To See or To Read: User Behavior Reasoning in Multimodal LLMs

Documenti analoghi

• Is More Context Always Better? Examining LLM Reasoning Capability for Time Interval Prediction
  di: Cao, Yanan, et al.
  Pubblicazione: (2026)
• Decoding Style: Efficient Fine-Tuning of LLMs for Image-Guided Outfit Recommendation with Preference
  di: Forouzandehmehr, Najmeh, et al.
  Pubblicazione: (2024)
• Character-based Outfit Generation with Vision-augmented Style Extraction via LLMs
  di: Forouzandehmehr, Najmeh, et al.
  Pubblicazione: (2024)
• Triple Modality Fusion: Aligning Visual, Textual, and Graph Data with Large Language Models for Multi-Behavior Recommendations
  di: Ma, Luyi, et al.
  Pubblicazione: (2024)
• LayoutAgent: A Vision-Language Agent Guided Compositional Diffusion for Spatial Layout Planning
  di: Fan, Zezhong, et al.
  Pubblicazione: (2025)