Wei Huang

The paper introduces SecGoal, a benchmark dataset and framework, demonstrating that fine-tuning smaller LLMs on this dataset significantly improves the precision of extracting formalizable security goals from natural language protocol documents.

The paper introduces an A*-inspired framework to generate highly effective and efficient adversarial prompts that cause LLMs to hallucinate commonsense errors while maintaining the original prompt's intent.

LongLive-RAG proposes a novel Retrieval-Augmented Generation (RAG) framework to stabilize and improve the quality of long-horizon video generation by treating the entire generated history as a searchable memory.

The paper proposes a lightweight post-processing framework that enhances identity continuity in thermal pedestrian tracking by leveraging scene-level spatial-temporal consistency, achieving improved tracking performance without complex re-identification models.