Lijun Li
17 papers · 2019–2026 · 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 ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (38) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π€
Dynamic Duo
(12)
π§¬
Topic Evolution
π
Renaissance Researcher
(6)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(86)
Top co-authors
Research topics
Artificial Intelligence
(13)
Core AI
(13)
Machine Learning
(8)
Deep Learning
(5)
Application Areas
(5)
Learning Types Β· Machine Learning
(5)
Computer Vision
(3)
Mathematics & Optimization
(3)
Natural Language Processing
(3)
Optimization
(3)
Security & Privacy
(2)
Generation
(2)
Learning Types Β· Deep Learning
(2)
Models
(2)
Privacy
(2)
Keywords
large language model
(4)
attack success rate
(3)
adversarial attack
(3)
jailbreak attack
(3)
approximation algorithm
(3)
safety alignment
(2)
safety benchmark
(2)
multimodal large language model
(2)
bias detection
(1)
harmful content
(1)
text summarization
(1)
data augmentation
(1)
value function
(1)
submodular maximization
(1)
ai safety
(1)
llm evaluation
(1)
toxicity detection
(1)
diffusion model
(1)
greedy algorithm
(1)
model safety
(1)
Papers
Evolutionary Guided Decoding: Iterative Value Refinement for LLMs
ACL 2026
HarmRLVR: Weaponizing Verifiable Rewards for Harmful LLM Alignment
ACL 2026
Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models
AAAI 2026
SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents
ACL 2026
TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration
CVPR 2026
Fair Submodular Maximization over a Knapsack Constraint
IJCAI 2025
Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment
EMNLP 2025
Self-adaptive Dataset Construction for Real-World Multimodal Safety Scenarios
EMNLP 2025
T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation
CVPR 2025
Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection
EMNLP 2025
WorldSimBench: Towards Video Generation Models as World Simulators
ICML 2025
PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety
ACL 2024
Public Event Scheduling with Busy Agents
IJCAI 2024
SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models
ACL 2024
RenderIH: A Large-Scale Synthetic Dataset for 3D Interacting Hand Pose Estimation
ICCV 2023
Approximate Group Fairness for Clustering
ICML 2021
NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks
ICML 2019