Zequn Zeng
6 papers · 2023–2025 · 3 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 · Silver
🗺️
Taxonomy Completionist
(18)
Top co-authors
Research topics
Machine Learning
(6)
Deep Learning
(4)
Learning Types · Deep Learning
(4)
Computer Vision
(3)
Core Methods
(3)
Artificial Intelligence
(2)
Natural Language Processing
(2)
Core AI
(2)
Generation · Computer Vision
(2)
Learning Types · Machine Learning
(2)
Analysis
(1)
Application Areas
(1)
Applications
(1)
Architectures
(1)
Generation · Natural Language Processing
(1)
Keywords
zero-shot image captioning
(2)
zero-shot learning
(2)
image captioning
(2)
vision-language model
(2)
multi-label classification
(1)
semantic consistency
(1)
interpretable classification
(1)
visual concept
(1)
disentangled representation
(1)
language model
(1)
cross-modal alignment
(1)
ood generalization
(1)
controllable generation
(1)
concept bottleneck
(1)
sparsity level
(1)
retrieval-augmented generation
(1)
patch embedding
(1)
contrastive objective
(1)
non-autoregressive generation
(1)
non-autoregressive language model
(1)
Papers
Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation
ICML 2025
Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models
CVPR 2025
Explaining Domain Shifts in Language: Concept Erasing for Interpretable Image Classification
CVPR 2025
MeaCap: Memory-Augmented Zero-shot Image Captioning
CVPR 2024
ConZIC: Controllable Zero-Shot Image Captioning by Sampling-Based Polishing
CVPR 2023
PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image Classification
ICCV 2023