Guoxuan Xia

6 papers · 2023–2025 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (14)

Venues

UAI (2) CVPR (1) ICCV (1) ICLR (1) NeurIPS (1)

Top co-authors

Christos-Savvas Bouganis (2) Gianni Franchi (2) Dat Nguyen Trong (1) Eliot Wong-Toi (1) Guy-Bart Stan (1) Stephan Mandt (1) Metod Jazbec (1) Olivier Laurent (1) Andrea Pilzer (1) Dan Zhang (1)

Research topics

Deep Learning (5) Machine Learning (4) Artificial Intelligence (3) Core AI (3) Models (3) Bayesian & Probabilistic (2) Core Methods (2) Optimization & Theory (2) Techniques (2) Healthcare & Medicine (1) Application Areas (1) Research (1)

Keywords

diffusion model (3) uncertainty quantification (2) uncertainty estimation (2) selective classification (2) flow matching (1) neural network optimization (1) label smoothing (1) laplace approximation (1) early exit (1) generative model (1) autoregressive model (1) out-of-distribution detection (1) genomic sequence (1) compositional generation (1) dna synthesis (1) large vision-language model (1) aleatoric uncertainty (1) model efficiency (1) dna sequence (1) gradient analysis (1)

Papers

Generative Uncertainty in Diffusion Models UAI 2025 Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation CVPR 2025 Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It ICLR 2025 Absorb & Escape: Overcoming Single Model Limitations in Generating Heterogeneous Genomic Sequences NeurIPS 2024 Logit-based ensemble distribution distillation for robust autoregressive sequence uncertainties UAI 2023 Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models ICCV 2023