The LLM Bottleneck: Why Open-Source Vision LLMs Struggle with Hierarchical Visual Recognition

Documenti analoghi

• Continual Adapter Tuning with Semantic Shift Compensation for Class-Incremental Learning
  di: Zhou, Qinhao, et al.
  Pubblicazione: (2024)
• Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understanding
  di: Huang, Kung-Hsiang, et al.
  Pubblicazione: (2025)
• Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Models
  di: Tan, Yuwen, et al.
  Pubblicazione: (2025)
• Multimodal LLMs Struggle with Basic Visual Network Analysis: a VNA Benchmark
  di: Williams, Evan M., et al.
  Pubblicazione: (2024)
• Diagnosing Bottlenecks in Data Visualization Understanding by Vision-Language Models
  di: Tartaglini, Alexa R., et al.
  Pubblicazione: (2025)