Yongyi Su
8 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(20)
🔥
Unstoppable · Bronze
Venues
Top co-authors
Research topics
Machine Learning
(8)
Application Areas
(6)
Learning Types · Machine Learning
(5)
Artificial Intelligence
(4)
Deep Learning
(4)
Computer Vision
(3)
Core AI · Artificial Intelligence
(3)
Learning Types · Deep Learning
(3)
Analysis
(2)
Core Methods
(2)
Architectures
(1)
Core AI · Computer Vision
(1)
Learning Paradigms
(1)
Models
(1)
Optimization & Theory
(1)
Keywords
domain adaptation
(4)
distribution shift
(2)
foundation model
(2)
test-time training
(2)
domain generalization
(2)
test-time adaptation
(2)
anomaly detection
(1)
label propagation
(1)
weakly supervised learning
(1)
batch normalization
(1)
depth estimation
(1)
class imbalance
(1)
out-of-distribution detection
(1)
multimodal large language model
(1)
pseudo label
(1)
segment anything
(1)
group relative policy optimization
(1)
segmentation model
(1)
few-shot example
(1)
multi-stage reasoning
(1)
Papers
AD-FM: Multimodal LLMs for Anomaly Detection via Multi-Stage Reasoning and Fine-Grained Reward Optimization
AAAI 2026
Enhancing Generalization of Depth Estimation Foundation Model via Weakly-Supervised Adaptation with Regularization
AAAI 2026
Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model
ICLR 2025
On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning
ICLR 2025
Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation
CVPR 2024
Towards Real-World Test-Time Adaptation: Tri-net Self-Training with Balanced Normalization
AAAI 2024
On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion
ICCV 2023
Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering
NeurIPS 2022