R-CoV is a six-step region-aware chain-of-verification technique that elicits coordinate and description outputs from LVLMs themselves to detect and reduce object hallucinations without external models or retraining.
Microsoft coco: Common objects in context
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3representative citing papers
Memorization in Stable Diffusion is driven by the structural duplication of the CLIP <eot> embedding inside <pad> tokens, which causes over-reliance on that vector; simple inference-time masking or token replacement suppresses it without quality loss.
ReSpec filters video-text streams by alignment, downstream-task density, and text specificity, achieving higher retrieval accuracy than full-data training while using between 5% and 27% of the data.
citing papers explorer
-
R-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMs
R-CoV is a six-step region-aware chain-of-verification technique that elicits coordinate and description outputs from LVLMs themselves to detect and reduce object hallucinations without external models or retraining.
-
Memorization In Stable Diffusion Is Unexpectedly Driven by CLIP Embeddings
Memorization in Stable Diffusion is driven by the structural duplication of the CLIP <eot> embedding inside <pad> tokens, which causes over-reliance on that vector; simple inference-time masking or token replacement suppresses it without quality loss.
-
ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams
ReSpec filters video-text streams by alignment, downstream-task density, and text specificity, achieving higher retrieval accuracy than full-data training while using between 5% and 27% of the data.