PhD Student · Computer Science · New York University
Yitao Long
I am a third-year PhD student in Computer Science at the Courant Institute at New York University.
I have the honor of working under the guidance of Prof. Dennis Shasha at New York University.
- Google Scholar
- GitHub
- X
- New York, NY
Research Interests
-
Foundation Models
- (Continued) pre-training and post-training methods
- Agents, memory and harness
-
Computational Biology
- Protein design
News
What's new
-
Two papers have been accepted at EACL 2027 Findings.
-
I will be joining Amazon as an applied scientist intern.
-
One paper has been accepted at EMNLP 2025 Findings.
-
I will be joining NEC Laboratories America as a research intern this summer 🎉 (Had a really great summer at Princeton ✨)
-
One paper has been accepted at CVPR 2025.
-
One paper has been accepted at EMNLP 2024.
-
Two papers have been accepted at ACL 2024.
-
Accepted the NYU CS PhD offer.
Experience
Research and industry
-
–
Applied Scientist Intern
Amazon
-
–
Research Intern
NEC Laboratories America
-
–
Publications
Papers and preprints
Preprints
5 papers
-
ProRetrieval: Learning to Orchestrate Hybrid Search via Executable Program Synthesis
arxiv:2608.27017 preprint.
-
OpenPM: Auditable Point-in-Time Evaluation for LLM Portfolio-Management Agents
arxiv:2608.09988 preprint.
-
Bayesian Data Reweighting Improves Multimodal Retrieval for Knowledge-Based Visual Question Answering
arxiv:2608.02907 preprint.
-
PuzzlePlex: Benchmarking Foundation Models on Reasoning and Planning with Puzzles
arxiv:2510.06475 preprint.
-
Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications
arXiv:2408.11878 preprint.
2027
2 papers
-
PivotSteer: Allocating Test-Time Compute through Sparse Reasoning Interventions
Findings of the European Chapter of the Association for Computational Linguistics (EACL Findings), 2027.
-
MedMMV: A Controllable Multimodal Multi-Agent Framework for Reliable and Verifiable Clinical Reasoning
Findings of the European Chapter of the Association for Computational Linguistics (EACL Findings), 2027.
2025
2 papers
-
FinLFQA: Evaluating Attributed Text Generation of LLMs in Financial Long-Form Question Answering
Findings of the Empirical Methods in Natural Language Processing (EMNLP Findings), 2025.
-
MMVU: Measuring Expert-Level Multi-Discipline Video Understanding
Computer Vision and Pattern Recognition (CVPR), 2025.
2024
3 papers
-
FinDVer: Explainable Claim Verification over Long and Hybrid-Content Financial Documents
Empirical Methods in Natural Language Processing (EMNLP), 2024.
-
FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains
Association for Computational Linguistics (ACL), 2024.
-
DocMath-Eval: Evaluating Math Reasoning Capabilities of LLMs in Understanding Long and Specialized Documents
Association for Computational Linguistics (ACL), 2024.
* Equal Contribution
Personal