HKD4VLM: A Progressive Hybrid Knowledge Distillation Framework for Robust Multimodal Hallucination and Factuality Detection in VLMs

Documenti analoghi

• Contrastive Knowledge Distillation for Robust Multimodal Sentiment Analysis
  di: Sang, Zhongyi, et al.
  Pubblicazione: (2024)
• AD-AVSR: Asymmetric Dual-stream Enhancement for Robust Audio-Visual Speech Recognition
  di: Xue, Junxiao, et al.
  Pubblicazione: (2025)
• FakeSV-VLM: Taming VLM for Detecting Fake Short-Video News via Progressive Mixture-Of-Experts Adapter
  di: Wang, Junxi, et al.
  Pubblicazione: (2025)
• Dark Side of Modalities: Reinforced Multimodal Distillation for Multimodal Knowledge Graph Reasoning
  di: Zhao, Yu, et al.
  Pubblicazione: (2025)
• Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs
  di: Ding, Peng, et al.
  Pubblicazione: (2024)