Yushu Li
4 papers · 2023–2025 · 2 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 · Bronze
🗺️
Taxonomy Completionist
(11)
Top co-authors
Research topics
Keywords
domain adaptation
(2)
out-of-distribution detection
(2)
model security
(1)
data poisoning
(1)
label propagation
(1)
point cloud
(1)
test-time adaptation
(1)
vision-language model
(1)
3d point cloud
(1)
prototype clustering
(1)
few-shot example
(1)
graph score propagation
(1)
graph-based approach
(1)
test-time training
(1)
negative prompting
(1)
prototype expansion
(1)
context-aware feature re-weighting
(1)
real-time inductive inference
(1)
adversarial learning
(1)
test sample manifold
(1)
Papers
Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model
ICLR 2025
Exploiting Vision Language Model for Training-Free 3D Point Cloud OOD Detection via Graph Score Propagation
ICCV 2025
On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning
ICLR 2025
On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion
ICCV 2023