Daize Dong
6 papers · 2022–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(5)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(16)
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
EMNLP (2)
ACL (1)
ICML (1)
NAACL (1)
WACV (1)
Top co-authors
Keywords
mixture of expert
(3)
parameter efficiency
(3)
dynamic convolution
(2)
model compression
(2)
network pruning
(1)
neural network optimization
(1)
instruction tuning
(1)
parameter efficient
(1)
language model
(1)
data sampling
(1)
continual pre-training
(1)
adapter tuning
(1)
expert routing
(1)
sparse adapter
(1)
efficient fine-tuning
(1)
dynamic network
(1)
data mixing
(1)
large language model
(1)
token routing
(1)
sampling weight
(1)
Papers
Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts
NAACL 2025
LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-Training
EMNLP 2024
A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer
ICML 2024
PAD-Net: An Efficient Framework for Dynamic Networks
ACL 2023
SD-Conv: Towards the Parameter-Efficiency of Dynamic Convolution
WACV 2023
SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters
EMNLP 2022