Xiaodan Song
9 papers · 2020–2022 · 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(18)
🐣
Hot Topic Early Bird
⚡
Prolific Year · Productive
Top co-authors
Research topics
Machine Learning
(6)
Deep Learning
(5)
Application Areas
(4)
Architectures
(4)
Artificial Intelligence
(2)
Core AI
(2)
Learning Types
(2)
Optimization & Theory · Deep Learning
(2)
Optimization & Theory · Machine Learning
(2)
Techniques
(2)
Computer Vision
(1)
Natural Language Processing
(1)
Analysis
(1)
Resources & Methods
(1)
Keywords
model compression
(3)
bert pretraining
(2)
transfer learning
(2)
knowledge distillation
(2)
neural architecture search
(2)
object detection
(2)
natural language inference
(1)
question answering
(1)
convergence analysis
(1)
deep learning
(1)
neural network optimization
(1)
efficient computing
(1)
computational efficiency
(1)
model scaling
(1)
pre-trained language model
(1)
multi-scale feature
(1)
mobile deployment
(1)
model optimization
(1)
backbone model
(1)
masked language modeling
(1)
Papers
A Simple Single-Scale Vision Transformer for Object Detection and Instance Segmentation
ECCV 2022
Auto-scaling Vision Transformers without Training
ICLR 2022
Token Dropping for Efficient BERT Pretraining
ACL 2022
BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models
ECCV 2020
Efficient Scale-Permuted Backbone with Learned Resource Distribution
ECCV 2020
Go Wide, Then Narrow: Efficient Training of Deep Thin Networks
ICML 2020
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
ICLR 2020
MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices
ACL 2020
SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
CVPR 2020