Zeliang Zhang
16 papers · 2022–2026 · 10 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 ↓+5 more ↓ Show less ↑
π Conference Polyglot Β· Gold π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (28) π Grand Slam π€ Dynamic Duo (11)
ποΈ
Keyword Collector
(76)
π₯
Unstoppable Β· Bronze
β
The Questioner
(3)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
Top co-authors
Research topics
Machine Learning
(12)
Artificial Intelligence
(11)
Core AI
(10)
Deep Learning
(6)
Application Areas
(6)
Learning Types Β· Machine Learning
(4)
Optimization & Theory
(4)
Computer Vision
(3)
Processing
(3)
Architectures
(2)
Learning Types Β· Deep Learning
(2)
Techniques
(2)
Reinforcement Learning
(1)
Applications
(1)
Generation
(1)
Keywords
adversarial robustness
(2)
input transformation
(2)
adversarial attack
(2)
audio-visual learning
(2)
multimodal learning
(2)
image classification
(2)
adversarial example
(2)
neural network training
(1)
model unlearning
(1)
zero-shot learning
(1)
knowledge distillation
(1)
bias detection
(1)
vision transformer
(1)
model architecture
(1)
object tracking
(1)
video captioning
(1)
adversarial training
(1)
flow matching
(1)
gradient estimation
(1)
video understanding
(1)
Papers
Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting
AAAI 2026
Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts
ACL 2025
FLOPS: Forward Learning with OPtimal Sampling
ICLR 2025
p-AVAS: Can Physics-Integrated Audio-Visual Modeling Boost Neural Acoustic Synthesis?
ICCV 2025
Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives
ICLR 2025
Targeted Forgetting of Image Subgroups in CLIP Models
CVPR 2025
Understanding Model Ensemble in Transferable Adversarial Attack
ICML 2025
VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?
CVPR 2025
Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP
EMNLP 2024
Discover and Mitigate Multiple Biased Subgroups in Image Classifiers
CVPR 2024
Learning to Transform Dynamically for Better Adversarial Transferability
CVPR 2024
One Forward is Enough for Neural Network Training via Likelihood Ratio Method
ICLR 2024
Random Smooth-based Certified Defense against Text Adversarial Attack
EACL 2024
Classical Simulation of Quantum Circuits: Parallel Environments and Benchmark
NeurIPS 2023
Structure Invariant Transformation for better Adversarial Transferability
ICCV 2023
Triangle Attack: A Query-Efficient Decision-Based Adversarial Attack
ECCV 2022