Xuechen Zhang
9 papers · 2021–2025 · 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(24)
🐣
Hot Topic Early Bird
🗃️
Keyword Collector
(58)
Venues
Top co-authors
Research topics
Machine Learning
(7)
Optimization & Theory
(5)
Artificial Intelligence
(4)
Application Areas
(4)
Core AI
(4)
Deep Learning
(3)
Core Methods
(3)
Learning Types · Deep Learning
(3)
Natural Language Processing
(2)
Architectures
(2)
Techniques
(2)
Reinforcement Learning
(1)
Generation
(1)
Learning Types · Machine Learning
(1)
Methods
(1)
Keywords
attention mechanism
(3)
language modeling
(2)
transformer architecture
(2)
support vector machine
(2)
universal approximation
(1)
data augmentation
(1)
reinforcement learning
(1)
bilevel optimization
(1)
manifold learning
(1)
sample complexity
(1)
token selection
(1)
policy learning
(1)
transformer
(1)
selective attention
(1)
distribution shift
(1)
gradient descent
(1)
probability density
(1)
score matching
(1)
in-context learning
(1)
model selection
(1)
Papers
On the Power of Convolution-Augmented Transformer
AAAI 2025
Test-Time Training Provably Improves Transformers as In-context Learners
ICML 2025
A Score-Based Deterministic Diffusion Algorithm with Smooth Scores for General Distributions
AAAI 2024
Class-Attribute Priors: Adapting Optimization to Heterogeneity and Fairness Objective
AAAI 2024
Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning
NeurIPS 2024
Selective Attention: Enhancing Transformer through Principled Context Control
NeurIPS 2024
Learning on Manifolds: Universal Approximations Properties using Geometric Controllability Conditions for Neural ODEs
L4DC 2023
Max-Margin Token Selection in Attention Mechanism
NeurIPS 2023
AutoBalance: Optimized Loss Functions for Imbalanced Data
NeurIPS 2021