Country
Infusing Synthetic Data with Real-World Patterns for Zero-Shot Material State Segmentation
Minerals in rocks, sediment in soil, dust on surfaces, infection on leaves, stains on fabrics, and foam in liquids are some of these almost infinite numbers of states and patterns.
Lift Yourself Up: Retrieval-augmented Text Generation with Self-Memory
With direct access to human-written reference as memory, retrieval-augmented generation has achieved much progress in a wide range of text generation tasks.
Parameterized Approximation Schemes for Fair-Range Clustering
It imposes lower and upper bound constraints on the number of facilities opened for each label, ensuring fair representation of all demographic groups by the selected facilities.
LART: Neural Correspondence Learning with Latent Regularization Transformer for 3D Motion Transfer
In this work, we propose a novel 3D Transformer framework called LART for 3D motion transfer.
SGD vs GD: Rank Deficiency in Linear Networks
Deep neural networks have significantly advanced machine learning in recent decades.
