Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence

Documenti analoghi

• Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation
  di: Hua, Zhenglin, et al.
  Pubblicazione: (2025)
• Active Zero: Self-Evolving Vision-Language Models through Active Environment Exploration
  di: He, Jinghan, et al.
  Pubblicazione: (2026)
• MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process Diagnosis
  di: Guo, Haiyun, et al.
  Pubblicazione: (2025)
• SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models
  di: He, Jinghan, et al.
  Pubblicazione: (2024)
• Zero-1-to-A: Zero-Shot One Image to Animatable Head Avatars Using Video Diffusion
  di: Zhou, Zhenglin, et al.
  Pubblicazione: (2025)