activity
20222026
most citedAn Image is Worth Multiple Words: Multi-attribute Inversion for Constrained Text-to-Image Synthesis

2 citations · 3 across the 7 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.CV2026

SAGE: Sink-Aware Grounded Decoding for Multimodal Hallucination Mitigation

Tripti Shukla, Zsolt Kira

Large vision-language models (VLMs) frequently suffer from hallucinations, generating content that is inconsistent with visual inputs. Existing methods typically address this probl…