conftrace_

interpolation technique

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

learnable position vector (1) logarithmic norm (1) density-ratio function (1) adaptive attention (1) velocity field (1) gradient propagation (1) neural ode (1) adjoint method (1) sparse attention (1) long sequence modeling (1)

Papers

Minimizing f-Divergences by Interpolating Velocity Fields ICML 2024 Adaptive Attention for Sparse-based Long-sequence Transformer ACL 2023 Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs NeurIPS 2020