Mingi Ji
9 papers · 2019–2024 · 5 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 ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze π Academic Marathon Β· Sprint πΊοΈ Taxonomy Completionist (25) π£ Hot Topic Early Bird π Conference Polyglot Β· Silver
π
Conference Pioneer
ποΈ
Keyword Collector
(51)
Venues
Top co-authors
Research topics
Deep Learning
(8)
Machine Learning
(8)
Application Areas
(5)
Architectures
(5)
Learning Types Β· Machine Learning
(4)
Learning Types Β· Deep Learning
(4)
Artificial Intelligence
(3)
Core AI
(2)
Core Methods
(2)
Optimization & Theory
(2)
Techniques
(2)
Computer Vision
(1)
Data Science & Analytics
(1)
Natural Language Processing
(1)
Analysis
(1)
Keywords
knowledge distillation
(3)
model compression
(3)
attention mechanism
(2)
adversarial learning
(2)
recurrent neural network
(2)
sequential recommendation
(2)
text classification
(1)
transfer learning
(1)
semantic segmentation
(1)
latent space
(1)
feature matching
(1)
parameter efficient
(1)
dynamic programming
(1)
dropout regularization
(1)
language modeling
(1)
pre-trained model
(1)
language model
(1)
sequential data
(1)
self-supervised learning
(1)
self-attention mechanism
(1)
Papers
Breaking ReLU Barrier: Generalized MoEfication for Dense Pretrained Models
EMNLP 2024
LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging
ICML 2024
BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents
AAAI 2022
Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation
NeurIPS 2022
Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation
CVPR 2021
Show, Attend and Distill: Knowledge Distillation via Attention-based Feature Matching
AAAI 2021
Sequential Recommendation with Relation-Aware Kernelized Self-Attention
AAAI 2020
Adversarial Dropout for Recurrent Neural Networks
AAAI 2019
Hierarchical Context Enabled Recurrent Neural Network for Recommendation
AAAI 2019