazaryan, Arakelyan, Minervini, Augenstein – SynDARin: Synthesising Datasets for Automated Reasoning in Low-Resource Languages. The 30th International Conference on Computational Linguistics (COLING 2025) [bibtex]
Du, Saxena, Perez-Beltrachini, Minervini, Titov - Enhancing Long Document Long Form Summarisation with Self-Planning. IJCNLP-AACL 2025 [bibtex]
van Krieken, Minervini, Ponti, Vergari - Neurosymbolic Reasoning Shortcuts under the Independence Assumption. 19th International Conference on Neurosymbolic Learning and Reasoning (NeSy 2025) [bibtex]
Passerini, Gema, Minervini, Sayin, Tentori – Fostering Effective Hybrid Human-LLM Reasoning and Decision Making. Frontiers in Artificial Intelligence 7, 1464690 (2025) [bibtex]
Ghasemi Madani, Gema, Sarti, Zhao, Minervini, Passerini - Noiser: Bounded Input Perturbations for Attributing Large Language Models. Conference on Language Modeling (CoLM 2025) [bibtex]
Devoto, Alvetreti, Pomponi, Di Lorenzo, Minervini, Scardapane - Adaptive Layer and Token Selection for Efficient Fine-Tuning of Vision Transformers. Neurocomputing (2025) [bibtex]
Merra, Skracic, Malitesta, Golebiowski, Minervini - SmaLLEXT: 1st Workshop on Small and Efficient Large Language Models for Knowledge Extraction. 34th ACM International Conference on Information and Knowledge Management (CIKM 2025) [bibtex]
Dileo, Minervini, Zignani, Gaito - Enhancing neural link predictors for temporal knowledge graphs with temporal regularisers. ESANN 2025 [bibtex]
Dileo, Minervini, Zignani - Fine-Tuning Foundation Models for Temporal Knowledge Graph Reasoning. PKDD/ECML Workshops 2025 [bibtex]
Sayin, Baris Schlicht, Vo Hong, Allievi, Staiano, Minervini, Passerini - MedSyn: Enhancing Diagnostics with Human-AI Collaboration. HHAI Workshops 2025 [bibtex]
Murphy, Rizvi, Haussmann, Nie, Liu, Gema, Minervini - An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering. CoRR abs/2503.23415 (2025) [bibtex]
Godey, Devoto, Zhao, Scardapane, Minervini, de la Clergerie, Sagot - Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression. CoRR abs/2503.02812 (2025) [bibtex]
Saxena, Minervini, Keller - PosterSum: A Multimodal Benchmark for Scientific Poster Summarization. IJCNLP-AACL 2025 (Findings) [bibtex]
Saxena, Gema, Minervini - Lost in Time: Clock and Calendar Understanding Challenges in Multimodal LLMs. ICLR 2025 Workshop on Reasoning and Planning for Large Language Models [bibtex]
Arakelyan, Hambardzumyan, Papikyan, Minervini, Gordo, Augenstein, Markosyan - With Great Backbones Comes Great Adversarial Transferability. CoRR abs/2501.12275 (2025) [bibtex]
Kwan, Leang, Vougiouklis, Pan, Valentino, Minervini - OpenSIR: Open-Ended Self-Improving Reasoner. CoRR abs/2511.00602 (2025) [bibtex]
Szatkowski, Bedkowski, Devoto, Dubinski, Minervini, Piorczynski, Scardapane, Wójcik - Universal Properties of Activation Sparsity in Modern Large Language Models. CoRR abs/2509.00454 (2025) [bibtex]
Luo, Rechardt, Sun, Nejad, Yáñez, Yilmaz, Lee, Cohen, Borghesani, Pashkov, Marinazzo, Nicholas, Salatiello, Sucholutsky, Minervini, Razavi, Rocca, Yusifov, Okalova, Gu, Ferianc, Khona, Patil, Lee, Mata, Myers, Bizley, Musslick, Bilgin, Niso, Ales, Gaebler, Murty, Loued-Khenissi, Behler, Hall, Dafflon, Bao, Love - Large language models surpass human experts in predicting neuroscience results. Nature Human Behaviour (2024) [bibtex]
Devoto, Zhao, Scardapane, Minervini - A Simple and Effective $L_{2}$ Norm-Based Strategy for KV Cache Compression. The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024 Main Conference; Oral, top 9% of accepted papers) [bibtex]
Stacey, Minervini, Dubossarsky, Camburu, Rei - Atomic Inference for NLI with Generated Facts as Atoms. The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024 Main Conference) [bibtex]
Zhou, Nie, Guo, Wei, Zhang, Minervini, Ma, Gui, Zhang, Huang - Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs. The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024 Main Conference) [bibtex]
Zhao, Qu, Staniszewski, Tworkowski, Liu, Miłoś, Wu, Minervini - Analysing The Impact of Sequence Composition on Language Model Pre-Training. 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024 Main Conference; Oral, top 8% of accepted papers) [bibtex]
van Krieken, Minervini, Ponti, Vergari - On the Independence Assumption in Neurosymbolic Learning. International Conference on Machine Learning (ICML 2024) [bibtex]
Solano, Sanni, Camburu, Minervini - SparseFit: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations. 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024, Main Conference) [bibtex]
He, Wu, Camburu, Minervini, Stenetorp - Using Natural Language Explanations to Improve Robustness of In-context Learning. 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024, Main Conference) [bibtex]
Wang, Minervini, Ponti - Probing the Emergence of Cross-lingual Alignment During Large Language Model Pre-Training. 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024, Findings) [bibtex]
Armengol-Estapé, Rocha, Woodruff, Minervini, O'Boyle - Forklift: An Extensible Neural Lifter. Conference on Language Modeling (CoLM 2024, 28% acceptance rate) [bibtex]
Yu, He, Minervini, Pan - Evaluating the Adversarial Robustness of Retrieval-Based In-Context Learning for Large Language Models. Conference on Language Modeling (CoLM 2024, 28% acceptance rate) [bibtex]
Tyukin, Dovonon, Kaddour, Minervini - Attention Is All You Need But You Don’t Need All Of It For Inference of Large Language Models. ICML 2024 Workshop on Theoretical Foundations of Foundation Model (TF2M @ ICML 2024) [bibtex]
Gema, Hong, Minervini, Daines, Alex - Edinburgh Clinical NLP at SemEval-2024 Task 2: Fine-tune your model unless you have access to GPT-4. 7th ClinicalNLP@NAACL 2024 (ClinicalNLP 2024) [bibtex]
Gema, Lee, Minervini, Daines, Simpson, Alex - Edinburgh Clinical NLP at MEDIQA-CORR 2024: Guiding Large Language Models with Hints. 7th ClinicalNLP@NAACL 2024 (ClinicalNLP 2024) [bibtex]
Sayin, Minervini, Staiano, Passerini - Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain. 7th ClinicalNLP@NAACL 2024 (ClinicalNLP 2024) [bibtex]
Gema, Daines, Minervini, Alex - Parameter-Efficient Fine-Tuning of LLaMA for the Clinical Domain. 7th ClinicalNLP@NAACL 2024 (ClinicalNLP 2024) [bibtex]
Scardapane, Baiocchi, Devoto, Marsocci, Minervini, Pomponi - Conditional computation in neural networks: principles and research trends. Intelligenza Artificiale 18(1): 175-190 (2024) [bibtex]
Abdumalikov, Minervini, Kementchedjhieva - Answerability in Retrieval-Augmented Open-Domain Question Answering. CoRR abs/2403.01461 (2024) [bibtex]
Malitesta, Mancino, Minervini, Di Noia - Dot Product is All You Need: Bridging the Gap Between Item Recommendation and Link Prediction. CoRR abs/2409.07433 (2024) [bibtex]
Hong, Gema, Saxena, Du, Nie, Zhao, Perez-Beltrachini, Ryabinin, He, Fourrier, Minervini - The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models. CoRR abs/2404.05904 (2024) [bibtex]
Setzu, Marchiori Manerba, Minervini, Nozza - FairBelief - Assessing Harmful Beliefs in Language Models. CoRR abs/2402.17389 (2024) [bibtex]
Zhao, Du, Hong, Gema, Devoto, Wang, He, Wong, Minervini - Analysing the Residual Stream of Language Models Under Knowledge Conflicts. CoRR abs/2410.16090 (2024) [bibtex]
Ilievski, Hammer, van Harmelen, Paassen, Saralajew, Schmid, Biehl, Bolognesi, Dong, Gashteovski, Hitzler, Marra, Minervini, Mundt, Ngonga Ngomo, Oltramari, Pasi, Saribatur, Serafini, Shawe-Taylor, Shwartz, Skitalinskaya, Stachl, van de Ven, Villmann - Aligning Generalisation Between Humans and Machines. CoRR abs/2411.15626 (2024) [bibtex]
Minervini, Franceschi, Niepert - Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models. 37th AAAI Conference on Artificial Intelligence (AAAI 2023, 19.6% acceptance rate) [bibtex]
Arakelyan*, Minervini*, Daza, Cochez, Augenstein - Adapting Neural Link Predictors for Data-Efficient Complex Query Answering. 37th Conference on Neural Information Processing Systems (NeurIPS 2023, 26% acceptance rate) [bibtex]
Kaddour, Key, Nawrot, Minervini, Kusner - No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models. 37th Conference on Neural Information Processing Systems (NeurIPS 2023, 26% acceptance rate) [bibtex]
Andresel, Tran, Domokos, Minervini, Stepanova - Combining Inductive and Deductive Reasoning for Query Answering over Incomplete Knowledge Graphs. 32nd ACM International Conference on Information and Knowledge Management (CIKM 2023) [bibtex]
Zhou, Iacobacci, Minervini - XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Tracking. The 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023) [bibtex]
Ghasemi Madani, Minervini - REFER: An End-to-end Rationale Extraction Framework for Explanation Regularization. SIGNLL Conference on Computational Natural Language Learning (CoNLL 2023) [bibtex]
Janik, Torrente, Costabello, Calvo, Walsh, Camps, Mohamed, Ortega, Nováček, Massutí, Minervini, Garcia Campelo, Del Barco, Bosch-Barrera, Menasalvas, Timilsina, Provencio - Machine Learning–Assisted Recurrence Prediction for Patients With Early-Stage Non–Small-Cell Lung Cancer. JCO Clinical Cancer Informatics 2023 :7 [bibtex]
Timilsina, Fey, Buosi, Janik, Costabello, Carcereny, Rodrıguez Abreu, Cobo, López Castro, Bernabé, Minervini, Torrente, Provencio, Nováček - Synergy between imputed genetic pathway and clinical information for predicting recurrence in early stage non-small cell lung cancer. Journal of Biomedical Informatics 144, ISSN 1532-0464 [bibtex]
Timilsina, Buosi, Janik, Minervini, Costabello, Torrente, Provencio, Calvo, Camps, Ortega, Massutí, Garcia Campelo, del Barco Bosch-Barrera, Nováček - Learning Survival Models for Relapse Prediction in Early-Stage Lung Cancer Patients. International Joint Conference on Neural Networks (IJCNN 2023) [bibtex]
Cochez, Alivanistos, Arakelyan, Berrendorf, Daza, Galkin, Minervini, Niepert, Ren - Approximate Answering of Graph Queries. Chapter in Compendium of Neurosymbolic Artificial Intelligence, IOS Press (2023). [bibtex]
Gema, Grabarczyk, De Wulf, Borole, Alfaro, Minervini, Vergari, Rajan - Knowledge Graph Embeddings in the Biomedical Domain: Are They Useful? A Look at Link Prediction, Rule Learning, and Downstream Polypharmacy Tasks. CoRR abs/2305.19979 (2023) [bibtex]
Chen, Mishra, Franceschi, Minervini, Stenetorp, Riedel - ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective. 36th Conference on Neural Information Processing Systems (NeurIPS 2022) [bibtex]
Stacey, Minervini, Dubossarsky, Rei - Logical Reasoning with Span Predictions: Span-level Logical Atoms for Interpretable and Robust NLI Models. 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022) and Efficient Natural Language and Speech Processing Workshop (ENLSP @ NeurIPS 2022, best poster award) [bibtex]
Wu, Zhao, Hu, Minervini, Stenetorp, Riedel - An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks. 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022) [bibtex]
Amin*, Minervini*, Chang, Stenetorp, Neumann - MedDistant19: Towards an Accurate Benchmark for Broad-Coverage Biomedical Relation Extraction. 29th International Conference on Computational Linguistics (COLING 2022) [bibtex]
Minervini*, Arakelyan*, Daza*, Cochez - Complex Query Answering with Neural Link Predictors (Extended Abstract). 31st International Joint Conference on Artificial Intelligence (IJCAI 2022) [bibtex]
Morris, Minervini, Blunsom - Learning Proof Path Selection Policies in Neural Theorem Proving. 16th International Workshop on Neural-Symbolic Learning and Reasoning (NeSy @ IJCLR 2022), and 4th Conference on Automated Knowledge Base Construction (AKBC 2022) [bibtex]
Wren, Minervini, Franceschi, Zantedeschi - Learning Discrete Directed Acyclic Graphs via Backpropagation. Workshop on Causality for Real-world Impact (CML4Impact @ NeurIPS 2022), and Workshop on Neuro Causal and Symbolic AI (nCSI @ NeurIPS 2022) [bibtex]
Timilsina, Buosi, Fey, Janik, Torrente, Provencio, Bermúdez, Carcereny, Costabello, Rodrıguez Abreu, Cobo, Castro, Bernabé, Guirado, Minervini, Nováček - Integration of Clinical Information and Imputed Aneuploidy Scores to Enhance Relapse Prediction in Early Stage Lung Cancer Patients. American Medical Informatics Association, Annual Symposium (AMIA 2022) [bibtex]
Li, Minervini - Differentiable Reasoning over Long Stories - Assessing Systematic Generalisation in Neural Models. CoRR abs/2203.10620 (2022) [bibtex]
Arakelyan*, Daza*, Minervini*, Cochez - Complex Query Answering with Neural Link Predictors. 9th International Conference on Learning Representations (ICLR 2021, oral presentation 2% acceptance rate, overall 29% - Outstanding Paper Award) [bibtex, presentation]
Niepert, Minervini, Franceschi - Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions. 35th Conference on Neural Information Processing Systems (NeurIPS 2021) [bibtex, presentation, Yannic Kilcher's explanation]
Jiang, Minervini, Jiang, Rocktäschel - Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning. 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021, 24.8% acceptance rate, oral presentation) [bibtex]
Lewis, Wu, Liu, Minervini, Küttler, Piktus, Stenetorp, Riedel - PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them. Transactions of the Association for Computational Linguistics (TACL 2021) [bibtex, presentation]
Wu, Minervini, Stenetorp, Riedel - Training Adaptive Computation for Open-Domain Question Answeringwith Computational Constraints. The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021) [bibtex]
de Vassimon Manela, Errington, Fisher, van Breugel, Minervini - Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models. 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021) [bibtex]
Dobrowolska, Vergari, Minervini - Neural Concept Formation in Knowledge Graphs. 3rd International Conference on Automated Knowledge Base Construction (AKBC 2021) [bibtex]
Chen, Minervini, Stenetorp, Riedel - Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations. 3rd International Conference on Automated Knowledge Base Construction (AKBC 2021) [bibtex]
Setzu, Monreale, Minervini - TRIPLEx: Triple Extraction for Explanation. 3rd IEEE International Conference on Cognitive Machine Intelligence (CogMI 2021) [bibtex]
Mohamed, Walsh, Timilsina, Torrente, Franco, Provencio, Janik, Costabello, Minervini, Stenetorp, Novácek - On Predicting Recurrence in Early Stage Non-small Cell Lung Cancer. American Medical Informatics Association, Annual Symposium (AMIA 2021) [bibtex]
Torrente, Franco, Calvo, Collazo Lorduy, Menasalvas, Vidal, Sousa, Pimentao, Novacek, Minervini, Fey, Costabello, Pocs, Provencio - P08.01 Building Personalized Follow-Up Care Through AI by Bringing the Lung Cancer Patient, Data Scientist and Oncologist Together. Journal of Thoracic Oncology, International Association for the Study of Lung Cancer 16(10):S991-S992, October 2021 [bibtex]
Chauhan, Gupta, Minervini - A Probabilistic Framework for Knowledge Graph Data Augmentation. Data-Centric AI Workshop (DCAI @ NeurIPS 2021) [bibtex]
Betz, Niepert, Minervini, Stuckenschmidt - Backpropagating through Markov Logic Networks. Proceedings of 15th International Workshop on Neural-Symbolic Learning and Reasoning (NeSy 2020/2021 @ IJCLR 2021) [bibtex]
Minervini, Riedel, Stenetorp, Grefenstette, Rocktäschel - Learning Reasoning Strategies in End-to-End Differentiable Proving. 37th International Conference on Machine Learning (ICML 2020, 21.8% acceptance rate) [bibtex]
Minervini*, Bošnjak*, Rocktäschel, Riedel, Grefenstette - Differentiable Reasoning on Large Knowledge Bases and Natural Language. 34th AAAI Conference on Artificial Intelligence (AAAI 2020, oral presentation 4.5% acceptance rate; overall 20.6%) [bibtex]
Min, Boyd-Graber, Alberti, Chen, Choi, Collins, Guu, Hajishirzi, Lee, Palomaki, Raffel, Roberts, Kwiatkowski, Lewis, Wu, Küttler, Liu, Minervini, Stenetorp, Riedel, Yang, Seo, Izacard, Petroni, Hosseini, De Cao, Grave, Yamada, Shimaoka, Suzuki, Miyawaki, Sato, Takahashi, Suzuki, Fajcik, Docekal, Ondrej, Smrz, Cheng, Shen, Liu, He, Chen, Gao, Oguz, Chen, Karpukhin, Peshterliev, Okhonko, Schlichtkrull, Gupta, Mehdad, Yih - NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned. NeurIPS 2020 Competition and Demonstration Track (NeurIPS 2020) [bibtex]
Camburu, Shillingford, Minervini, Lukasiewicz, Blunsom - Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations. 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020, 17.6% acceptance rate) [bibtex]
Wu, Minervini, Stenetorp, Riedel - Don't Read Too Much Into It: Adaptive Computation for Open-Domain Question Answering. The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020, 22.4% acceptance rate) [bibtex]
Stacey, Minervini, Dubossarsky, Riedel, Rocktäschel - Gone At Last: Removing the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Training. The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020, 22.4% acceptance rate) [bibtex]
Welbl, Minervini, Bartolo, Stenetorp, Riedel - Undersensitivity in Neural Reading Comprehension. Findings of EMNLP 2020 [bibtex]
Minervini, Bošnjak, Rocktäschel, Riedel, Grefenstette - Differentiable Reasoning on Large Knowledge Bases and Natural Language. Chapter in Knowledge Graphs for eXplainable Artificial Intelligence: Foundations, Applications and Challenges, IOS Press (2020). [bibtex]
Bianchi, Rossiello, Costabello, Palmonari, Minervini - Knowledge Graph Embeddings and Explainable AI. Chapter in Knowledge Graphs for eXplainable Artificial Intelligence: Foundations, Applications and Challenges, IOS Press (2020). [bibtex]
Dobrowolska, Vergari, Minervini - Neural Concept Formation in Knowledge Graphs. Knowledge Representation & Reasoning Meets Machine Learning workshop at NeurIPS (KR2ML 2020) [bibtex]
Stacey, Minervini, Dubossarsky, Riedel, Rocktäschel - There is Strength in Numbers: Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adver-sarial Training. CoRR abs/2004.07790 (2020) [bibtex]
Jiang, Luketina, Nardelli, Minervini, Torr, Whiteson, Rocktäschel - WordCraft: An Environment for Benchmarking Commonsense Agents. Workshop on Language in Reinforcement Learning (LaReL) @ ICML 2020 [bibtex]
Weber, Minervini, Münchmeyer, Leser, Rocktäschel - NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language. 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019, 22.7% acceptance rate) [bibtex]
Muñoz, Minervini, Nickles - Embedding Cardinality Constraints in Neural Link Predictors. ACM Symposium on Applied Computing - Semantic Web Track (ACM SAC 2019, 25% acceptance rate) [bibtex]
Cowen-Rivers, Minervini, Riedel, Rocktäschel, Wang, Bošnjak - Neural Variational Inference for Estimating Knowledge Graph Embedding Uncertainty. 14th International Workshop on Neural-Symbolic Learning and Reasoning (NeSy) at IJCAI 2019 [bibtex]
Minervini, Riedel - Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledge. SIGNLL Conference on Computational Natural Language Learning (CoNLL 2018, 20.65% acceptance rate) [bibtex]
Minervini, Bošnjak, Campero, Rocktäschel, Grefenstette, Riedel - Neural Theorem Proving on Natural Language. International Conference on Probabilistic Programming (PROBPROG 2018) [bibtex]
Minervini, Bošnjak, Rocktäschel, Riedel - Towards Neural Theorem Proving at Scale. Federated Artificial Intelligence Meeting (FAIM) Workshop on Neural Abstract Machines & Program Induction v2 (NAMPI 2018) [bibtex]
Mitchell, Minervini, Stenetorp, Riedel - Extrapolation in NLP. Workshop on Generalization in the Age of Deep Learning @ ACL 2018 [bibtex]
Weissenborn, Minervini, Dettmers, Augenstein, Welbl, Rocktäschel, Bošnjak, Mitchell, Demeester, Stenetorp, Riedel - Jack the Reader - A Machine Reading Framework. Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL 2018), System Demonstrations [bibtex]
Dettmers, Minervini, Stenetorp, Riedel - Convolutional 2D Knowledge Graph Embeddings. 32nd AAAI Conference on Artificial Intelligence (AAAI 2018), February 2018 [bibtex]
Minervini, Tresp, d'Amato, Fanizzi - Adaptive Knowledge Propagation in Web Ontologies. Journal Article on ACM Transactions on the Web (ACM TWEB 2018) [bibtex]
Minervini, Demeester, Rocktäschel, Riedel - Adversarial Sets for Regularising Neural Link Predictors. 33rd Conference on Uncertainty in Artificial Intelligence (UAI 2017), August 2017 [bibtex]
Minervini, Costabello, Muñoz, Nováček, Vandenbussche - Regularizing Neural Knowledge Graph Embeddings via Equivalence and Inversion Axioms. European Conference on Machine Learning & Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2017) [bibtex]
Minervini, d'Amato, Fanizzi - Efficient Energy-based Embedding Models for Link Prediction in Knowledge Graphs. Journal on Intelligent Information Systems (JIIS 2016), Recent Advances in Mining Patterns from Complex Data, ISSN 1573-7675, June 2016 [bibtex]
Minervini, d'Amato, Fanizzi, Tresp - Discovering Similarity and Dissimilarity Relations for Knowledge Propagation in Web Ontologies. Journal on Data Semantics (JoDS), May 2016 [bibtex]
Minervini, d'Amato, Fanizzi, Esposito - Leveraging the Schema in Latent Factor Models for Knowledge Graph Completion. ACM Symposium on Applied Computing - Semantic Web Track (ACM SAC 2016), ISBN 978-1-4503-3739-7, April 2016 (24% acceptance rate) [bibtex]
Yumusak, Muñoz, Minervini, Dogdu, Kodaz - A Hybrid Method for Rating Prediction Using Linked Data Features and Text Reviews. 1st International Workshop on Completing and Debugging the Semantic Web (Know@LOD-2016 (winning entry) [bibtex]
Minervini, d'Amato, Fanizzi, Esposito - Scalable Learning of Entity and Predicate Embeddings for Knowledge Graph Completion. 14th IEEE International Conference on Machine Learning and Applications (ICMLA 2015), ISBN 978-1-5090-0287-0, December 2015 [bibtex]
Minervini, d'Amato, Fanizzi, Esposito - Efficient Learning of Entity and Predicate Embeddings for Link Prediction in Knowledge Graphs. 11th International Workshop on Uncertainty Reasoning for the Semantic Web, October 2015 [bibtex]
Minervini, d'Amato, Fanizzi, Esposito - A Gaussian Process Model for Knowledge Propagation in Web Ontologies. IEEE International Conference on Data Mining (ICDM 2014) ISBN 978-1-4799-4302-9, December 2014 (19% acceptance rate) [bibtex]
Minervini, d'Amato, Fanizzi, Esposito - Adaptive Knowledge Propagation in Web Ontologies. 19th International Conference on Knowledge Engineering and Knowledge Management (EKAW 2014), ISBN 978-3-319-13703-2, November 2014 (best paper award) [bibtex]
Minervini, d'Amato, Fanizzi, Tresp - Learning to Propagate Knowledge in Web Ontologies. 10th International Workshop on Uncertainty Reasoning for the Semantic Web (best paper award) [bibtex]
Minervini, d'Amato, Fanizzi, Esposito - Graph-Based Regularization for Transductive Class-Membership Prediction. In: Uncertainty Reasoning for the Semantic Web III - ISWC International Workshops, URSW 2011-2013, Revised Selected Papers - Springer, ISBN: 978-3-319-13412-3 [bibtex]
Minervini, d'Amato, Fanizzi, Esposito - Learning Probabilistic Description Logic Concepts Under Alternative Assumptions on Incompleteness. In: Uncertainty Reasoning for the Semantic Web III - ISWC International Workshops, URSW 2011-2013, Revised Selected Papers - Springer, ISBN: 978-3-319-13412-3 [bibtex]
Minervini, Fanizzi, d'Amato, Esposito - Rank Prediction for Semantically Annotated Resources. ACM Symposium on Applied Computing - Semantic Web Track (ACM SAC 2013), ISBN 978-1-4503-1656-9, March 2013 (24% acceptance rate) [bibtex]
Minervini, d'Amato, Fanizzi, Esposito - Transductive Inference for Class-Membership Propagation in Web Ontologies. The Semantic Web: Semantics and Big Data (ESWC 2013), ISBN 978-3-642-38287-1, May 2013 (26% acceptance rate) (sources and datasets) [bibtex]
Minervini, Fanizzi, d'Amato, Esposito - Learning probabilistic Description logic concepts: under different Assumptions on missing knowledge. ACM Symposium on Applied Computing - Semantic Web Track (ACM SAC 2012), ISBN 978-1-4503-0857-1, March 2012 [bibtex]
Minervini, d'Amato, Fanizzi - A Graph Regularization Based Approach to Transductive Class-Membership Prediction. 8th International Workshop on Uncertainty Reasoning for the Semantic Web, November 2012 [bibtex]
Fanizzi, d’Amato, Esposito, Minervini - Numeric Prediction on OWL Knowledge Bases through Terminological Regression Trees. International Journal on Semantic Computing 2012 [bibtex]
Minervini, d'Amato, Fanizzi - Learning Terminological Bayesian Classifiers: A Comparison of Alternative Approaches to Dealing with Unknown Concept Memberships. 9th Italian Convention on Computational Logic, June 2012 [bibtex]
Minervini, d'Amato, Fanizzi - Learning Terminological Naive Bayesian Classifiers under Different Assumptions on Missing Knowledge. 7th International Workshop on Uncertainty Reasoning for the Semantic Web (URSW 2011), CEUR Workshop Proceedings vol. 778 ISSN 1613-0073, October 2011 [bibtex]
Calefato, Lanubile, Minervini - Can Real-Time Machine Translation Overcome Language Barriers in Distributed Requirements Engineering?. 5th IEEE International Conference on Global Software Engineering, IEEE ICGSE 2010, ISBN 978-1-4244-7619-0, August 2010 [bibtex]
Minervini - Apertium goes SOA: an efficient and scalable service based on the Apertium rule-based machine translation platform. 1st International Workshop on Free/Open-Source Rule-Based Machine Translation, ISBN-13: 978-8-46-136188-5, November 2009 [bibtex]