Austin Senna Wijaya

New York, NY

I’m an undergraduate at Columbia University studying computer science. Most of my work is on agentic systems and retrieval, right now through agent-based retrieval and question-answering research at the Columbia Data, Agents, and Processes Lab (DAPLab). I’m also interested in machine learning, data infrastructure, and software observability.

experience

current Software Engineer Intern, Garner Health
current Data Agents Research Assistant, DAPLab
Machine Learning Research Assistant, Columbia Zuckerman Institute

selected publications

ICML 2026

LakeQA: An Exploratory QA Benchmark over a Million-Scale Data Lake

Haonan Wang, Jiaxiang Liu, Yurong Liu, Austin Senna Wijaya, Tianle Zhou, Eden Wu, Yijia Chen, Wanting You, Reya Vir, Daniela Pinto, Grace Fan, Yusen Zhang, Juliana Freire, and Eugene Wu

arXiv Bib HTML PDF

@inproceedings{wang2026lakeqa,
  title = {{LakeQA}: An Exploratory {QA} Benchmark over a Million-Scale Data Lake},
  author = {Wang, Haonan and Liu, Jiaxiang and Liu, Yurong and Wijaya, Austin Senna and Zhou, Tianle and Wu, Eden and Chen, Yijia and You, Wanting and Vir, Reya and Pinto, Daniela and Fan, Grace and Zhang, Yusen and Freire, Juliana and Wu, Eugene},
  booktitle = {International Conference on Machine Learning},
  year = {2026},
  month = jun,
  archiveprefix = {arXiv},
  primaryclass = {cs.CL},
  note = {ICML 2026},
}

VLDB DASHSys26

SANA: What Matters for QA Agents over Massive Data Lakes?

Austin Senna Wijaya, Jiaxiang Liu, Haonan Wang, and Eugene Wu

arXiv Bib HTML PDF

@article{wijaya2026sana,
  title = {{SANA}: What Matters for {QA} Agents over Massive Data Lakes?},
  author = {Wijaya, Austin Senna and Liu, Jiaxiang and Wang, Haonan and Wu, Eugene},
  journal = {arXiv preprint arXiv:2606.13904},
  year = {2026},
  archiveprefix = {arXiv},
  note = {VLDB DASHSys26},
}

bioRxiv 2026
under review

MINA: linear probes reveal coding-sequence family signal in frozen DNA encoders

Austin Senna Wijaya, H. Leung, and H. Yoo

DOI HTML PDF Code

selected projects

ResearcherX: local-first AI research IDE that answers questions against a bounded source library with graph-based RAG, flagging unsupported claims, contradictions, and citation drift in drafts. Finalist, Millard Chan Technology ‘99 Startup Competition; 2nd place, Columbia Lion Cage Startup Competition.
LakeAgent: deep-research system for answering analytical questions over structured and unstructured data lakes with provenance-backed outputs.