state-space models

Problem-Class Descriptors Descriptors that characterize the properties of problem classes to aid in understanding… Fixed Random Projection A method that uses a fixed random projection to accelerate distance computations… Sparsity-Aware Retraining A retraining process that takes into account the sparsity of the model,… EvoLMM EvoLMM is a self-evolving framework for training large multimodal models using continuous… Low-rank Learning A method that approximates high-dimensional matrices using low-rank representations to reduce computational… Group-aware SSM Elastification A method that preserves structural constraints in model compression while optimizing for…