From the 9 of 237 papers with an AI index.
23 citations
- Heidelberg UniversityDE61 papers
- University of ChicagoUS58 papers
- Université Paris CitéFR56 papers
- Columbia UniversityUS55 papers
- Sapienza University of RomeIT55 papers
- University of OxfordGB55 papers
- Tsinghua UniversityCN54 papers
- Université Paris-SaclayFR54 papers
- The University of Texas at AustinUS53 papers
- University of CambridgeGB53 papers
- European Organization for Nuclear ResearchCH52 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di NapoliIT52 papers
8 papers · 1 filter
LionVote: Per-Layer Learning Rate Adaptation for Lion
Kris Atallah
Per-layer diagnostics reveal that, at the prescribed learning rate, Lion's effective scale is 2.6-2.8x too high for attention and MLP parameters and ~2x too high for normalization…
What's on My Network? Using Large Language Models to Identify Real-World IoT Devices at Scale
Rameen Mahmood, Tousif Ahmed, Sai Teja Peddinti +1
The growth of IoT devices in shared environments has outpaced our ability to identify them, posing urgent risks to privacy, safety, and accountability. This challenge is especially…
Causal Machine Learning Is Not a Panacea: A Roadmap for Observational Causal Inference in Health
Donna Tjandra, Trenton Chang, Sonali Parbhoo +8
Objective: The growing availability of large-scale observational clinical datasets and challenges in conducting randomized controlled trials have spurred enthusiasm in using causal…
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…
Large Language Models Predict Functional Outcomes after Acute Ischemic Stroke
Anjali K. Kapoor, Anton Alyakin, Jin Vivian Lee +8
Accurate prediction of functional outcomes after acute ischemic stroke can inform clinical decision-making and resource allocation. Prior work on modified Rankin Scale (mRS) predic…
Flash STU: Fast Spectral Transform Units
Y. Isabel Liu, Windsor Nguyen, Yagiz Devre +3
Recent advances in state-space model architectures have shown great promise for efficient sequence modeling, but challenges remain in balancing computational efficiency with model…