Yilun Xu
17 papers · 2019–2025 · 4 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 ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (25) π Academic Marathon Β· Sprint π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Triple Crown
π§¬
Topic Evolution
π₯
Unstoppable Β· Bronze
β
The Questioner
ποΈ
Keyword Collector
(73)
π
Century Club Β· Bronze
Venues
Top co-authors
Research topics
Deep Learning
(13)
Machine Learning
(11)
Models
(11)
Optimization & Theory
(7)
Core Methods
(5)
Computer Vision
(3)
Generation Β· Computer Vision
(3)
Application Areas
(2)
Learning Types Β· Deep Learning
(2)
Learning Types Β· Machine Learning
(2)
Artificial Intelligence
(1)
Natural Language Processing
(1)
Architectures
(1)
Core AI
(1)
Generation Β· Natural Language Processing
(1)
Keywords
diffusion model
(6)
image generation
(3)
language modeling
(2)
poisson flow
(2)
mutual information
(2)
generative model
(2)
ordinary differential equation
(2)
energy-based model
(2)
text generation
(2)
principal component analysis
(1)
flow matching
(1)
diverse sampling
(1)
out-of-distribution generalization
(1)
orthogonal decomposition
(1)
domain adaptation
(1)
lottery ticket hypothesis
(1)
text-to-image generation
(1)
score matching
(1)
autoregressive transformer
(1)
variance reduction
(1)
Papers
Energy-Based Diffusion Language Models for Text Generation
ICLR 2025
Heavy-Tailed Diffusion Models
ICLR 2025
Think while You Generate: Discrete Diffusion with Planned Denoising
ICLR 2025
Truncated Consistency Models
ICLR 2025
DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents
ICML 2024
Hamiltonian Score Matching and Generative Flows
NeurIPS 2024
Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models
ICLR 2024
PFGM++: Unlocking the Potential of Physics-Inspired Generative Models
ICML 2023
Restart Sampling for Improving Generative Processes
NeurIPS 2023
Stable Target Field for Reduced Variance Score Estimation in Diffusion Models
ICLR 2023
Controlling Directions Orthogonal to a Classifier
ICLR 2022
Poisson Flow Generative Models
NeurIPS 2022
Anytime Sampling for Autoregressive Models via Ordered Autoencoding
ICLR 2021
Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization?
ICML 2021
A Theory of Usable Information under Computational Constraints
ICLR 2020
TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning
ECCV 2020
L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise
NeurIPS 2019