Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner

Documenti analoghi

• LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
  di: Shang, Yuzhang, et al.
  Pubblicazione: (2024)
• freePruner: A Training-free Approach for Large Multimodal Model Acceleration
  di: Xu, Bingxin, et al.
  Pubblicazione: (2024)
• Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning
  di: Kang, Weitai, et al.
  Pubblicazione: (2024)
• Vinoground: Scrutinizing LMMs over Dense Temporal Reasoning with Short Videos
  di: Zhang, Jianrui, et al.
  Pubblicazione: (2024)
• ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms
  di: Xu, Bingxin, et al.
  Pubblicazione: (2025)