Guoxuan Xia

24 papers A* 4A 2Journal 17Unranked 1
YearRankTypeTitle / Venue / Authors
2025 J jnl
A Practical Investigation of Spatially-Controlled Image Generation with Transformers.
CoRR
Guoxuan Xia, Harleen Hanspal, Petru-Daniel Tudosiu, Shifeng Zhang, Sarah Parisot
2025 J jnl
A Practical Investigation of Spatially-Controlled Image Generation with Transformers.
Trans. Mach. Learn. Res.
Guoxuan Xia, Harleen Hanspal, Petru-Daniel Tudosiu, Shifeng Zhang, Sarah Parisot
2025 J jnl
Dynamic Mixture-of-Experts for Visual Autoregressive Model.
CoRR
Jort Vincenti, Metod Jazbec, Guoxuan Xia
2025 J jnl
Exploiting Mixture-of-Experts Redundancy Unlocks Multimodal Generative Abilities.
CoRR
Raman Dutt, Harleen Hanspal, Guoxuan Xia, Petru-Daniel Tudosiu, Alexander Black, Yongxin Yang, Steven McDonagh, Sarah Parisot
2025 A conf
Generative Uncertainty in Diffusion Models.
UAI
Metod Jazbec, Eliot Wong-Toi, Guoxuan Xia, Dan Zhang, Eric T. Nalisnick, Stephan Mandt
2025 J jnl
Generative Uncertainty in Diffusion Models.
CoRR
Metod Jazbec, Eliot Wong-Toi, Guoxuan Xia, Dan Zhang, Eric T. Nalisnick, Stephan Mandt
2025 A* conf
Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It.
ICLR
Guoxuan Xia, Olivier Laurent, Gianni Franchi, Christos-Savvas Bouganis
2025 A* conf
Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation.
CVPR
Gianni Franchi, Nacim Belkhir, Dat Nguyen Trong, Guoxuan Xia, Andrea Pilzer
2024 J jnl
Absorb & Escape: Overcoming Single Model Limitations in Generating Genomic Sequences.
CoRR
Zehui Li, Yuhao Ni, Guoxuan Xia, William A. V. Beardall, Akashaditya Das, Guy-Bart Stan, Yiren Zhao
2024 A* conf
Absorb & Escape: Overcoming Single Model Limitations in Generating Heterogeneous Genomic Sequences.
NeurIPS
Zehui Li, Yuhao Ni, Guoxuan Xia, William A. V. Beardall, Akashaditya Das, Guy-Bart Stan, Yiren Zhao
2024 J jnl
Augmenting the Softmax with Additional Confidence Scores for Improved Selective Classification with Out-of-Distribution Data.
Int. J. Comput. Vis.
Guoxuan Xia, Christos-Savvas Bouganis
2024 J jnl
DiscDiff: Latent Diffusion Model for DNA Sequence Generation.
CoRR
Zehui Li, Yuhao Ni, William A. V. Beardall, Guoxuan Xia, Akashaditya Das, Guy-Bart Stan, Yiren Zhao
2024 J jnl
Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation.
CoRR
Gianni Franchi, Dat Nguyen Trong, Nacim Belkhir, Guoxuan Xia, Andrea Pilzer
2024 J jnl
Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It.
CoRR
Guoxuan Xia, Olivier Laurent, Gianni Franchi, Christos-Savvas Bouganis
2023 J jnl
Latent Diffusion Model for DNA Sequence Generation.
CoRR
Zehui Li, Yuhao Ni, Tim August B. Huygelen, Akashaditya Das, Guoxuan Xia, Guy-Bart Stan, Yiren Zhao
2023 J jnl
Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties.
CoRR
Yassir Fathullah, Guoxuan Xia, Mark J. F. Gales
2023 A conf
Logit-based ensemble distribution distillation for robust autoregressive sequence uncertainties.
UAI
Yassir Fathullah, Guoxuan Xia, Mark J. F. Gales
2023 J jnl
Score Normalization for a Faster Diffusion Exponential Integrator Sampler.
CoRR
Guoxuan Xia, Duolikun Danier, Ayan Das, Stathi Fotiadis, Farhang Nabiei, Ushnish Sengupta, Alberto Bernacchia
2023 A* conf
Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models.
ICCV
Guoxuan Xia, Christos-Savvas Bouganis
2023 J jnl
Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models.
CoRR
Guoxuan Xia, Christos-Savvas Bouganis
2022 — conf
Augmenting Softmax Information for Selective Classification with Out-of-Distribution Data.
ACCV (6)
Guoxuan Xia, Christos-Savvas Bouganis
2022 J jnl
Augmenting Softmax Information for Selective Classification with Out-of-Distribution Data.
CoRR
Guoxuan Xia, Christos-Savvas Bouganis
2022 J jnl
On the Usefulness of Deep Ensemble Diversity for Out-of-Distribution Detection.
CoRR
Guoxuan Xia, Christos-Savvas Bouganis
2021 J jnl
An Underexplored Dilemma between Confidence and Calibration in Quantized Neural Networks.
CoRR
Guoxuan Xia, Sangwon Ha, Tiago Azevedo, Partha Maji