Mingi Ji
9 papers · 2019–2024 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Cross-Pollinator (15) π Academic Marathon (5) π Renaissance Researcher (6) π Interdisciplinary Bridge
π
Conference Polyglot
(5)
πΊοΈ
Taxonomy Completionist
(28)
π§
Keyword Pioneer
π
Trend Setter
π
Conference Pioneer
Conferences
AAAI (5)
CVPR (1)
EMNLP (1)
ICML (1)
NIPS (1)
Top co-authors
Keywords
knowledge distillation
(3)
model compression
(3)
sequential recommendation
(2)
adversarial learning
(2)
recurrent neural network
(2)
attention mechanism
(2)
text classification
(1)
transfer learning
(1)
semantic segmentation
(1)
mixture of expert
(1)
feature matching
(1)
parameter efficient
(1)
dropout regularization
(1)
sequential datum
(1)
language modeling
(1)
latent space
(1)
language model
(1)
self-supervised learning
(1)
self-attention mechanism
(1)
feature alignment
(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
Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation
NIPS 2022
BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents
AAAI 2022
Show, Attend and Distill: Knowledge Distillation via Attention-based Feature Matching
AAAI 2021
Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation
CVPR 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