Yunfeng Diao
12 papers · 2021–2026 · 5 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 ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (30) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver ⚡ Prolific Year · Productive
💎
Century Club · Bronze
🗃️
Keyword Collector
(69)
Top co-authors
Research topics
Machine Learning
(9)
Learning Types · Machine Learning
(8)
Computer Vision
(6)
Deep Learning
(5)
Artificial Intelligence
(4)
Analysis
(4)
Models
(4)
Application Areas
(3)
Core AI
(3)
Core Methods
(2)
Learning Types · Deep Learning
(2)
Interdisciplinary
(1)
Natural Language Processing
(1)
Architectures
(1)
Bayesian & Probabilistic
(1)
Keywords
human activity recognition
(2)
skeletal action recognition
(2)
energy-based model
(2)
adversarial training
(2)
adversarial attack
(2)
robustness
(1)
bayesian learning
(1)
semantic segmentation
(1)
prompt-based learning
(1)
weakly supervised learning
(1)
action recognition
(1)
deepfake detection
(1)
machine unlearning
(1)
visual recognition
(1)
bayesian optimization
(1)
self-supervised learning
(1)
energy landscape
(1)
activity recognition
(1)
black-box attack
(1)
adversarial robustness
(1)
Papers
Beyond Fully Supervised Pixel Annotations: Scribble-Driven Weakly-Supervised Framework for Image Manipulation Localization
AAAI 2026
Layer Consistency Matters: Elegant Latent Transition Discrepancy for Generalizable Synthetic Image Detection
CVPR 2026
Uncovering and Mitigating Destructive Multi-Embedding Attacks in Deepfake Proactive Forensics
AAAI 2026
Your Classifier Can Do More: Towards Balancing the Gaps in Classification, Robustness, and Generation
CVPR 2026
Zero-shot Recommendation: Towards Class Semantic Relation Learning for Inferring Labels of Unseen Micro-videos
AAAI 2026
Moderating the Generalization of Score-based Generative Model
ICCV 2025
MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights
AAAI 2025
SafeMap: Robust HD Map Construction from Incomplete Observations
ICML 2025
Synergistic Prompting for Robust Visual Recognition with Missing Modalities
ICCV 2025
TASAR: Transfer-based Attack on Skeletal Action Recognition
ICLR 2025
Defending Black-Box Skeleton-Based Human Activity Classifiers
AAAI 2023
BASAR:Black-Box Attack on Skeletal Action Recognition
CVPR 2021