Peiyu Yu
7 papers · 2021–2026 · 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 ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(16)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Deep Learning
(5)
Models
(4)
Computer Vision
(3)
Machine Learning
(3)
Learning Types · Machine Learning
(3)
Processing
(3)
Artificial Intelligence
(2)
Learning Types · Deep Learning
(2)
Bayesian & Probabilistic
(1)
Core AI · Computer Vision
(1)
Core AI · Artificial Intelligence
(1)
Core Methods
(1)
Generation
(1)
Optimization & Theory
(1)
Keywords
energy-based model
(3)
generative model
(2)
latent diffusion
(2)
diffusion model
(2)
variational inference
(1)
foreground extraction
(1)
policy gradient
(1)
text generation
(1)
expectation maximization
(1)
image editing
(1)
text-to-image generation
(1)
instruction following
(1)
flow matching
(1)
markov chain monte carlo
(1)
image super-resolution
(1)
james-stein estimator
(1)
linear inverse problem
(1)
latent space
(1)
text-to-image model
(1)
mixture of expert
(1)
Papers
Designing Instance-Level Sampling Schedules via REINFORCE with James-Stein Shrinkage
CVPR 2026
Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching
NeurIPS 2024
Object-Conditioned Energy-Based Attention Map Alignment in Text-to-Image Diffusion Models
ECCV 2024
UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
NeurIPS 2024
Learning Energy-Based Prior Model with Diffusion-Amortized MCMC
NeurIPS 2023
Latent Diffusion Energy-Based Model for Interpretable Text Modelling
ICML 2022
Unsupervised Foreground Extraction via Deep Region Competition
NeurIPS 2021