5 papers
Practical Bayesian Inference for Speech SNNs: Uncertainty and Loss-Landscape Smoothing
Yesmine Abdennadher, Philip N. Garner
Spiking Neural Networks (SNNs) are naturally suited for speech processing tasks due to their specific dynamics, which allows them to handle temporal data. However, the threshold-ba…
Alleviating Forgetfulness of Linear Attention by Hybrid Sparse Attention and Contextualized Learnable Token Eviction
Mutian He, Philip N. Garner
Linear-attention models that compress the entire input sequence into a fixed-size recurrent state offer an efficient alternative to Transformers, but their finite memory induces fo…
Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity
Mutian He, Philip N. Garner
Architectures such as Linformer and Mamba have recently emerged as competitive linear time replacements for transformers. However, corresponding large pretrained models are often u…
A Bayesian Interpretation of Adaptive Low-Rank Adaptation
Haolin Chen, Philip N. Garner
Motivated by the sensitivity-based importance score of the adaptive low-rank adaptation (AdaLoRA), we utilize more theoretically supported metrics, including the signal-to-noise ra…
Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting
Haolin Chen, Philip N. Garner
We are motivated primarily by the adaptation of text-to-speech synthesis models; however we argue that more generic parameter-efficient fine-tuning (PEFT) is an appropriate framewo…