Seeing the Forest and the Trees: Query-Aware Tokenizer for Long-Video Multimodal Language Models

Documenti analoghi

• Making Dialogue Grounding Data Rich: A Three-Tier Data Synthesis Framework for Generalized Referring Expression Comprehension
  di: Shao, Juexi, et al.
  Pubblicazione: (2025)
• GlazyBench: A Benchmark for Ceramic Glaze Property Prediction and Image Generation
  di: Zhai, Ziyu, et al.
  Pubblicazione: (2026)
• $μ^2$Tokenizer: Differentiable Multi-Scale Multi-Modal Tokenizer for Radiology Report Generation
  di: Li, Siyou, et al.
  Pubblicazione: (2025)
• Improving LLMs' Learning for Coreference Resolution
  di: Gan, Yujian, et al.
  Pubblicazione: (2025)
• NovBench: Evaluating Large Language Models on Academic Paper Novelty Assessment
  di: Wu, Wenqing, et al.
  Pubblicazione: (2026)