Search Results for author:
Found 6 papers, 1 papers with code
Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding
We investigate the combination of encoder-decoder LLMs with both encoder-decoder and decoder-only SLMs from different model families and only require fine-tuning of the SLM.
Hyperbolic Convolutional Neural Networks
However, no papers have yet suggested a general approach to using Hyperbolic Convolutional Neural Networks for structured data processing, although these are the most common examples of data used.
Revisiting Single-gated Mixtures of Experts
Mixture of Experts (MoE) are rising in popularity as a means to train extremely large-scale models, yet allowing for a reasonable computational cost at inference time.
Simple and Efficient Architectures for Semantic Segmentation
Though the state-of-the architectures for semantic segmentation, such as HRNet, demonstrate impressive accuracy, the complexity arising from their salient design choices hinders a range of model acceleration tools, and further they make use of operations that are inefficient on current hardware.
Cyclical Pruning for Sparse Neural Networks
Current methods for pruning neural network weights iteratively apply magnitude-based pruning on the model weights and re-train the resulting model to recover lost accuracy.
Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces
Second, a rapid evolutionary search finds a set of pareto-optimal architectures for any scenario using the accuracy predictor and on-device measurements.
