Test-time adaptation (TTA) for vision-language models (VLMs) is usually studied in a fully unsupervised regime, where adaptation relies on pseudo-labels, confidence scores, or entropy computed by the model itself. This is a severe restriction on hard shifted samples: the model is asked to repair its own uncertain predi...
Jihwan Bang, Sumyeong Ahn, Hwanjun Song et al.· 0 citations
A novel reference-free preference optimization framework D UAL R EFORM that generates pseudo reference passages from commonly-encountered conversational datasets containing only queries and responses that achieves 96.9–99.1% of the retrieval accuracy attainable only with reference passages.
Doyoung Kim, Youngjun Lee, Joeun Kim et al.· 0 citations
TimelyRAG is proposed, a retriever-agnostic framework that incorporates temporal distance into ranking to align queries with version-appropriate documents, and TimelyQABench is introduced, the first benchmark for regulation-heavy domains with overlapping-evolving challenges.
Youngeun Nam, Joeun Kim, Hwanjun Song et al.· Conference on Empirical Meth...· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.