pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

LVLM-Aided Alignment of Task-Specific Vision Models

cs.CV · 2025-12-26 · unverdicted · novelty 7.0

LVLM-VA aligns small vision models with human knowledge using an LVLM bidirectional interface, reducing spurious features and group biases on synthetic and real datasets without fine-grained feedback.

citing papers explorer

Showing 1 of 1 citing paper.

  • LVLM-Aided Alignment of Task-Specific Vision Models cs.CV · 2025-12-26 · unverdicted · none · ref 9

    LVLM-VA aligns small vision models with human knowledge using an LVLM bidirectional interface, reducing spurious features and group biases on synthetic and real datasets without fine-grained feedback.