Yepeng Liu
9 papers · 2023–2026 · 6 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (19) 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer
🚀
Conference Pioneer
Top co-authors
Research topics
Artificial Intelligence
(6)
Core AI
(6)
Machine Learning
(4)
Deep Learning
(3)
Computer Vision
(2)
Natural Language Processing
(2)
Application Areas
(2)
Techniques
(2)
Analysis
(1)
Applications
(1)
Architectures
(1)
Core Methods
(1)
Generation · Natural Language Processing
(1)
Generation · Computer Vision
(1)
Models
(1)
Keywords
reinforcement learning
(2)
trojan attack
(2)
model security
(1)
robustness
(1)
text classification
(1)
policy gradient
(1)
image matching
(1)
model pruning
(1)
entropy
(1)
adversarial attack
(1)
black-box attack
(1)
diffusion model
(1)
semantic embedding
(1)
reward hacking
(1)
computational cost
(1)
prompt injection
(1)
poisoned sample
(1)
token merging
(1)
keypoint detection
(1)
compression rate
(1)
Papers
A Reinforcement Learning Framework for Robust and Secure LLM Watermarking
EACL 2026
From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection
CVPR 2026
Image Watermarks are Removable using Controllable Regeneration from Clean Noise
ICLR 2025
Adaptive Text Watermark for Large Language Models
ICML 2024
MLIP: Efficient Multi-Perspective Language-Image Pretraining with Exhaustive Data Utilization
ICML 2024
Position-Guided Prompt Learning for Anomaly Detection in Chest X-Rays
MICCAI 2024
MG-ViT: A Multi-Granularity Method for Compact and Efficient Vision Transformers
NeurIPS 2023
TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models
NeurIPS 2023
TrojText: Test-time Invisible Textual Trojan Insertion
ICLR 2023