Seeing Is Believing? A Benchmark for Multimodal Large Language Models on Visual Illusions and Anomalies

Documenti analoghi

• Incentivizing Generative Zero-Shot Learning via Outcome-Reward Reinforcement Learning with Visual Cues
  di: Hou, Wenjin, et al.
  Pubblicazione: (2026)
• Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions
  di: Sun, Xiaoxiao, et al.
  Pubblicazione: (2026)
• Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models
  di: He, Zhentao, et al.
  Pubblicazione: (2025)
• Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models
  di: Endo, Mark, et al.
  Pubblicazione: (2025)
• Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration
  di: Endo, Mark, et al.
  Pubblicazione: (2024)