Zhenbo Shi

Orcid: 0000-0002-4230-1552

According to our database1, Zhenbo Shi authored at least 24 papers between 2021 and 2026.

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

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning.
CoRR, May, 2026

Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs.
CoRR, May, 2026

UTOPIA: Unlearnable Tabular Data via Decoupled Shortcut Embedding.
CoRR, February, 2026

A survey on anomaly segmentation in urban scene understanding with image data.
Knowl. Based Syst., 2026

2025
A Unified Perspective From Diffuse Deviation to Target Hijacking.
IEEE Trans. Dependable Secur. Comput., 2025

On filling the intra-class and inter-class gaps for few-shot segmentation.
Expert Syst. Appl., 2025

Leaving No OOD Instance Behind: Instance-Level OOD Fine-Tuning for Anomaly Segmentation.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Tip the Scales: Achieving Balance in Adversarial Examples Across Modalities.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

RP-PGD: Boosting Segmentation Robustness with a Region-and-Prototype Based Adversarial Attack.
Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

AAKR: Adversarial Attack-based Knowledge Retention for Continual Semantic Segmentation.
Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

Stop Diverse OOD Attacks: Knowledge Ensemble for Reliable Defense.
Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024
PFFAA: Prototype-based Feature and Frequency Alteration Attack for Semantic Segmentation.
Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024

GenSeg: On Generating Unified Adversary for Segmentation.
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024

TIKP: Text-to-Image Knowledge Preservation for Continual Semantic Segmentation.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

Attacks on Continual Semantic Segmentation by Perturbing Incremental Samples.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
Reinforcement Learning-based Adversarial Attacks on Object Detectors using Reward Shaping.
Proceedings of the 31st ACM International Conference on Multimedia, 2023

2022
AtHom: Two Divergent Attentions Stimulated By Homomorphic Training in Text-to-Image Synthesis.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

Shape Prior Guided Attack: Sparser Perturbations on 3D Point Clouds.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021
AggNet for Self-supervised Monocular Depth Estimation: Go An Aggressive Step Furthe.
Proceedings of the MM '21: ACM Multimedia Conference, Virtual Event, China, October 20, 2021

Private FLI: Anti-Gradient Leakage Recovery Data Privacy Architecture.
Proceedings of the International Joint Conference on Neural Networks, 2021

Continuous Copy-Paste for One-stage Multi-object Tracking and Segmentation.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Adversarial Attacks on Object Detectors with Limited Perturbations.
Proceedings of the IEEE International Conference on Acoustics, 2021

Mask4D: 4D Convolution Network for Light Field Occlusion Removal.
Proceedings of the IEEE International Conference on Acoustics, 2021

VK-Net: Category-Level Point Cloud Registration with Unsupervised Rotation Invariant Keypoints.
Proceedings of the IEEE International Conference on Acoustics, 2021


  Loading...