We have 5 of 9 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
This work introduces MASDR-RAG (Metadata-Scoped Domain Retrieval for RAG) as a controlled testbed and finds hard partitioning to be unsafe, whereas training-free soft scoping is safe when the scope structure is real.
Civil infrastructure compliance checking has long relied on engineers manually reading legacy 2D plans; however, OCR-based automation strips away the geometry and layout essential for interpreting these plans. We present a Visual-First Multimodal Retrieval-Augmented Generation (RAG) framework called PlanSightRAG. It in...
This work measures knowledge capacity, the factual bits stored per parameter, on synthetic biographies with known information content and suggests judging low-precision training by retained capacity during training rather than final loss.
It is shown that most techniques'gains shrink when re-measured among competitive submissions, isolating the few methods that help regardless of the surrounding stack, and that most techniques'gains shrink when re-measured among competitive submissions.
A five-axis taxonomy (modality, mechanism, prompting, supervision level, and generalization setting) is introduced to audit the literature across application domains, including microscopy, remote sensing, crowd counting, and agriculture, and formalizes prevailing challenges into six structural contradictions.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
