PPaperPicks

Sheng-Jun Huang

25 papers at tracked venues · 17 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. MultiMedBench: A Scenario-Aware Benchmark for Evaluating Knowledge Editing in Medical VQA
  2. Reflect Then Learn: Active Prompting for Information Extraction Guided by Introspective Confusion
  3. Conservative Query and Adaptive Regularization for Offline RL under Uncertainty Estimation
  4. DM-POSA: Enhancing Open-World Test-Time Adaptation with Dual-Mode Matching and Prompt-Based Open Set Adaptation
  5. Dual-Head Knowledge Distillation: Enhancing Logits Utilization with an Auxiliary Head
  6. Efficient Heterogeneity-Aware Federated Active Data Selection
  7. FedDLAD: A Federated Learning Dual-Layer Anomaly Detection Framework for Enhancing Resilience Against Backdoor Attacks
  8. Graph-guided Cross-composition Feature Disentanglement for Compositional Zero-shot Learning
  9. Improving Generalization of Deep Neural Networks by Optimum Shifting
  10. Inconsistency-Based Federated Active Learning
  11. Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL
  12. MLC-NC: Long-Tailed Multi-Label Image Classification Through the Lens of Neural Collapse
  13. Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition
  14. Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approach
  15. StructSR: Refuse Spurious Details in Real-World Image Super-Resolution
  16. Asymmetric Beta Loss for Evidence-Based Safe Semi-Supervised Multi-Label Learning
  17. Bidirectional Uncertainty-Based Active Learning for Open-Set Annotation
  18. Causality-enhanced Discreted Physics-informed Neural Networks for Predicting Evolutionary Equations
  19. Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training
  20. Dirichlet-Based Prediction Calibration for Learning with Noisy Labels
  21. Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-supervised Multi-label Learning
  22. NanoAdapt: Mitigating Negative Transfer in Test Time Adaptation with Extremely Small Batch Sizes
  23. One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models
    ICLR 2024 · Sheng-Jun Huang
  24. Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL
  25. Unlocking the Power of Open Set: A New Perspective for Open-Set Noisy Label Learning