6 citations · 19 across the 11 of their papers we have counts for
11 papers
A Practical Investigation of Training-free Relaxed Speculative Decoding
Guoxuan Xia, Luka Ribar, Paul Balanca
Speculative decoding accelerates sampling from an autoregressive LLM by using a faster auxiliary model to draft tokens which are then verified in parallel by the LLM. Standard spec…
Absorb & Escape: Overcoming Single Model Limitations in Generating Genomic Sequences
Zehui Li, Yuhao Ni, Guoxuan Xia +4
Abstract Recent advances in immunology and synthetic biology have accelerated the development of deep generative methods for DNA sequence design. Two dominant approaches in this fi…
Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It
Guoxuan Xia, Olivier Laurent, Gianni Franchi +1
Label smoothing (LS) is a popular regularisation method for training neural networks as it is effective in improving test accuracy and is simple to implement. ``Hard'' one-hot labe…
DiscDiff: Latent Diffusion Model for DNA Sequence Generation
Zehui Li, Yuhao Ni, William A V Beardall +4
This paper introduces a novel framework for DNA sequence generation, comprising two key components: DiscDiff, a Latent Diffusion Model (LDM) tailored for generating discrete DNA se…
Score Normalization for a Faster Diffusion Exponential Integrator Sampler
Guoxuan Xia, Duolikun Danier, Ayan Das +4
Recently, Zhang et al. have proposed the Diffusion Exponential Integrator Sampler (DEIS) for fast generation of samples from Diffusion Models. It leverages the semi-linear nature o…
Latent Diffusion Model for DNA Sequence Generation
Zehui Li, Yuhao Ni, Tim August B. Huygelen +4
The harnessing of machine learning, especially deep generative models, has opened up promising avenues in the field of synthetic DNA sequence generation. Whilst Generative Adversar…
Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties
Yassir Fathullah, Guoxuan Xia, Mark Gales
Efficiently and reliably estimating uncertainty is an important objective in deep learning. It is especially pertinent to autoregressive sequence tasks, where training and inferenc…
Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models
Guoxuan Xia, Christos-Savvas Bouganis
Deep Ensembles are a simple, reliable, and effective method of improving both the predictive performance and uncertainty estimates of deep learning approaches. However, they are wi…
On the Usefulness of Deep Ensemble Diversity for Out-of-Distribution Detection
Guoxuan Xia, Christos-Savvas Bouganis
The ability to detect Out-of-Distribution (OOD) data is important in safety-critical applications of deep learning. The aim is to separate In-Distribution (ID) data drawn from the…
Augmenting Softmax Information for Selective Classification with Out-of-Distribution Data
Guoxuan Xia, Christos-Savvas Bouganis
Detecting out-of-distribution (OOD) data is a task that is receiving an increasing amount of research attention in the domain of deep learning for computer vision. However, the per…
An Underexplored Dilemma between Confidence and Calibration in Quantized Neural Networks
Guoxuan Xia, Sangwon Ha, Tiago Azevedo +1
Modern convolutional neural networks (CNNs) are known to be overconfident in terms of their calibration on unseen input data. That is to say, they are more confident than they are…