Zhouxing Shi
13 papers · 2019–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (23) π Academic Marathon (5) π Interdisciplinary Bridge π Conference Polyglot (6) π§ Keyword Pioneer
π
Academic Marathon
(5)
π€
Dynamic Duo
(10)
π
Grand Slam
π§¬
Topic Evolution
π₯
Unstoppable
(6)
π
Century Club
(12)
π
Conference Pioneer
Conferences
NIPS (4)
ACL (3)
ICLR (3)
AAAI (1)
EMNLP (1)
ICML (1)
Top co-authors
Keywords
adversarial robustness
(3)
large language model
(2)
certified robustness
(2)
natural language processing
(2)
adversarial training
(2)
neural network verification
(2)
stability analysis
(1)
deep learning
(1)
text classification
(1)
preference optimization
(1)
masked language model
(1)
domain generalization
(1)
batch normalization
(1)
model interpretability
(1)
sensitivity analysis
(1)
perturbation analysis
(1)
sequential model
(1)
distribution shift
(1)
weight initialization
(1)
model robustness
(1)
Papers
From Individual to Common: An Early Exploration of Consensus in Non-verifiable Data for Balanced Preference Optimization
ACL 2026
Defending LLMs against Jailbreaking Attacks via Backtranslation
ACL 2024
Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation
ICML 2024
Effective Robustness against Natural Distribution Shifts for Models with Different Training Data
NIPS 2023
Towards Robustness Certification Against Universal Perturbations
ICLR 2023
Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation
NIPS 2022
On the Sensitivity and Stability of Model Interpretations in NLP
ACL 2022
On the Convergence of Certified Robust Training with Interval Bound Propagation
ICLR 2022
Fast Certified Robust Training with Short Warmup
NIPS 2021
Robustness Verification for Transformers
ICLR 2020
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
NIPS 2020
Robustness to Modification with Shared Words in Paraphrase Identification
EMNLP 2020
A Deep Sequential Model for Discourse Parsing on Multi-Party Dialogues
AAAI 2019