1.5k citations
- Centre National de la Recherche ScientifiqueFR17 papers
- Space Telescope Science InstituteUS14 papers
- California Institute of TechnologyUS11 papers
- Leiden UniversityNL11 papers
- Max Planck Institute for AstronomyDE11 papers
- University of MichiganUS11 papers
- George Washington UniversityUS10 papers
- The University of Texas at AustinUS10 papers
- Université Bourgogne Franche-ComtéFR10 papers
- University of ArizonaUS10 papers
- University of HoustonUS9 papers
- Center for Astrophysics Harvard & SmithsonianUS8 papers
9 papers · 1 filter
Class-Conditioned Gaussian Mixture Modeling for Imbalanced Time Series Quantification
Md Shahriar Kabir, Mayesha Maliha R. Mithila, Anne H. H. Ngu +2
Quantification, estimating class prevalences in bags of unlabeled instances is vital in domains where aggregate statistics are more important than individual instance labels, such…
Provably Lossless Acceleration of DNN Mutation Testing via Memoization
Ali Ghanbari, Ben Greenman, Sasan Tavakkol +1
Mutation analysis has recently reemerged in the context of deep neural networks (DNNs) as a promising, but notoriously costly, approach for assessing test dataset adequacy. Existin…
SpecPylot: Python Specification Generation using Large Language Models
Ragib Shahariar Ayon, Shibbir Ahmed
Automatically generating formal specifications could reduce the effort needed to improve program correctness, but in practice, this is still challenging. Many developers avoid writ…
How leaky? A large parameter study of leaky dust traps to quantify the transport of pebbles and ice in protoplanetary discs
Adrien Houge, Anders Johansen, Andrea Banzatti +1
In protoplanetary discs, the presence of dust traps can significantly alter the transport of solids from the outer to the inner regions, and hence they are often invoked as an expl…
From Helpful to Trustworthy: LLM Agents for Pair Programming
Ragib Shahariar Ayon
LLM-based coding agents are increasingly used to generate code, tests, and documentation. Still, their outputs can be plausible yet misaligned with developer intent and provide lim…
TransConv-DDPM: Enhanced Diffusion Model for Generating Time-Series Data in Healthcare
Md Shahriar Kabir, Sana Alamgeer, Minakshi Debnath +1
The lack of real-world data in clinical fields poses a major obstacle in training effective AI models for diagnostic and preventive tools in medicine. Generative AI has shown promi…