Kai Mei
11 papers · 2022–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (12) π§ Keyword Pioneer π Conference Polyglot (7)
β‘
Prolific Year
(6)
π
Century Club
(11)
β
The Questioner
Conferences
ICLR (3)
ACL (2)
NIPS (2)
COLING (1)
EMNLP (1)
ICML (1)
NAACL (1)
Top co-authors
Keywords
large language model
(3)
backdoor attack
(2)
adversarial learning
(1)
model security
(1)
factual knowledge
(1)
prompt-based learning
(1)
autonomous driving
(1)
feature space
(1)
user modeling
(1)
human feedback
(1)
language model
(1)
domain expert
(1)
recommender system
(1)
memory management
(1)
backdoor detection
(1)
agent system
(1)
layer-wise representation
(1)
modular architecture
(1)
llm agent
(1)
artificial general intelligence
(1)
Papers
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
ICLR 2025
Cerebrum (AIOS SDK): A Platform for Agent Development, Deployment, Distribution, and Discovery
NAACL 2025
Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
ICML 2025
iAgent: LLM Agent as a Shield between User and Recommender Systems
ACL 2025
Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?
COLING 2025
From Commands to Prompts: LLM-based Semantic File System for AIOS
ICLR 2025
Learning Autonomous Driving Tasks via Human Feedbacks with Large Language Models
EMNLP 2024
UNICORN: A Unified Backdoor Trigger Inversion Framework
ICLR 2023
NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models
ACL 2023
OpenAGI: When LLM Meets Domain Experts
NIPS 2023
Rethinking the Reverse-engineering of Trojan Triggers
NIPS 2022