Xuhong Zhang
26 papers · 2021–2026 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🐝 Cross-Pollinator (9) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (9) 🏃 Academic Marathon (5)
🌍
Conference Polyglot
(9)
🐝
Cross-Pollinator
(9)
🤝
Dynamic Duo
(11)
🏆
Keyword Champion
(3)
⚡
Prolific Year
(11)
🗃️
Keyword Collector
(124)
💎
Century Club
(22)
Conferences
AAAI (8)
ACL (4)
EMNLP (4)
ICLR (3)
IJCAI (3)
COLING (1)
ICCV (1)
NAACL (1)
WACV (1)
Top co-authors
Research topics
Keywords
large language model
(6)
code generation
(3)
retrieval-augmented generation
(3)
model protection
(3)
contrastive learning
(3)
information extraction
(2)
intellectual property
(2)
question answering
(2)
adversarial attack
(2)
in-context learning
(2)
model compression
(2)
intellectual property protection
(2)
knowledge distillation
(1)
object detection
(1)
zero-shot learning
(1)
image retrieval
(1)
text classification
(1)
reinforcement learning
(1)
differential privacy
(1)
transfer learning
(1)
Papers
Ground What You See: Hallucination-Resistant MLLMs via Caption Feedback, Diversity-Aware Sampling, and Conflict Regularization
AAAI 2026
Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Merging
AAAI 2026
RAGFort: Dual-Path Defense Against Proprietary Knowledge Base Extraction in Retrieval-Augmented Generation
AAAI 2026
HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors
AAAI 2026
Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks
ACL 2025
An Inversion-based Measure of Memorization for Diffusion Models
ICCV 2025
Uncovering LLM-Generated Code: A Zero-Shot Synthetic Code Detector via Code Rewriting
AAAI 2025
DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models
AAAI 2025
MEraser: An Effective Fingerprint Erasure Approach for Large Language Models
ACL 2025
CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing
EMNLP 2025
Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
ICLR 2025
Tool-Planner: Task Planning with Clusters across Multiple Tools
ICLR 2025
CollabEdit: Towards Non-destructive Collaborative Knowledge Editing
ICLR 2025
Scalable Multi-Stage Influence Function for Large Language Models via Eigenvalue-Corrected Kronecker-Factored Parameterization
IJCAI 2025
Multi-Resolution Guided 3D GANs for Medical Image Translation
WACV 2025
Knowledge Triplets Derivation from Scientific Publications via Dual-Graph Resonance
COLING 2024
RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback
ACL 2024
Pluggable Watermarking of Deepfake Models for Deepfake Detection
IJCAI 2024
Protecting Object Detection Models from Model Extraction Attack via Feature Space Coverage
IJCAI 2024
ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis
ACL 2024
Let All Be Whitened: Multi-Teacher Distillation for Efficient Visual Retrieval
AAAI 2024
AdaCCD: Adaptive Semantic Contrasts Discovery Based Cross Lingual Adaptation for Code Clone Detection
AAAI 2024
SecCoder: Towards Generalizable and Robust Secure Code Generation
EMNLP 2024
Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization
NAACL 2024
CP-BCS: Binary Code Summarization Guided by Control Flow Graph and Pseudo Code
EMNLP 2023
Constructing contrastive samples via summarization for text classification with limited annotations
EMNLP 2021