Bo Wang
7 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
MemHint is a neuro-symbolic static analysis pipeline that significantly improves memory leak detection in C/C++ by combining LLM semantic understanding with Z3 symbolic reasoning, detecting more leaks than existing tools.
This paper systematically investigates unlearnable examples (UEs) across diverse training paradigms, finding that existing UEs fail under pretraining-finetuning (PF) settings, and proposes Shallow Semantic Camouflage (SSC) to maintain unlearnability.
This paper reinterprets catastrophic overfitting (CO) in Fast Adversarial Training (FAT) as a weak backdoor mechanism, proposing backdoor-inspired strategies to mitigate this generalization failure.
The paper proposes a Distribution-aware Dynamic Guidance (DDG) strategy to mitigate catastrophic overfitting and the robustness-accuracy trade-off inherent in Fast Adversarial Training (FAT) by dynamically adjusting perturbation budgets and supervision signals based on sample confidence.
This paper introduces a new benchmark for evaluating the performance of large language models in generating slide decks that consider the target audience.
A new paradigm for generating personalized videos on demand from inferred user interest.
This paper proposes RAPS-DA, a framework that addresses conflicts in retrieval-augmented generation using a regime-aware peer specialization system and a dual-layer selector.
Papers
Regime-Aware Peer Specialization for Robust RAG under Heterogeneous Knowledge Conflicts
Bo Wang, Heyan Huang, Yaolin Li, Yanghao Zhou +4 more
This paper proposes RAPS-DA, a framework that addresses conflicts in retrieval-augmented generation using a regime-aware peer specialization system and a dual-layer selector.