Bo Han

25

Papers

109

Total Citations

Papers (25)

Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond

Federated Learning with Extremely Noisy Clients via Negative Distillation

Towards Effective Evaluations and Comparisons for LLM Unlearning Methods

Understanding and Enhancing the Transferability of Jailbreaking Attacks

Understanding Fairness Surrogate Functions in Algorithmic Fairness

Robust Training of Federated Models with Extremely Label Deficiency

From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?

Learning to Instruct for Visual Instruction Tuning

NeurIPS 2025arXiv

Towards Out-of-Modal Generalization without Instance-level Modal Correspondence

Detecting Generated Images by Fitting Natural Image Distributions

Fast and Accurate Blind Flexible Docking

Balancing Similarity and Complementarity for Federated Learning

Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection

Golden Noise for Diffusion Models: A Learning Framework

Towards Realistic Model Selection for Semi-supervised Learning

Provable Discriminative Hyperspherical Embedding for Out-of-Distribution Detection

Eliciting Causal Abilities in Large Language Models for Reasoning Tasks

AMD: Autoregressive Motion Diffusion

Enhancing Evolving Domain Generalization through Dynamic Latent Representations

Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning

How Interpretable Are Interpretable Graph Neural Networks?

Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency

MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence

Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning

Mitigating Label Noise on Graphs via Topological Sample Selection