dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models

Documenti analoghi

• Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models
  di: Luo, Siqi, et al.
  Pubblicazione: (2026)
• Modality-Fair Preference Optimization for Trustworthy MLLM Alignment
  di: Jiang, Songtao, et al.
  Pubblicazione: (2024)
• Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding
  di: Xin, Yi, et al.
  Pubblicazione: (2025)
• Resurrect Mask AutoRegressive Modeling for Efficient and Scalable Image Generation
  di: Xin, Yi, et al.
  Pubblicazione: (2025)
• PIP-MM: Pre-Integrating Prompt Information into Visual Encoding via Existing MLLM Structures
  di: Wu, Tianxiang, et al.
  Pubblicazione: (2024)