Lin Lu
9 papers · 2024–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (6) π Cross-Pollinator (5) π Renaissance Researcher (7)
πΊοΈ
Taxonomy Completionist
(20)
Conferences
ACL (2)
EMNLP (2)
ICCV (1)
ICLR (1)
ICML (1)
MIDL (1)
NIPS (1)
Top co-authors
Research topics
Keywords
large language model
(3)
decision making
(1)
adversarial attack
(1)
vision-language alignment
(1)
cross-modal retrieval
(1)
model merging
(1)
neural network optimization
(1)
ai safety
(1)
synthetic data generation
(1)
model alignment
(1)
gradient descent
(1)
constraint satisfaction
(1)
sequential decision
(1)
backdoor attack
(1)
attention mechanism
(1)
sample selection
(1)
real-time decision-making
(1)
predictive inference
(1)
sequential analysis
(1)
online learning
(1)
Papers
SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator
ACL 2026
HiPro-CT: A Hierarchical Probabilistic Framework for 3D Medical Vision-Language Alignment
MIDL 2026
Merger-as-a-Stealer: Stealing Targeted PII from Aligned LLMs with Model Merging
EMNLP 2025
Conditional Testing based on Localized Conformal $p$-values
ICLR 2025
GFPack++: Attention-Driven Gradient Fields for Optimizing 2D Irregular Packing
ICCV 2025
Stealing Training Data from Large Language Models in Decentralized Training through Activation Inversion Attack
ACL 2025
Position: Exploring the Robustness of Pipeline-Parallelism-Based Decentralized Training
ICML 2024
Real-Time Selection Under General Constraints via Predictive Inference
NIPS 2024
Virtual Context Enhancing Jailbreak Attacks with Special Token Injection
EMNLP 2024