Kaizhao Liang
9 papers · 2020–2024 · 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Silver
๐บ๏ธ
Taxonomy Completionist
(22)
๐ฅ
Unstoppable ยท Bronze
๐๏ธ
Keyword Collector
(53)
Venues
Top co-authors
Research topics
Machine Learning
(8)
Artificial Intelligence
(5)
Application Areas
(5)
Optimization & Theory
(5)
Core AI
(4)
Deep Learning
(3)
Learning Types
(3)
Natural Language Processing
(2)
Models
(2)
Computer Vision
(1)
Mathematics & Optimization
(1)
Applications
(1)
Architectures
(1)
Core Methods
(1)
Domain-Specific
(1)
Keywords
model compression
(3)
neural network optimization
(2)
stochastic gradient descent
(1)
vision transformer
(1)
adversarial robustness
(1)
variational inference
(1)
domain adaptation
(1)
autonomous driving
(1)
scene understanding
(1)
knowledge distillation
(1)
question answering
(1)
text generation
(1)
language modeling
(1)
multimodal learning
(1)
transfer learning
(1)
adversarial learning
(1)
constrained optimization
(1)
lyapunov function
(1)
mutual information
(1)
image classification
(1)
Papers
Communication Efficient Distributed Training with Distributed Lion
NeurIPS 2024
Lion Secretly Solves a Constrained Optimization: As Lyapunov Predicts
ICLR 2024
MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene Understanding
CVPR 2024
Memory-Efficient LLM Training with Online Subspace Descent
NeurIPS 2024
A Unified Knowledge Distillation Framework for Deep Directed Graphical Models
CVPR 2023
Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models
ICLR 2022
Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability
ICML 2021
Adversarial Mutual Information for Text Generation
ICML 2020
Unrestricted Adversarial Examples via Semantic Manipulation
ICLR 2020