6 papers
Linger and Lose: Knowledge Collapse in Low-Bit Language Models
Prashanna Mani Paudel, Shivanand Venkanna Sheshappanavar
Training language models with ternary weights is commonly judged by loss and downstream accuracy, which record only a modest cost relative to full precision. We show that these met…
PlanSightRAG: A Visual-First Multimodal RAG for Automating Question Answering and Compliance Checking for Civil Standard Plans
Nabaraj Subedi, Shuvo Dip Datta, Ahmed Abdelaty +1
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…
Object Counting Across Modalities: Taxonomies, Benchmarks, Applications, and Open Challenges
Joana Konadu Owusu, Shivanand Venkanna Sheshappanavar
Object-counting methods have rapidly shifted from class-specific density regression to open-vocabulary, foundation-model-backed counters. These methods now enumerate instances from…
Parameter Golf: What Really Works?
Prashanna Mani Paudel, Shivanand Venkanna Sheshappanavar
How far can a language model improve under a strict artifact budget? Parameter Golf posed this question as an open community challenge in which participants trained the best langua…
When More Documents Hurt RAG: Measuring and Reducing Vector Search Dilution with Domain-Scoped Retrieval
Nabaraj Subedi, Ahmed Abdelaty, Shivanand Venkanna Sheshappanavar
Retrieval-augmented generation (RAG) degrades when applied to large, heterogeneous document collections. In RAG systems, dense similarity becomes less discriminative, causing top-$…
The Effect of Negation on CLIP in Medical Imaging: Limitations of Contrastive Language-Image Pretraining
Jasmine Vu, Shivanand Sheshappanavar
Large vision-language models like CLIP are increasingly used in medical imaging tasks due to their ability to align images and text without the need for extensive labeled data. Thi…