3 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Flow-based spectral kernel attention (FSKA), a framework for learning expressive nonstationary attention kernels, is proposed and it is shown that expressive kernel learning enables a simplified attention design with removed query--key projections and fixed orthogonal value projections, resulting in a more parameter-ef...
Transformers provide a state-of-the-art modeling framework, yet poor calibration limits their reliability in safety-critical applications. A promising direction addresses this issue by interpreting attention as a Gaussian process (GP) posterior, which enables principled uncertainty calibration but incurs cubic complexi...
This work analytically marginalize the sparse GP posterior to derive a tractable drift-matching objective that accounts for both the posterior mean and uncertainty of the unknown drift, and introduces an irregular-time-aware variational state posterior that incorporates the actual observation times during both encoding...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
