CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples

Documenti analoghi

• Vinoground: Scrutinizing LMMs over Dense Temporal Reasoning with Short Videos
  di: Zhang, Jianrui, et al.
  Pubblicazione: (2024)
• Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition
  di: Oh, Youngtaek, et al.
  Pubblicazione: (2024)
• CHARTOM: A Visual Theory-of-Mind Benchmark for LLMs on Misleading Charts
  di: Bharti, Shubham, et al.
  Pubblicazione: (2024)
• Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding
  di: Zhang, Le, et al.
  Pubblicazione: (2023)
• VGBench: Evaluating Large Language Models on Vector Graphics Understanding and Generation
  di: Zou, Bocheng, et al.
  Pubblicazione: (2024)