Benchmark Dataloader
A benchmarking setup for multimodal dataloaders, built to surface throughput bottlenecks before they become training-time surprises.
Member of Technical Staff at Datology
I build multimodal systems at Datology. The work spans pretraining, VLM evaluation, distributed training, and research infrastructure. Recent projects range from data curation systems and vLLM eval paths to multi-node training and agentic tooling that shortens experimental loops.
I care most about shrinking the distance between a data decision and a trustworthy model comparison.
DatBench is the clearest public example of the kind of work I care about: evaluation systems that shape model decisions and still stay inside the loop.


A benchmark and evaluation framework for vision-language models built around discriminative tasks, faithful scoring, and practical efficiency.
S. Joshi, H. Yin, R. Adiga, R. Monti, A. Carranza, A. Fang, A. Deng, A. Abbas, et al.
Three operating lanes keep the loop moving. Together they cover benchmark design, data handling, and launch.
Built evaluation paths that keep model comparisons useful for curation decisions and model iteration.
Built ingestion and export paths that make large multimodal corpora easier to train on and inspect.
Added vLLM eval support and hardened multi-node launch plus checkpoint behavior for faster experimental turnover.
Open work that still points in the same direction as the current systems surface. Fewer pieces, clearer signal.