|
- DATT: Deep Adaptive Trajectory Tracking for Quadrotor Control
DATT enables quadrotors to precisely track arbitrary, potentially infeasible trajectories in the presence of large disturbances
- DATT: Deep Adaptive Trajectory Tracking for Quadrotor Control
DATT builds on a novel feedforward-feedback-adaptive control structure trained in simulation us- ing reinforcement learning When deployed on real hardware, DATT is augmented with a disturbance estimator using L 1adaptive control in closed-loop, without any fine-tuning
- TinyMIG: Transferring Generalization from Vision Foundation Models to . . .
Medical imaging faces significant challenges in single-domain generalization (SDG) due to the diversity of imaging devices and the variability among data collection centers To address these challenges, we propose TinyMIG, a framework designed to transfer generalization capabilities from vision foundation models to medical imag- ing SDG TinyMIG aims to enable lightweight specialized models to
- RETHINKING ATTENTION WITH PERFORMERS - OpenReview
ABSTRACT We introduce Performers, Transformer architectures which can estimate regular (softmax) full-rank-attention Transformers with provable accuracy, but using only linear (as opposed to quadratic) space and time complexity, without relying on any priors such as sparsity or low-rankness To approximate softmax attention-kernels, Performers use a novel Fast Attention Via positive Orthogonal
|
|
|