Chengyu Dong
14 papers · 2020–2024 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
๐ Interdisciplinary Bridge ๐ Cross-Pollinator (13) ๐งญ Keyword Pioneer ๐ Conference Polyglot (6) ๐บ๏ธ Taxonomy Completionist (28)
๐
Conference Polyglot
(6)
๐ค
Dynamic Duo
(13)
๐ฅ
Unstoppable
(5)
๐
Century Club
(14)
โก
Prolific Year
(5)
๐๏ธ
Keyword Collector
(64)
โ
The Questioner
Conferences
EMNLP (6)
ICLR (2)
ICML (2)
NIPS (2)
ACL (1)
ICCV (1)
Top co-authors
Keywords
text classification
(4)
weakly supervised learning
(3)
representation learning
(2)
adversarial training
(2)
large language model
(2)
text generation
(2)
pre-trained language model
(2)
weak supervision
(2)
principal component analysis
(1)
zero-shot learning
(1)
knowledge distillation
(1)
prompt engineering
(1)
self-supervised learning
(1)
data poisoning
(1)
model calibration
(1)
machine unlearning
(1)
pseudo labeling
(1)
neural network optimization
(1)
label noise
(1)
feature selection
(1)
Papers
Toward Student-oriented Teacher Network Training for Knowledge Distillation
ICLR 2024
Text Grafting: Near-Distribution Weak Supervision for Minority Classes in Text Classification
EMNLP 2024
Evaluating the Smooth Control of Attribute Intensity in Text Generation with LLMs
ACL 2024
Fast-ELECTRA for Efficient Pre-training
ICLR 2024
Understand and Modularize Generator Optimization in ELECTRA-style Pretraining
ICML 2023
Bridging Discrete and Backpropagation: Straight-Through and Beyond
NIPS 2023
Debiasing Made State-of-the-art: Revisiting the Simple Seed-based Weak Supervision for Text Classification
EMNLP 2023
SELFOOD: Self-Supervised Out-Of-Distribution Detection via Learning to Rank
EMNLP 2023
Learning Concise and Descriptive Attributes for Visual Recognition
ICCV 2023
Label Noise in Adversarial Training: A Novel Perspective to Study Robust Overfitting
NIPS 2022
LOPS: Learning Order Inspired Pseudo-Label Selection for Weakly Supervised Text Classification
EMNLP 2022
BFClass: A Backdoor-free Text Classification Framework
EMNLP 2021
โAverageโ Approximates โFirst Principal Componentโ? An Empirical Analysis on Representations from Neural Language Models
EMNLP 2021
Towards Adaptive Residual Network Training: A Neural-ODE Perspective
ICML 2020