VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model

Documenti analoghi

• VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning
  di: Zhuang, Xianwei, et al.
  Pubblicazione: (2025)
• VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification
  di: Zhuang, Xianwei, et al.
  Pubblicazione: (2025)
• ATRI: Mitigating Multilingual Audio Text Retrieval Inconsistencies by Reducing Data Distribution Errors
  di: Yin, Yuguo, et al.
  Pubblicazione: (2025)
• Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation
  di: Tang, Lexiang, et al.
  Pubblicazione: (2025)
• Do we really have to filter out random noise in pre-training data for language models?
  di: Ru, Jinghan, et al.
  Pubblicazione: (2025)