Research
Work across time-series forecasting, retrieval-augmented systems, and trustworthy conversational fraud detection. I recently presented my ICLR 2026 poster, and my IJCAI-ECAI 2026 paper ICFD-31k has been accepted for presentation in Bremen.
Research papers
Jul 21, 2026
Do LLM Reviewers Respect Scope? ScopeBench-PR: A Benchmark for Scope Fairness in Peer Review
Accepted to GlobalSouthAI (IJCAI-ECAI 2026) · GlobalSouthAI @ IJCAI-ECAI 2026
Accepted at GlobalSouthAI @ IJCAI-ECAI 2026. A counterfactual benchmark for measuring whether LLM reviewers respect papers' stated geographic, linguistic, and empirical scope.
Apr 30, 2026
ICFD-31k: A Large-Scale Dataset and Benchmark for Real-Time Conversational Fraud Detection
Accepted to IJCAI-ECAI 2026 · IJCAI-ECAI 2026 Special Track (Main Conference)
Accepted at IJCAI-ECAI 2026 main conference special track. A large-scale Indian bilingual fraud-call benchmark with streaming labels and rationales.
Mar 2, 2026
Retrieval Mechanisms Surpass Long-Context Scaling in Time Series Forecasting
ICLR 2026 · 1st ICLR Workshop on Time Series in the Age of Large Models
Published at the ICLR 2026 TSALM Workshop. A paper arguing that selective retrieval beats brute-force long context in time-series forecasting.