Zexin Li
8 papers · 2023–2026 · 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
(24)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Artificial Intelligence
(8)
Core AI
(8)
Machine Learning
(4)
Natural Language Processing
(4)
Deep Learning
(3)
Learning Types · Machine Learning
(3)
Learning Types · Deep Learning
(3)
Application Areas
(2)
Generation
(2)
Resources & Methods
(2)
Computer Vision
(1)
Speech & Audio
(1)
Analysis · Speech & Audio
(1)
Analysis · Computer Vision
(1)
Applications
(1)
Keywords
large language model
(4)
adversarial attack
(3)
transfer learning
(1)
text editing
(1)
dialogue generation
(1)
text generation
(1)
instruction following
(1)
black-box attack
(1)
efficient computing
(1)
early exit
(1)
speech classification
(1)
attribute recognition
(1)
multi-objective optimization
(1)
backdoor attack
(1)
face recognition
(1)
domain adaptation
(1)
latent representation
(1)
normalizing flow
(1)
computational cost
(1)
multi-task learning
(1)
Papers
NaturalSloth: Revisiting Denial-of-Service Attacks on Large Language Models
ACL 2026
Policy Search, Retrieval, and Composition via Task Similarity in Collaborative Agentic Systems
AAAI 2026
Benchmarking Large Language Models Under Data Contamination: A Survey from Static to Dynamic Evaluation
EMNLP 2025
Bridging the Editing Gap in LLMs: FineEdit for Precise and Targeted Text Modifications
EMNLP 2025
LRBA: Stealthy Backdoor Attacks on Speech Classification via Latent Rearrangement in VITS
Interspeech 2025
Dynamic Transformers Provide a False Sense of Efficiency
ACL 2023
Sibling-Attack: Rethinking Transferable Adversarial Attacks Against Face Recognition
CVPR 2023
White-Box Multi-Objective Adversarial Attack on Dialogue Generation
ACL 2023