Reasoning Like Experts: Leveraging Multimodal Large Language Models for Drawing-based Psychoanalysis

Documenti analoghi

• Investigating The Functional Roles of Attention Heads in Vision Language Models: Evidence for Reasoning Modules
  di: Jiang, Yanbei, et al.
  Pubblicazione: (2025)
• KALE: An Artwork Image Captioning System Augmented with Heterogeneous Graph
  di: Jiang, Yanbei, et al.
  Pubblicazione: (2024)
• PROPA: Toward Process-level Optimization in Visual Reasoning via Reinforcement Learning
  di: Jiang, Yanbei, et al.
  Pubblicazione: (2025)
• Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task
  di: Jiang, Yanbei, et al.
  Pubblicazione: (2025)
• MM-InstructEval: Zero-Shot Evaluation of (Multimodal) Large Language Models on Multimodal Reasoning Tasks
  di: Yang, Xiaocui, et al.
  Pubblicazione: (2024)