Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding

Documenti analoghi

• Strefer: Empowering Video LLMs with Space-Time Referring and Reasoning via Synthetic Instruction Data
  di: Zhou, Honglu, et al.
  Pubblicazione: (2025)
• Future Optical Flow Prediction Improves Robot Control & Video Generation
  di: Ranasinghe, Kanchana, et al.
  Pubblicazione: (2026)
• xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs
  di: Ryoo, Michael S., et al.
  Pubblicazione: (2024)
• ViUniT: Visual Unit Tests for More Robust Visual Programming
  di: Panagopoulou, Artemis, et al.
  Pubblicazione: (2024)
• xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations
  di: Qin, Can, et al.
  Pubblicazione: (2024)