Nikhil Reddy
Pottanigari.

Text, Pixels, or Both? Evaluating Input Representations for Multimodal Document QA

Comparing text, page images, and combined inputs for document QA, including their accuracy, latency, and cost trade-offs.

Preserving What Matters: Semantic Scaffolds Beyond Saturation in Summarization Evaluation

Evaluating summary quality through preservation of facts, questions, and entity attributes when conventional scores saturate.

Splitting Documents at Lower Cost: Multi-Split Boundary Decisions for LLM-Based Page Stream Segmentation

Predicting multiple document boundaries in one model call to improve the accuracy–efficiency trade-off in page stream segmentation.

Applied Research Scientist · Document intelligence, multimodal retrieval, and trustworthy AI.

Graduate Student Researcher · Legal AI and evaluation of language models.

Software Engineer II · Semantic search, recommendations, and product engineering.