Mozhi Zhang
14 papers · 2019–2025 · 7 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 ↓+5 more ↓ Show less ↑
๐บ๏ธ Taxonomy Completionist (39) ๐ Interdisciplinary Bridge ยท Bronze ๐ Conference Polyglot ยท Silver ๐ Academic Marathon ยท Sprint ๐ฃ Hot Topic Early Bird
๐
Triple Crown
๐
Grand Slam
๐
Century Club ยท Bronze
๐๏ธ
Keyword Collector
(77)
โ
The Questioner
(3)
Top co-authors
Research topics
Deep Learning
(11)
Machine Learning
(11)
Artificial Intelligence
(10)
Core AI
(8)
Natural Language Processing
(7)
Resources & Methods
(6)
Learning Types ยท Machine Learning
(5)
Core Methods
(4)
Learning Types ยท Deep Learning
(4)
Application Areas
(3)
Architectures
(3)
Learning Paradigms
(3)
Optimization & Theory
(3)
Techniques
(3)
Applications
(2)
Keywords
large language model
(5)
graph neural network
(3)
reinforcement learning from human feedback
(3)
cross-lingual word embedding
(3)
inference-time alignment
(2)
text classification
(2)
low-resource language
(2)
direct preference optimization
(2)
natural language processing
(1)
in-context learning
(1)
transfer learning
(1)
cross-lingual transfer
(1)
text generation
(1)
sample complexity
(1)
representation learning
(1)
preference alignment
(1)
safety alignment
(1)
knowledge transfer
(1)
interactive learning
(1)
cross-lingual alignment
(1)
Papers
Domain2Vec: Vectorizing Datasets to Find the Optimal Data Mixture without Training
ICML 2025
LongSafety: Enhance Safety for Long-Context LLMs
ACL 2025
MetaAlign: Align Large Language Models with Diverse Preferences during Inference Time
NAACL 2025
Calibrating the Confidence of Large Language Models by Eliciting Fidelity
EMNLP 2024
InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance
EMNLP 2024
A Dataset and Baselines for Multilingual Reply Suggestion
ACL 2021
How does a Neural Network's Architecture Impact its Robustness to Noisy Labels?
NeurIPS 2021
How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
ICLR 2021
Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth
ICML 2021
Exploiting Cross-Lingual Subword Similarities in Low-Resource Document Classification
AAAI 2020
Interactive Refinement of Cross-Lingual Word Embeddings
EMNLP 2020
What Can Neural Networks Reason About?
ICLR 2020
Why Overfitting Isnโt Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries
ACL 2020
Are Girls Neko or Shลjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization
ACL 2019