PPaperPicks

Zhenbo Shi

10 papers at tracked venues · 9 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning
  2. Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs
  3. AAKR: Adversarial Attack-based Knowledge Retention for Continual Semantic Segmentation
  4. Leaving No OOD Instance Behind: Instance-Level OOD Fine-Tuning for Anomaly Segmentation
  5. RP-PGD: Boosting Segmentation Robustness with a Region-and-Prototype Based Adversarial Attack
  6. Stop Diverse OOD Attacks: Knowledge Ensemble for Reliable Defense
    AAAI 2025 · Zhenbo Shi
  7. Attacks on Continual Semantic Segmentation by Perturbing Incremental Samples
  8. GenSeg: On Generating Unified Adversary for Segmentation
  9. PFFAA: Prototype-based Feature and Frequency Alteration Attack for Semantic Segmentation
  10. TIKP: Text-to-Image Knowledge Preservation for Continual Semantic Segmentation