MINGZHI DONG
7 papers · 2020–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Academic Marathon (5) π Cross-Pollinator (12)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(25)
Conferences
NIPS (3)
ICLR (2)
CVPR (1)
ICML (1)
Top co-authors
Keywords
neural tangent kernel
(2)
reinforcement learning
(1)
metric learning
(1)
non-convex optimization
(1)
domain adaptation
(1)
video segmentation
(1)
model architecture
(1)
neural network optimization
(1)
efficient computing
(1)
computational efficiency
(1)
gradient descent
(1)
generalization bound
(1)
language model
(1)
long-tail distribution
(1)
long-tail domain knowledge
(1)
domain-specific pretraining
(1)
cluster-guided sparse expert
(1)
representation space
(1)
over-parameterized model
(1)
selective update
(1)
Papers
Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference
ICML 2025
Once Read is Enough: Domain-specific Pretraining-free Language Models with Cluster-guided Sparse Experts for Long-tail Domain Knowledge
NIPS 2024
Over-parameterized Model Optimization with Polyak-{\L}ojasiewicz Condition
ICLR 2023
Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models
NIPS 2023
Recursive Disentanglement Network
ICLR 2022
Dynamic Face Video Segmentation via Reinforcement Learning
CVPR 2020
Generalization Bound of Gradient Descent for Non-Convex Metric Learning
NIPS 2020