Ngā tūemi rite

• Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation
  mā: Jia, Sihang, me ētahi atu.
  I whakaputaina: (2026)
• Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality
  mā: Zhou, Guanyu, me ētahi atu.
  I whakaputaina: (2024)
• When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMs
  mā: Cao, Fanpu, me ētahi atu.
  I whakaputaina: (2026)
• Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models
  mā: Zheng, Kening, me ētahi atu.
  I whakaputaina: (2024)
• Distilling the Thought, Watermarking the Answer: A Principle Semantic Guided Watermark for Large Reasoning Models
  mā: Liu, Shuliang, me ētahi atu.
  I whakaputaina: (2026)