Research
Papers, preprints, talks, and references from the VideoDB research archive.
Research note / May 15, 2026
A practical workflow for evaluating video VLM setups with VideoDB and Langfuse, from task definition and dataset design to tracing, scoring, and deployment decisions.
arXiv preprint arXiv:2604.11177 / 2026/4/13
Benchmarks how internal reasoning traces affect video scene understanding in Gemini models, including where quality gains plateau and how tight budgets increase compression-step hallucination.
arXiv preprint arXiv:2502.06445 / 2025/2/10
Introduces an open-source benchmark for evaluating VLMs on OCR tasks in dynamic video environments across 1,477 manually annotated frames.
Systems 9(3), 53 / 2021/7/13
Presents an agent-based extension of epidemic modeling for confined spaces, comparing black-box and glass-box views while simulating lockdowns, social distancing, hygiene, quarantine, and hospitalization policies.
IEEE Transactions on Computational Social Systems 5(1), 277–288 / 2018/1/17
Models emergency evacuations with agents whose panic behavior is shaped by psychological and physical factors, then uses simulations to identify bottlenecks and compare evacuation strategies.
PyCon India talk / 2015
A practical talk that starts from rule-based NLP features and WordNet, then motivates distributed word representations and deep learning for solving logical puzzles from natural language.
