Deep Learning
TA GATES An Encoding Neural Network Architectures
Then, (t) is operationembeddingsemb(t)op (Line 9).emb(t)op will (t 1)
SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data
Recent text-to-image (T2I) generation models have demonstrated impressive capabilities in creating images from text descriptions.
On the convergence of single-call stochastic extra-gradient methods
Yu-Guan Hsieh, Franck Iutzeler, Jérôme Malick, Panayotis Mertikopoulos
VI problems; logarithmic factors ignored throughout. A box indicates a contribution from this paper.
Activating Self-Attention for Multi-Scene Absolute Pose Regression
Multi-scene absolute pose regression addresses the demand for fast and memory-efficient camera pose estimation across various real-world environments.
Attack-Resilient Image Watermarking Using Stable Diffusion
Watermarking images is critical for tracking image provenance and proving ownership.
GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series
Modeling real-world multidimensional time series can be particularly challenging when these are sporadically observed ( i.e., sampling is irregular both in time
Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks
For deep linear networks, these kernels satisfy a set of algebraic matrix equations. For nonlinear networks, we provide an alternating sampling procedure to self-consistently solve for the kernel order parameters.