most citedASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.CVShow all

2 papers · 1 filter

cs.CV2025★ 1 cited

ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM

Yujun Wang, Aniri, Jinhe Bi +2

Multimodal large language models (MLLMs) frequently hallucinate by over-committing to spurious visual cues. Prior remedies-Visual and Instruction Contrastive Decoding (VCD, ICD)-mi…

cs.CV2025

PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection

Jinhe Bi, Aniri, Zengjie Jin +11

Visual instruction tuning adapts pre-trained Multimodal Large Language Models (MLLMs) to follow human instructions for real-world applications. However, the rapid growth of these d…