Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation

Documenti analoghi

• From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis
  di: Cheng, Chuanqi, et al.
  Pubblicazione: (2024)
• Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains
  di: Zhang, Juntian, et al.
  Pubblicazione: (2025)
• From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment
  di: Li, Jia-Nan, et al.
  Pubblicazione: (2025)
• "In Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning
  di: Cheng, Chuanqi, et al.
  Pubblicazione: (2024)
• Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signals
  di: Li, Jia-Nan, et al.
  Pubblicazione: (2025)