Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models

Documenti analoghi

• MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly
  di: Wang, Zhaowei, et al.
  Pubblicazione: (2025)
• MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
  di: Ren, Xiyu, et al.
  Pubblicazione: (2026)
• Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
  di: Wang, Zhaowei, et al.
  Pubblicazione: (2026)
• $\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ Retrieval
  di: Wang, Zihao, et al.
  Pubblicazione: (2026)
• DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations
  di: Gema, Aryo Pradipta, et al.
  Pubblicazione: (2024)