Papers
Deep, long-form breakdowns of recent research in AI, machine learning, security & programming languages.
16 results on this page · clear filters
Exponential Hardness of Off-Policy Evaluation under History-Dependent Logging
by Pranaya Jajoo
Probabilistic Linear Explanations
by Frederic Koriche, Jean-Marie Lagniez, Chi Tran
Double descent is the principle of least action
by Congzhou M Sha
Knowledge as Orbit: Finite Collections as Phases of an Exactly Periodic Latent Generator
by Siddharth Pal, Viktoria Rojkova
Type Diversity Enables Transformers to Generalise Compositionally
by Anssi Moisio, Mathias Creutz, Mikko Kurimo
General Quantification of Covariate and Concept Shifts
by Hongbo Chen, Li Charlie Xia
Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated Data
by Atindra Jha, Margaret Li, Jure Leskovec, Percy Liang, Luke Zettlemoyer
Distance generalization in transformers: why bother with positional encoding?
by Daniel Henrik Nevermann, Claudius Gros
From Protocols to Evidence: Bounded Claims for AI in Service of the Common Good
by Nitesh V. Chawla, Paulo Benanti
TART: A Modular Tool for Technique-Aware Audio-to-Tablature Guitar Transcription
by Akshaj Gupta, Hwi Joo Park, Andrea Guzman, Shamak Gowda, Samhita Konduri, Jiachen Lian, Robin Netzorg, Gopala Anumanchipalli