Sledovať
Chengyu Dong
Chengyu Dong
PhD student, UCSD
Overená e-mailová adresa na: eng.ucsd.edu - Domovská stránka
Názov
Citované v
Citované v
Rok
Learning concise and descriptive attributes for visual recognition
A Yan, Y Wang, Y Zhong, C Dong, Z He, Y Lu, WY Wang, J Shang, ...
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023
692023
Towards adaptive residual network training: A neural-ode perspective
C Dong, L Liu, Z Li, J Shang
International Conference on Machine Learning, 2616-2626, 2020
442020
Robust and interpretable medical image classifiers via concept bottleneck models
A Yan, Y Wang, Y Zhong, Z He, P Karypis, Z Wang, C Dong, A Gentili, ...
arXiv preprint arXiv:2310.03182, 2023
312023
Label Noise in Adversarial Training: A Novel Perspective to Study Robust Overfitting
C Dong, L Liu, J Shang
Advances in Neural Information Processing Systems (Oral) 35, 17556-17567, 2022
31*2022
Bfclass: A backdoor-free text classification framework
Z Li, D Mekala, C Dong, J Shang
The 2021 Conference on Empirical Methods in Natural Language Processing, 2021
272021
Bridging discrete and backpropagation: Straight-through and beyond
L Liu, C Dong, X Liu, B Yu, J Gao
Advances in Neural Information Processing Systems (Oral) 36, 2024
192024
LOPS: Learning order inspired pseudo-label selection for weakly supervised text classification
D Mekala, C Dong, J Shang
The 2022 Conference on Empirical Methods in Natural Language Processing, 2022
182022
Data quality matters for adversarial training: An empirical study
C Dong, L Liu, J Shang
arXiv preprint arXiv:2102.07437, 2021
16*2021
Toward student-oriented teacher network training for knowledge distillation
C Dong, L Liu, J Shang
arXiv preprint arXiv:2206.06661, 2022
11*2022
Perturbation Deterioration: The Other Side of Catastrophic Overfitting
Z Li, L Liu, C Dong, J Shang
6*
Debiasing made state-of-the-art: Revisiting the simple seed-based weak supervision for text classification
C Dong, Z Wang, J Shang
The 2023 Conference on Empirical Methods in Natural Language Processing, 2023
42023
" Average" Approximates" First Principal Component"? An Empirical Analysis on Representations from Neural Language Models
Z Wang, C Dong, J Shang
Proceedings of the 2021 Conference on Empirical Methods in Natural Language …, 2021
32021
Physics-informed data denoising for real-life sensing systems
X Zhang, X Fu, D Teng, C Dong, K Vijayakumar, J Zhang, RR Chowdhury, ...
Proceedings of the 21st ACM Conference on Embedded Networked Sensor Systems …, 2023
22023
Understand and modularize generator optimization in electra-style pretraining
C Dong, L Liu, H Cheng, J Shang, J Gao, X Liu
International Conference on Machine Learning, 8244-8259, 2023
22023
SELFOOD: Self-Supervised Out-Of-Distribution Detection via Learning to Rank
D Mekala, A Samavedhi, C Dong, J Shang
Findings of the Association for Computational Linguistics: EMNLP 2023, 2023
22023
Evaluating the Smooth Control of Attribute Intensity in Text Generation with LLMs
S Zhou, F Yao, C Dong, Z Wang, J Shang
Findings of the Association for Computational Linguistics: ACL 2024, 2024
12024
Fast-ELECTRA for Efficient Pre-training
C Dong, L Liu, H Cheng, J Shang, J Gao, X Liu
The Twelfth International Conference on Learning Representations, 2023
12023
Linear Correlation in LM's Compositional Generalization and Hallucination
L Peng, C An, S Hao, C Dong, J Shang
arXiv preprint arXiv:2502.04520, 2025
2025
Next-Token Prediction Task Assumes Optimal Data Ordering for LLM Training in Proof Generation
C An, S Imani, F Yao, C Dong, A Abbasi, H Shrivastava, S Buss, J Shang, ...
arXiv preprint arXiv:2411.00863, 2024
2024
Decoupled optimization of models during pretraining
X Liu, D Chengyu, L Liu, H Cheng, J Gao
US Patent App. 18/212,491, 2024
2024
Systém momentálne nemôže vykonať operáciu. Skúste to neskôr.
Články 1–20