Zitai Wang
14 papers · 2022–2026 · 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 ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (39) 🤝 Dynamic Duo (13)
🗃️
Keyword Collector
(76)
💎
Century Club · Bronze
🔥
Unstoppable · Bronze
Venues
Top co-authors
Research topics
Deep Learning
(10)
Machine Learning
(9)
Core Methods
(7)
Artificial Intelligence
(6)
Core AI · Artificial Intelligence
(5)
Computer Vision
(4)
Architectures
(4)
Learning Types · Machine Learning
(4)
Learning Types · Deep Learning
(4)
Models
(4)
Analysis
(3)
Optimization & Theory
(3)
Application Areas
(2)
Core AI · Computer Vision
(2)
Learning Paradigms
(1)
Keywords
generalization bound
(2)
diffusion model
(2)
out-of-distribution detection
(2)
semantic segmentation
(2)
feature extraction
(1)
multi-label learning
(1)
metric learning
(1)
knowledge distillation
(1)
anomaly detection
(1)
sharpness-aware minimization
(1)
outlier detection
(1)
novelty detection
(1)
auc optimization
(1)
area under curve
(1)
generative model
(1)
graph anomaly detection
(1)
generalization
(1)
preference modeling
(1)
feature selection
(1)
image generation
(1)
Papers
GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment
ACL 2026
Making Training-Free Diffusion Segmentors Scale with the Generative Power
CVPR 2026
Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMs
CVPR 2026
Quantifying the Potential to Escape Filter Bubbles: A Behavior-Aware Measure via Contrastive Simulation
AAAI 2026
ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $α$-$β$-Divergence
ICML 2025
EDGE: Unknown-aware Multi-label Learning by Energy Distribution Gap Expansion
AAAI 2025
Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification
ICML 2025
OpenworldAUC: Towards Unified Evaluation and Optimization for Open-world Prompt Tuning
ICML 2025
ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection
AAAI 2024
Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition
ICML 2024
Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features
NeurIPS 2024
Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques
NeurIPS 2024
A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning
NeurIPS 2023
OpenAUC: Towards AUC-Oriented Open-Set Recognition
NeurIPS 2022