Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs

Documenti analoghi

• Token-Efficient Item Representation via Images for LLM Recommender Systems
  di: Kim, Kibum, et al.
  Pubblicazione: (2025)
• Lost in Sequence: Do Large Language Models Understand Sequential Recommendation?
  di: Kim, Sein, et al.
  Pubblicazione: (2025)
• Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding
  di: Kim, Jiwan, et al.
  Pubblicazione: (2026)
• CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs
  di: Kim, Jiwan, et al.
  Pubblicazione: (2025)
• Adaptive Self-training Framework for Fine-grained Scene Graph Generation
  di: Kim, Kibum, et al.
  Pubblicazione: (2024)