Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuracy

Documenti analoghi

• VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model
  di: Long, Zuwei, et al.
  Pubblicazione: (2025)
• VEGA: Learning Interleaved Image-Text Comprehension in Vision-Language Large Models
  di: Zhou, Chenyu, et al.
  Pubblicazione: (2024)
• Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs
  di: Li, Xudong, et al.
  Pubblicazione: (2025)
• VITA: Towards Open-Source Interactive Omni Multimodal LLM
  di: Fu, Chaoyou, et al.
  Pubblicazione: (2024)
• VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
  di: Fu, Chaoyou, et al.
  Pubblicazione: (2025)