Lijun Sheng

Orcid: 0000-0002-8240-9736

According to our database1, Lijun Sheng authored at least 18 papers between 2023 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
Adapting Vision-Language Models Without Labels: A Comprehensive Survey.
CoRR, August, 2025

The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models.
CoRR, June, 2025

R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Protecting Model Adaptation from Trojans in the Unlabeled Data.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024
Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection.
Int. J. Comput. Vis., December, 2024

Towards Compatible Fine-tuning for Vision-Language Model Updates.
CoRR, 2024

Prototypical Distillation and Debiased Tuning for Black-box Unsupervised Domain Adaptation.
CoRR, 2024

Recent Advances in OOD Detection: Problems and Approaches.
CoRR, 2024

Can We Trust the Unlabeled Target Data? Towards Backdoor Attack and Defense on Model Adaptation.
CoRR, 2024

Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay.
Proceedings of the Computer Vision - ECCV 2024, 2024

2023
ProxyMix: Proxy-based Mixup training with label refinery for source-free domain adaptation.
Neural Networks, October, 2023

Self-training solutions for the ICCV 2023 GeoNet Challenge.
CoRR, 2023

Unleashing the power of Neural Collapse for Transferability Estimation.
CoRR, 2023

Towards Realistic Unsupervised Fine-tuning with CLIP.
CoRR, 2023

Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification.
CoRR, 2023

AdaptGuard: Defending Against Universal Attacks for Model Adaptation.
CoRR, 2023


  Loading...