Yilun Xu
17 papers · 2019–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (14) π Conference Polyglot (4) π Academic Marathon (6) π Cross-Pollinator (13) π Interdisciplinary Bridge
π§
Keyword Pioneer
π
Triple Crown
β
The Questioner
π
Century Club
(17)
π₯
Unstoppable
(7)
Conferences
ICLR (9)
NIPS (4)
ICML (3)
ECCV (1)
Top co-authors
Keywords
poisson flow
(2)
diffusion model
(2)
generative model
(2)
ordinary differential equation
(2)
out-of-distribution generalization
(1)
mutual information
(1)
label noise
(1)
score matching
(1)
deep neural network
(1)
normalizing flow
(1)
loss function
(1)
stochastic differential equation
(1)
energy-based model
(1)
latent space
(1)
spurious correlation
(1)
generative flow
(1)
sampling algorithm
(1)
classification task
(1)
physics-inspired model
(1)
generative process
(1)
Papers
Truncated Consistency Models
ICLR 2025
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
Hamiltonian Score Matching and Generative Flows
NIPS 2024
Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models
ICLR 2024
DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents
ICML 2024
Stable Target Field for Reduced Variance Score Estimation in Diffusion Models
ICLR 2023
Restart Sampling for Improving Generative Processes
NIPS 2023
PFGM++: Unlocking the Potential of Physics-Inspired Generative Models
ICML 2023
Poisson Flow Generative Models
NIPS 2022
Controlling Directions Orthogonal to a Classifier
ICLR 2022
Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization?
ICML 2021
Anytime Sampling for Autoregressive Models via Ordered Autoencoding
ICLR 2021
TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning
ECCV 2020
A Theory of Usable Information under Computational Constraints
ICLR 2020
L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise
NIPS 2019