Ziyou Jiang
8 papers · 2021–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (13) π Conference Polyglot (3) π Academic Marathon (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (14)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
β
The Questioner
Conferences
ACL (3)
EMNLP (2)
IJCAI (2)
EACL (1)
Top co-authors
Keywords
dialogue disentanglement
(2)
adversarial attack
(2)
text classification
(1)
multimodal learning
(1)
video understanding
(1)
intent classification
(1)
software engineering
(1)
mixture of expert
(1)
multimodal large language model
(1)
retrieval-augmented generation
(1)
tool agent
(1)
mutual learning
(1)
privacy breach
(1)
error analysis
(1)
input perturbation
(1)
hate speech detection
(1)
security vulnerability
(1)
conversation analysis
(1)
large language model
(1)
harmful meme detection
(1)
Papers
SAGE: Synergistic Adaptive Gating of Experts for Hateful Video Detection
ACL 2026
All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction
ACL 2026
Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in LLMs
EACL 2026
Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System
ACL 2025
Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems
EMNLP 2025
One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
EMNLP 2025
MuiDial: Improving Dialogue Disentanglement with Intent-Based Mutual Learning
IJCAI 2022
Dialogue Disentanglement in Software Engineering: How Far are We?
IJCAI 2021