Kaican Li
Affiliations:- The Hong Kong University of Science and Technology
- SenseTime Research (former)
According to our database1,
Kaican Li
authored at least 16 papers
between 2018 and 2025.
Collaborative distances:
Collaborative distances:
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
2025
CannyEdit: Selective Canny Control and Dual-Prompt Guidance for Training-Free Image Editing.
CoRR, August, 2025
The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs.
CoRR, July, 2025
2024
Consistency Regularization for Domain Generalization with Logit Attribution Matching.
Proceedings of the Uncertainty in Artificial Intelligence, 2024
Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
2023
Robustness May be More Brittle than We Think under Different Degrees of Distribution Shifts.
CoRR, 2023
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023
2022
CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving.
Proceedings of the Computer Vision - ECCV 2022, 2022
OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
Regularization Penalty Optimization for Addressing Data Quality Variance in OoD Algorithms.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022
2021
OoD-Bench: Benchmarking and Understanding Out-of-Distribution Generalization Datasets and Algorithms.
CoRR, 2021
2020
Proceedings of the Computer Vision - ECCV 2020, 2020
2018
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018