Kaiyuan Zhang
20 papers · 2019–2026 · 10 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 ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (42) π Conference Polyglot Β· Gold π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze π€ Dynamic Duo (12)
π§¬
Topic Evolution
π
Grand Slam
ποΈ
Keyword Collector
(92)
β‘
Prolific Year Β· Productive
π
Renaissance Researcher
(6)
π
Trend Setter
π
Century Club Β· Bronze
Venues
Top co-authors
Research topics
Artificial Intelligence
(15)
Core AI
(14)
Machine Learning
(9)
Deep Learning
(6)
Natural Language Processing
(6)
Learning Types Β· Machine Learning
(6)
Application Areas
(5)
Applications
(4)
Learning Types Β· Deep Learning
(4)
Resources & Methods
(3)
Computer Science
(2)
Learning Paradigms
(2)
Systems
(2)
Understanding
(2)
Computer Vision
(1)
Keywords
large language model
(6)
backdoor attack
(5)
adversarial learning
(3)
word sense disambiguation
(3)
backdoor detection
(3)
model security
(2)
ai-generated text detection
(2)
natural language processing
(2)
preference optimization
(1)
lexical semantics
(1)
text classification
(1)
information retrieval
(1)
self-supervised learning
(1)
automatic speech recognition
(1)
transfer learning
(1)
binary analysis
(1)
formal verification
(1)
preference learning
(1)
source code
(1)
evaluation framework
(1)
Papers
WSDPO: A Generative Word Sense Disambiguation Framework with Chain-of-Thought and Preference Optimization
ACL 2026
CHSER: A Dataset and Case Study on Generative Speech Error Correction for Child ASR
Interspeech 2025
Equipping Retrieval-Augmented Large Language Models with Document Structure Awareness
EMNLP 2025
MADAWSD: Multi-Agent Debate Framework for Adversarial Word Sense Disambiguation
EMNLP 2025
MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation
EMNLP 2025
Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis
EMNLP 2025
ProSec: Fortifying Code LLMs with Proactive Security Alignment
ICML 2025
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
BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens
NeurIPS 2024
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
AAAI 2024
LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
CVPR 2024
Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases
NeurIPS 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
NeurIPS 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
NeurIPS 2023
Automated Verification of Customizable Middlebox Properties with Gravel
NSDI 2020
Slim: OS Kernel Support for a Low-Overhead Container Overlay Network
NSDI 2019