Xin Yi

Affiliations:
  • East China Normal University (ECNU), Lab of Artificial Intelligence for Education, School of Computer Science and Technology, China


According to our database1, Xin Yi authored at least 12 papers between 2024 and 2026.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2026
Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks.
Expert Syst. Appl., 2026

2025
From Evaluation to Defense: Constructing Persistent Edit-Based Fingerprints for Large Language Models.
CoRR, September, 2025

Unified Attacks to Large Language Model Watermarks: Spoofing and Scrubbing in Unauthorized Knowledge Distillation.
CoRR, April, 2025

Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks.
CoRR, January, 2025

Unified attacks to large language model watermarks: Spoofing and scrubbing in unauthorized knowledge distillation.
Knowl. Based Syst., 2025

Fine-grained detoxification framework via instance-level prefixes for large language models.
Neurocomputing, 2025

Verbalization diversification for relation extraction with long-tailed entity augmentation.
Neurocomputing, 2025

Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024
A safety realignment framework via subspace-oriented model fusion for large language models.
Knowl. Based Syst., 2024

Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models.
CoRR, 2024

Scenarios-aware Commonsense Correcton via Instance-level Knowledge Injection.
Proceedings of the Database Systems for Advanced Applications, 2024


  Loading...