Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions

Documenti analoghi

• TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs
  di: Li, Yunheng, et al.
  Pubblicazione: (2025)
• Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought
  di: Li, Yunheng, et al.
  Pubblicazione: (2026)
• High-Quality Mask Tuning Matters for Open-Vocabulary Segmentation
  di: Zeng, Quan-Sheng, et al.
  Pubblicazione: (2024)
• Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation
  di: Li, Yunheng, et al.
  Pubblicazione: (2024)
• Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction
  di: Li, Yunheng, et al.
  Pubblicazione: (2024)