8 papers
Bayesian Data Reweighting Improves Multimodal Retrieval for Knowledge-Based Visual Question Answering
Jingchen Sun, Shaobo Han, Ruiyi Zhang +5
Multimodal retrievers are essential for knowledge-based visual question answering, where they retrieve external evidence for image-question pairs. However, existing contrastive tra…
Score-Control for Hallucination Reduction in Diffusion Models
Mahesh Bhosale, Naresh Kumar Devulapally, Abdul Wasi +3
Diffusion models have emerged as the backbone of modern generative AI, powering advances in vision, language, audio and other modalities. Despite their success, they suffer from ha…
OSCAR: Orchestrated Self-verification and Cross-path Refinement
Yash Shah, Abhijit Chakraborty, Naresh Kumar Devulapally +2
Diffusion language models (DLMs) expose their denoising trajectories, offering a natural handle for inference-time control; accordingly, an ideal hallucination mitigation framework…
Forget Less by Learning Together through Concept Consolidation
Arjun Ramesh Kaushik, Naresh Kumar Devulapally, Vishnu Suresh Lokhande +2
Custom Diffusion Models (CDMs) have gained significant attention due to their remarkable ability to personalize generative processes. However, existing CDMs suffer from catastrophi…
Forget Less by Learning from Parents Through Hierarchical Relationships
Arjun Ramesh Kaushik, Naresh Kumar Devulapally, Vishnu Suresh Lokhande +2
Custom Diffusion Models (CDMs) offer impressive capabilities for personalization in generative modeling, yet they remain vulnerable to catastrophic forgetting when learning new con…
Model-Agnostic Gender Bias Control for Text-to-Image Generation via Sparse Autoencoder
Chao Wu, Zhenyi Wang, Kangxian Xie +3
Text-to-image (T2I) diffusion models often exhibit gender bias, particularly by generating stereotypical associations between professions and gendered subjects. This paper presents…