Decoupled Proxy Alignment: Mitigating Language Prior Conflict for Multimodal Alignment in MLLM

Documenti analoghi

• UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets
  di: Wang, Pengyu, et al.
  Pubblicazione: (2025)
• InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance
  di: Wang, Pengyu, et al.
  Pubblicazione: (2024)
• MetaAlign: Align Large Language Models with Diverse Preferences during Inference Time
  di: Zhang, Mozhi, et al.
  Pubblicazione: (2024)
• SpeechAgents: Human-Communication Simulation with Multi-Modal Multi-Agent Systems
  di: Zhang, Dong, et al.
  Pubblicazione: (2024)
• Sparser Block-Sparse Attention via Token Permutation
  di: Wang, Xinghao, et al.
  Pubblicazione: (2025)