most citedMitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance

4 citations · 4 across the 4 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

Self-Augmenting Retrieval for Diffusion Language Models

Paul Jünger, Justin Lovelace, Linxi Zhao +2

Diffusion language models generate text by iteratively denoising an entire response in parallel, holding a noisy draft of the answer at every step. We show that these intermediate…