Mingda Zhang
15 papers · 2017–2026 · 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 ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (38)
π§¬
Topic Evolution
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
ποΈ
Keyword Collector
(82)
Top co-authors
Research topics
Artificial Intelligence
(10)
Machine Learning
(10)
Core AI
(10)
Deep Learning
(7)
Learning Types Β· Machine Learning
(6)
Computer Vision
(5)
Learning Types Β· Deep Learning
(5)
Analysis
(4)
Application Areas
(4)
Natural Language Processing
(3)
Applications
(3)
Processing
(3)
Core Methods
(2)
Optimization & Theory
(2)
Techniques
(2)
Keywords
backdoor attack
(4)
multimodal learning
(3)
domain adaptation
(2)
external knowledge
(2)
transfer learning
(2)
visual question answering
(2)
visual reasoning
(2)
backdoor defense
(2)
video understanding
(2)
deep learning
(2)
multimodal large language model
(2)
object detection
(1)
few-shot learning
(1)
semi-supervised learning
(1)
image classification
(1)
domain generalization
(1)
named entity recognition
(1)
data poisoning
(1)
benchmark evaluation
(1)
weakly supervised learning
(1)
Papers
AdapAction: Adaptive Target Action Backdoor Attack against GUI Agents
CVPR 2026
Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
ICLR 2025
OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities
ICLR 2025
Scaling Inference Time Compute for Diffusion Models
CVPR 2025
VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models
ICLR 2024
VIEWS: Entity-Aware News Video Captioning
EMNLP 2024
How To Practice VQA on a Resource-Limited Target Domain
WACV 2023
Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
NeurIPS 2023
Train-Once-for-All Personalization
CVPR 2023
Video Timeline Modeling For News Story Understanding
NeurIPS 2023
BackdoorBench: A Comprehensive Benchmark of Backdoor Learning
NeurIPS 2022
Breaking Shortcuts by Masking for Robust Visual Reasoning
WACV 2021
Domain-Robust VQA With Diverse Datasets and Methods but No Target Labels
CVPR 2021
Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection
ICCV 2019
Automatic Understanding of Image and Video Advertisements
CVPR 2017