Zongru Wu
8 papers · 2024–2026 · 7 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
(13)
❓
The Questioner
⚡
Prolific Year · Productive
Top co-authors
Research topics
Keywords
backdoor attack
(3)
multimodal large language model
(3)
gui agent
(2)
frequency space
(2)
backdoor defense
(1)
knowledge transfer
(1)
knowledge editing
(1)
fourier analysis
(1)
gaussian mixture model
(1)
language model
(1)
multimodal agent
(1)
low-rank adaptation
(1)
out-of-distribution detection
(1)
multimodal reasoning
(1)
ood detection
(1)
min-max optimization
(1)
agent system
(1)
graphical user interface
(1)
knowledge neuron
(1)
generative language model
(1)
Papers
GEM: Gaussian Embedding Modeling for Out-of-Distribution Detection in GUI Agents
AAAI 2026
See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles
CVPR 2026
Can Knowledge be Transferred from Unimodal to Multimodal? Investigating the Transitivity of Multimodal Knowledge Editing
ICCV 2025
Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining
COLING 2025
Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents
EMNLP 2025
OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agents
ACL 2025
SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer
NAACL 2025
Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space
ACL 2024