Kaiyuan Zhang
19 papers · 2019–2026 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Interdisciplinary Bridge π Academic Marathon (6) π Renaissance Researcher (7) π Conference Polyglot (9) πΊοΈ Taxonomy Completionist (36)
πΊοΈ
Taxonomy Completionist
(36)
π§
Keyword Pioneer
π
Grand Slam
π€
Dynamic Duo
(12)
β‘
Prolific Year
(5)
π
Century Club
(18)
π
Trend Setter
ποΈ
Keyword Collector
(77)
Conferences
EMNLP (5)
NIPS (4)
ACL (2)
CVPR (2)
NSDI (2)
AAAI (1)
ECCV (1)
ICLR (1)
ICML (1)
Top co-authors
Research topics
Keywords
large language model
(6)
backdoor attack
(4)
backdoor detection
(3)
word sense disambiguation
(3)
adversarial learning
(3)
model security
(2)
natural language processing
(2)
ai-generated text detection
(2)
object detection
(1)
preference optimization
(1)
text classification
(1)
model safety
(1)
evaluation framework
(1)
formal verification
(1)
information retrieval
(1)
lexical semantics
(1)
kernel optimization
(1)
distribution shift
(1)
source code
(1)
binary analysis
(1)
Papers
WSDPO: A Generative Word Sense Disambiguation Framework with Chain-of-Thought and Preference Optimization
ACL 2026
RoDEval: A Robust Word Sense Disambiguation Evaluation Framework for Large Language Models
EMNLP 2025
System Prompt Hijacking via Permutation Triggers in LLM Supply Chains
ACL 2025
MADAWSD: Multi-Agent Debate Framework for Adversarial Word Sense Disambiguation
EMNLP 2025
Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis
EMNLP 2025
MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation
EMNLP 2025
Equipping Retrieval-Augmented Large Language Models with Document Structure Awareness
EMNLP 2025
ProSec: Fortifying Code LLMs with Proactive Security Alignment
ICML 2025
LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
CVPR 2024
BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens
NIPS 2024
Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases
NIPS 2024
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
AAAI 2024
UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening
ECCV 2024
Detecting Backdoors in Pre-Trained Encoders
CVPR 2023
Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration
NIPS 2023
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
ICLR 2023
ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP
NIPS 2023
Automated Verification of Customizable Middlebox Properties with Gravel
NSDI 2020
Slim: OS Kernel Support for a Low-Overhead Container Overlay Network
NSDI 2019