M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding

Documenti analoghi

• VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning
  di: Lin, Han, et al.
  Pubblicazione: (2023)
• MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies
  di: Zhang, Shiyue, et al.
  Pubblicazione: (2023)
• CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval
  di: Wan, David, et al.
  Pubblicazione: (2025)
• Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement
  di: Lee, Daeun, et al.
  Pubblicazione: (2024)
• Video-Skill-CoT: Skill-based Chain-of-Thoughts for Domain-Adaptive Video Reasoning
  di: Lee, Daeun, et al.
  Pubblicazione: (2025)