{"slug": "radc-risk-aware-dual-caching-for-vision-language-test-time-adaptation", "title": "RADC: Risk-Aware Dual Caching for Vision-Language Test-Time Adaptation", "summary": "Researchers proposed RADC, a risk-aware dual caching method for test-time adaptation of vision-language models, detailed in arXiv paper 2610.06932v1. RADC adds a Semantic Foreground Cache that aggregates category-consistent spatial evidence from CLIP representations to build foreground prototypes alongside the global cache, and uses Gaussian Risk Admission to model multi-view representations as diagonal Gaussian distributions, jointly weighing class separation and feature uncertainty when admitting cache candidates. The authors report consistent state-of-the-art performance on cross-domain and out-of-distribution benchmarks.", "body_md": "arXiv:2610.06932v1 Announce Type: new \nAbstract: Cache-based test-time adaptation (TTA) for vision-language models is often hindered by background bias in global representations and unreliable entropy-based cache admission under representation variations. To address these limitations, we propose RADC, which enhances prototype learning through reliable dual caching. RADC introduces a Semantic Foreground Cache that aggregates category-consistent spatial evidence from CLIP representations, yielding foreground prototypes that complement the global cache while mitigating background interference. To reliably manage both caches, Gaussian Risk Admission models multi-view representations as diagonal Gaussian distributions and jointly considers class separation and feature uncertainty to prioritize reliable cache candidates. RADC integrates zero-shot logits with complementary global- and foreground-cache predictions for robust inference. Extensive experiments on cross-domain and out-of-distribution benchmarks demonstrate consistent state-of-the-art performance.", "url": "https://wpnews.pro/news/radc-risk-aware-dual-caching-for-vision-language-test-time-adaptation", "canonical_source": "https://arxiv.org/abs/2610.06932", "published_at": "2026-10-07 04:00:00+00:00", "updated_at": "2026-10-07 04:16:05.578909+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning", "ai-research", "large-language-models"], "entities": ["RADC", "CLIP", "arXiv", "Semantic Foreground Cache", "Gaussian Risk Admission"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/radc-risk-aware-dual-caching-for-vision-language-test-time-adaptation", "markdown": "https://wpnews.pro/news/radc-risk-aware-dual-caching-for-vision-language-test-time-adaptation.md", "text": "https://wpnews.pro/news/radc-risk-aware-dual-caching-for-vision-language-test-time-adaptation.txt", "jsonld": "https://wpnews.pro/news/radc-risk-aware-dual-caching-for-vision-language-test-time-adaptation.jsonld"}}