Lijun Sheng
6 papers · 2024–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(6)
🌉
Interdisciplinary Bridge
🐝
Cross-Pollinator
(15)
Conferences
AAAI (1)
CVPR (1)
ECCV (1)
ICCV (1)
ICLR (1)
ICML (1)
Top co-authors
Keywords
vision-language model
(2)
adversarial robustness
(1)
data poisoning
(1)
transfer learning
(1)
entropy minimization
(1)
pseudo labeling
(1)
model adaptation
(1)
unsupervised classification
(1)
backdoor attack
(1)
poisoning attack
(1)
prompt aggregation
(1)
trojan attack
(1)
test-time prompt tuning
(1)
federated learning
(1)
backdoor injection
(1)
Papers
Protecting Model Adaptation from Trojans in the Unlabeled Data
AAAI 2025
R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
CVPR 2025
Cooperative Pseudo Labeling for Unsupervised Federated Classification
ICCV 2025
STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay
ECCV 2024
A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
ICLR 2024
Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization
ICML 2024