VIP evolves text prompts using visual cues and saliency-aware aggregation inside dino.txt to deliver 1.4-8.4% higher mIoU on dense vision-language tasks with low overhead.
Adapting vision-language models without labels: A comprehensive survey.arXiv preprint arXiv:2508.05547
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
ComMem proposes complementary fast visual cache and slow textual prototype memories for test-time adaptation of VLMs, claiming superior performance on 15 benchmarks under distribution shifts.
citing papers explorer
-
VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference
VIP evolves text prompts using visual cues and saliency-aware aggregation inside dino.txt to deliver 1.4-8.4% higher mIoU on dense vision-language tasks with low overhead.
-
ComMem: Complementary Memory Systems for Test-Time Adaptation of Vision-Language Models
ComMem proposes complementary fast visual cache and slow textual prototype memories for test-time adaptation of VLMs, claiming superior performance on 15 benchmarks under distribution shifts.