TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives

Documenti analoghi

• EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment
  di: Kusumba, Abhiram, et al.
  Pubblicazione: (2025)
• ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models
  di: Patel, Maitreya, et al.
  Pubblicazione: (2023)
• $λ$-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space
  di: Patel, Maitreya, et al.
  Pubblicazione: (2024)
• On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation
  di: Chatterjee, Agneet, et al.
  Pubblicazione: (2024)
• VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning
  di: Yilmaz, Nilay, et al.
  Pubblicazione: (2025)