Pith. sign in

Prompting large vision-language models for compositional reasoning.arXiv preprint arXiv:2401.11337

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

2 Pith papers citing it

fields

cs.CV 2

years

2026 1 2025 1

verdicts

UNVERDICTED 2

representative citing papers

Visual Compositional Tuning

cs.CV · 2025-04-30 · unverdicted · novelty 6.0

COMPACT synthesizes compositional visual instruction data to reduce VIT training data by 90% while achieving 100.2% of full performance across eight multimodal benchmarks.

citing papers explorer

Showing 2 of 2 citing papers.

  • Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval cs.CV · 2026-07-01 · unverdicted · none · ref 21

    FoCo learns composition for zero-shot CIR via text-anchored visual aggregation and context-conditioned semantic completion trained jointly with cross-instance contrastive loss, reporting SOTA on four benchmarks.

  • Visual Compositional Tuning cs.CV · 2025-04-30 · unverdicted · none · ref 14

    COMPACT synthesizes compositional visual instruction data to reduce VIT training data by 90% while achieving 100.2% of full performance across eight multimodal benchmarks.