Europe
Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models
Authors contributed equally to this work.
UnderstandingAdaptive, MultiscaleTemporal IntegrationInDeepSpeechRecognitionSystems
A central challenge of representing natural signals, such as speech and music, is that they are structured across many different timescales (Chomsky and Halle, 1968; Lerdahl and Jackendoff, 1985; Hickokand Poeppel, 2007).
Boosting Learning for LDPC Codes to Improve the Error-Floor Performance
These works assume an arbitrary neural network with no prior knowledge of decoding algorithms, and accordingly, face the challenge of learning a decoding algorithm.
Enhancing Robustness of Graph Neural Networks on Social Media with Explainable Inverse Reinforcement Learning
Social media platforms capture diverse attack sequence samples through both machine and manual screening processes. Investigating effective ways to leverage these adversarial samples to enhance robustness is imperative.