Junjian Li
6 papers · 2024–2026 · 4 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(10)
Venues
Top co-authors
Research topics
Machine Learning
(3)
Artificial Intelligence
(2)
Learning Types · Machine Learning
(2)
Computer Science
(1)
Deep Learning
(1)
Healthcare & Medicine
(1)
Security & Privacy
(1)
Applications
(1)
Clinical
(1)
Core AI
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory
(1)
Privacy
(1)
Techniques
(1)
Keywords
image classification
(2)
few-shot learning
(1)
wavelet transform
(1)
multiple instance learning
(1)
fourier transform
(1)
backdoor attack
(1)
vision-language model
(1)
frequency domain
(1)
whole slide image
(1)
backdoor detection
(1)
poisoned sample
(1)
pathology diagnosis
(1)
target label
(1)
model retraining
(1)
neural network
(1)
cosine transform
(1)
energy-based defense
(1)
top predictions
(1)
Papers
Universal-to-Specific: Dynamic Knowledge-Guided Multiple Instance Learning for Few-Shot Whole Slide Image Classification
CVPR 2026
Bipartite Patient-Modality Graph Learning with Event-Conditional Modelling of Censoring for Cancer Survival Prediction
MICCAI 2025
MiCo: Multiple Instance Learning with Context-Aware Clustering for Whole Slide Image Analysis
MICCAI 2025
VisNet: A Human Visual System Inspired Lightweight Dual-Path Network for Medical Images Denoising
MICCAI 2025
A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectives
AAAI 2024
Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining
ICML 2024