TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation

Documenti analoghi

• Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation
  di: Ge, Yuying, et al.
  Pubblicazione: (2024)
• SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension
  di: Li, Bohao, et al.
  Pubblicazione: (2024)
• DiCoDe: Diffusion-Compressed Deep Tokens for Autoregressive Video Generation with Language Models
  di: Li, Yizhuo, et al.
  Pubblicazione: (2024)
• TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs
  di: Zhang, Jun, et al.
  Pubblicazione: (2025)
• SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation
  di: Ge, Yuying, et al.
  Pubblicazione: (2024)