pith. sign in

Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

dataset 1

citation-polarity summary

fields

cs.CV 1 cs.MM 1

years

2026 2

verdicts

UNVERDICTED 2

roles

dataset 1

polarities

use dataset 1

representative citing papers

LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?

cs.CV · 2026-05-09 · unverdicted · novelty 6.0

LLaVA-UHD v4 reduces visual-encoding FLOPs by 55.8% for high-resolution images in MLLMs via slice-based encoding plus intra-ViT early compression while matching or exceeding baseline performance on document, OCR, and VQA benchmarks.

Anisotropic Modality Align

cs.MM · 2026-05-08 · unverdicted · novelty 6.0

Modality representations share dominant semantic geometry but have an anisotropic residual gap; AnisoAlign corrects source representations boundedly using target geometry for unpaired alignment.

citing papers explorer

Showing 2 of 2 citing papers.

  • LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs? cs.CV · 2026-05-09 · unverdicted · none · ref 13

    LLaVA-UHD v4 reduces visual-encoding FLOPs by 55.8% for high-resolution images in MLLMs via slice-based encoding plus intra-ViT early compression while matching or exceeding baseline performance on document, OCR, and VQA benchmarks.

  • Anisotropic Modality Align cs.MM · 2026-05-08 · unverdicted · none · ref 5

    Modality representations share dominant semantic geometry but have an anisotropic residual gap; AnisoAlign corrects source representations boundedly using target geometry for unpaired alignment.