Author

Tie-Jun Ma

h-index 5 View on Semantic Scholar

We have 2 of 12 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Sep 2026

Metric Algebra: Embedding-Independence in Vector Databases

Vector databases are increasingly central to retrieval applications, yet deployments remain embedding-siloed: different databases store vectors produced by different embedding models and ANN pipelines, making cross-database search ill-defined or forcing expensive re-embedding and index rebuilds. We propose metric al...

Tian-Jian Yang, Yang Cao, Bei-Ning Yang et al. · Proceedings of the ACM on Ma... · 0 citations

#artificial intelligence May 2026

Summoning the Oracle to Slay It: Mitigating Look-Ahead Bias in Financial Backtesting with Large Language Models

FinCAD is proposed, an inference-time adaptation of Context-Aware Decoding that attenuates contributions from memorised historical outcomes without retraining and raises the subset-averaged in-sample/out-of-sample Spearman correlation on an eleven-model leaderboard.

Weixian Waylon Li, Mengyu Wang, Tiejun Ma · arXiv.org · 2 citations