PhD student, University of Science and Technology of China
2 papers at NeurIPS 2025
We propose CARML, a novel retrieval-augmented editing framework that integrates conflict-aware dynamic retrieval with multi-level collaborative guidance for reliable lifelong multimodal editing.
We present Fact-R1, a reasoning-enhanced framework for video misinformation detection, along with FakeVV, a large-scale benchmark of over 100,000 annotated video-text pairs.
