Xinyu Luo
4 papers · 2023–2025 · 3 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Silver
๐บ๏ธ
Taxonomy Completionist
(13)
Top co-authors
Research topics
Keywords
dimensionality reduction
(1)
entropy minimization
(1)
test-time adaptation
(1)
medical image segmentation
(1)
reinforcement learning from human feedback
(1)
gaussian kernel
(1)
kernel density estimation
(1)
gaussian mixture model
(1)
approximation algorithm
(1)
mixture model
(1)
randomized algorithm
(1)
latent variable
(1)
foundation model
(1)
test-time alignment
(1)
speculative sampling
(1)
conditional random field
(1)
mode finding
(1)
reward shifting
(1)
weak-to-strong alignment
(1)
sgd
(1)
Papers
Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner
EMNLP 2025
Stacey: Promoting Stochastic Steepest Descent via Accelerated โ_p-Smooth Nonconvex Optimization
ICML 2025
Test-time Adaptation for Foundation Medical Segmentation Model Without Parametric Updates
ICCV 2025
Dimensionality Reduction for General KDE Mode Finding
ICML 2023