DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding

Documenti analoghi

• Think When Needed: Adaptive Reasoning-Driven Multimodal Embeddings with a Dual-LoRA Architecture
  di: Zhang, Longxiang, et al.
  Pubblicazione: (2026)
• PromptEcho: Annotation-Free Reward from Vision-Language Models for Text-to-Image Reinforcement Learning
  di: Liu, Jinlong, et al.
  Pubblicazione: (2026)
• Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO
  di: Tong, Yunze, et al.
  Pubblicazione: (2026)
• Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative Models
  di: Wang, Yi, et al.
  Pubblicazione: (2025)
• CMMCoT: Enhancing Complex Multi-Image Comprehension via Multi-Modal Chain-of-Thought and Memory Augmentation
  di: Zhang, Guanghao, et al.
  Pubblicazione: (2025)