Geguang Pu
8 papers · 2017–2025 · 4 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 ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (26) π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Gold π Academic Marathon Β· Sprint 𧬠Topic Evolution
π§
Keyword Pioneer
ποΈ
Keyword Collector
(52)
π
Conference Pioneer
π
Renaissance Researcher
(5)
π
Trend Setter
Top co-authors
Research topics
Artificial Intelligence
(5)
Core AI
(5)
Deep Learning
(4)
Machine Learning
(4)
Mathematics & Optimization
(4)
Knowledge & Reasoning
(3)
Learning Types Β· Machine Learning
(3)
Learning Types Β· Deep Learning
(3)
Optimization
(3)
Reasoning
(3)
Computer Science
(2)
Computer Vision
(2)
Foundations
(2)
Models
(2)
Analysis
(1)
Keywords
linear temporal logic
(3)
finite trace
(3)
adversarial attack
(2)
formal verification
(2)
deterministic finite automaton
(2)
concept learning
(1)
symbolic computation
(1)
few-shot learning
(1)
diffusion model
(1)
optimization algorithm
(1)
prompt engineering
(1)
language model
(1)
text-to-image model
(1)
text-to-image diffusion
(1)
adversarial prompt
(1)
jailbreak attack
(1)
latent diffusion
(1)
prompt optimization
(1)
prompt injection
(1)
backdoor attack
(1)
Papers
Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization
ACL 2025
Perception-Guided Jailbreak Against Text-to-Image Models
AAAI 2025
CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection
CVPR 2024
Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models
AAAI 2024
On-the-fly Synthesis for LTL over Finite Traces
AAAI 2021
LTLΖ Synthesis with Fairness and Stability Assumptions
AAAI 2020
SAT-Based Explicit LTLf Satisfiability Checking
AAAI 2019
Symbolic LTLf Synthesis
IJCAI 2017