Chain-of-Frames: Advancing Video Understanding in Multimodal LLMs via Frame-Aware Reasoning

Documenti analoghi

• Towards Unified Benchmark and Models for Multi-Modal Perceptual Metrics
  di: Ghazanfari, Sara, et al.
  Pubblicazione: (2024)
• SYNCR: A Cross-Video Reasoning Benchmark with Synthetic Grounding
  di: Ghazanfari, Sara, et al.
  Pubblicazione: (2026)
• EMMA: Efficient Visual Alignment in Multi-Modal LLMs
  di: Ghazanfari, Sara, et al.
  Pubblicazione: (2024)
• LipSim: A Provably Robust Perceptual Similarity Metric
  di: Ghazanfari, Sara, et al.
  Pubblicazione: (2023)
• On the Out-of-Distribution Generalization of Reasoning in Multimodal LLMs for Simple Visual Planning Tasks
  di: Neuhaus, Yannic, et al.
  Pubblicazione: (2026)