Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models

Documenti analoghi

• Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models
  di: Zheng, Kening, et al.
  Pubblicazione: (2024)
• SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning
  di: Chen, Junkai, et al.
  Pubblicazione: (2025)
• Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention
  di: Zou, Xin, et al.
  Pubblicazione: (2025)
• MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models
  di: Huo, Jiahao, et al.
  Pubblicazione: (2025)
• Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination
  di: Zheng, Haojie, et al.
  Pubblicazione: (2024)