PPaperPicks

Bo Han

Hong Kong Baptist University, Department of Computer Science, Hong Kong

76 papers at tracked venues · 71 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Select Before Use: On the Importance of Reference Model Selection in Preference Alignment
  2. Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach
  3. Trustworthy Foundation Models for Web Intelligence: Causal Perspectives and Challenges
  4. A Lens into Interpretable Transformer Mistakes via Semantic Dependency
  5. A Robust Method to Discover Causal or Anticausal Relation
  6. Adaptive Localization of Knowledge Negation for Continual LLM Unlearning
  7. Advancing Machine-Generated Text Detection from an Easy to Hard Supervision Perspective
  8. Atomas: Hierarchical Adaptive Alignment on Molecule-Text for Unified Molecule Understanding and Generation
  9. Characterizing Submanifold Region for Out-of-Distribution Detection: (Extended Abstract)
  10. Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning
  11. Detecting Generated Images by Fitting Natural Image Distributions
  12. Eliciting Causal Abilities in Large Language Models for Reasoning Tasks
  13. Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples
  14. Epistemic Uncertainty for Generated Image Detection
  15. Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
  16. Fast and Accurate Blind Flexible Docking
  17. FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning
  18. From Debate to Equilibrium: Belief‑Driven Multi‑Agent LLM Reasoning via Bayesian Nash Equilibrium
  19. From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
  20. GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs
  21. Generative Model Inversion Through the Lens of the Manifold Hypothesis
  22. Golden Noise for Diffusion Models: A Learning Framework
  23. Hot-pluggable Federated Learning: Bridging General and Personalized FL via Dynamic Selection
  24. Instance-dependent Early Stopping
  25. Learning to Instruct for Visual Instruction Tuning
  26. Learning without Isolation: Pathway Protection for Continual Learning
  27. Noisy Test-Time Adaptation in Vision-Language Models
  28. One-shot Federated Learning Methods: A Practical Guide
  29. Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection
  30. Practical Kernel Selection for Kernel-based Conditional Independence Test
  31. Provable Discriminative Hyperspherical Embedding for Out-of-Distribution Detection
  32. Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond
  33. Towards Effective Evaluations and Comparisons for LLM Unlearning Methods
  34. Towards Out-of-Modal Generalization without Instance-level Modal Correspondence
  35. Towards Regularized Mixture of Predictions for Class-Imbalanced Semi-Supervised Facial Expression Recognition
  36. Trustworthy AI under Imperfect Web Data
  37. Understanding and Enhancing the Transferability of Jailbreaking Attacks
  38. Unlocker: Disentangle the Deadlock of Learning between Label-noisy and Long-tailed Data
  39. When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need
  40. A Sober Look at the Robustness of CLIPs to Spurious Features
  41. Accurate Forgetting for Heterogeneous Federated Continual Learning
  42. Balancing Similarity and Complementarity for Federated Learning
  43. Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?
  44. Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy
  45. Discovery of the Hidden World with Large Language Models
  46. Enhancing Contrastive Learning for Ordinal Regression via Ordinal Content Preserved Data Augmentation
  47. Enhancing Evolving Domain Generalization through Dynamic Latent Representations
  48. Enhancing Neural Subset Selection: Integrating Background Information into Set Representations
  49. Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting
  50. Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection
  51. FedImpro: Measuring and Improving Client Update in Federated Learning
  52. Federated Learning with Extremely Noisy Clients via Negative Distillation
  53. Few-Shot Adversarial Prompt Learning on Vision-Language Models
  54. FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion
  55. How Interpretable Are Interpretable Graph Neural Networks?
  56. Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency
  57. Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs
  58. MCM: Multi-condition Motion Synthesis Framework
  59. MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence
  60. Mind the Gap Between Prototypes and Images in Cross-domain Finetuning
  61. Mitigating Label Noise on Graphs via Topological Sample Selection
  62. Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning
  63. Negative Label Guided OOD Detection with Pretrained Vision-Language Models
  64. Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication Channel
  65. NoiseDiffusion: Correcting Noise for Image Interpolation with Diffusion Models beyond Spherical Linear Interpolation
  66. On the Over-Memorization During Natural, Robust and Catastrophic Overfitting
  67. Out-of-Distribution Detection with Negative Prompts
  68. Pseudo-Private Data Guided Model Inversion Attacks
  69. Revive Re-weighting in Imbalanced Learning by Density Ratio Estimation
  70. Robust Training of Federated Models with Extremely Label Deficiency
  71. Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection
  72. Towards Realistic Model Selection for Semi-supervised Learning
  73. Trustworthy Machine Learning under Imperfect Data
    IJCAI 2024 · Bo Han
  74. Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning
  75. Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
  76. What If the Input is Expanded in OOD Detection?