Weijie J Su
11 papers · 2022–2025 · 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 · Bronze
🗺️
Taxonomy Completionist
(25)
💎
Century Club · Bronze
🗃️
Keyword Collector
(60)
Top co-authors
Research topics
Machine Learning
(8)
Optimization & Theory · Machine Learning
(7)
Deep Learning
(5)
Artificial Intelligence
(4)
Core AI
(4)
Natural Language Processing
(3)
Mathematics & Optimization
(2)
Application Areas
(2)
Optimization & Theory · Deep Learning
(2)
Resources & Methods
(2)
Techniques
(2)
Applications
(1)
Learning Types · Deep Learning
(1)
Learning Types · Machine Learning
(1)
Mathematics
(1)
Keywords
neural collapse
(2)
differential privacy
(2)
stochastic gradient descent
(1)
calibration
(1)
em algorithm
(1)
logical reasoning
(1)
preference optimization
(1)
fair classification
(1)
model merging
(1)
language model alignment
(1)
sequence tagging
(1)
part-of-speech tagging
(1)
neural network optimization
(1)
reinforcement learning from human feedback
(1)
pretraining
(1)
named entity recognition
(1)
nash equilibrium
(1)
hypothesis testing
(1)
strongly convex
(1)
algorithmic fairness
(1)
Papers
Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic
ICLR 2025
Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment
ICLR 2025
Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach
ICML 2025
Towards Rationality in Language and Multimodal Agents: A Survey
NAACL 2025
A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners
EMNLP 2024
Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning
ICML 2024
Shifted Interpolation for Differential Privacy
ICML 2024
FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data
ICLR 2023
The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent
ICML 2023
An Unconstrained Layer-Peeled Perspective on Neural Collapse
ICLR 2022
Weighted Training for Cross-Task Learning
ICLR 2022