From the 6 of 183 papers with an AI index.
266 citations
- University of TorontoCA57 papers
- University of ChicagoUS55 papers
- Université de MontréalCA52 papers
- Michigan State UniversityUS48 papers
- University of OxfordGB48 papers
- University of British ColumbiaCA47 papers
- University of GenevaCH47 papers
- Centre National de la Recherche ScientifiqueFR46 papers
- Université Paris CitéFR46 papers
- Université Paris-SaclayFR46 papers
- University College LondonGB46 papers
- University of ArizonaUS44 papers
5 papers · 1 filter
Diversity-Enriched Option-Critic
Anand Kamat, Doina Precup
The paper introduces an information‑theoretic intrinsic reward and a new termination objective to encourage a diverse set of options in the option‑critic framework, improving perfo…
The Pragmatic Frames of Spurious Correlations in Machine Learning: Interpreting How and Why They Matter
Samuel J. Bell, Skyler Wang
Learning correlations from data forms the foundation of today's machine learning (ML) and artificial intelligence research. While contemporary methods enable the automatic discover…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1144
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
Link Representation Learning for Probabilistic Travel Time Estimation
Chen Xu, Qiang Wang, Lijun Sun
Travel time estimation is a key task in navigation apps and web mapping services. Existing deterministic and probabilistic methods, based on the assumption of trip independence, pr…
Certifying Robustness of Graph Convolutional Networks for Node Perturbation with Polyhedra Abstract Interpretation
Boqi Chen, Kristóf Marussy, Oszkár Semeráth +2
Graph convolutional neural networks (GCNs) are powerful tools for learning graph-based knowledge representations from training data. However, they are vulnerable to small perturbat…