ICFD-31k
A large-scale benchmark for real-time conversational fraud detection.
IJCAI–ECAI 2026 · AI for Social Good Special Track
Hello 👋
I am Rishi Ahuja, a 19-year-old undergraduate researcher pursuing a B.Tech. with Research in Information Technology at NIT Jalandhar, and an incoming intern at Cisco.
My research focuses on building and evaluating reliable AI systems, with current work in language-model evaluation, temporal retrieval, and conversational fraud detection.
Featured research
ScopeBench-PR
★ Awarded Best Paper Presentation
Measuring whether LLM reviewers respect a paper’s stated scope.
GlobalSouthAI Workshop · IJCAI–ECAI 2026
Temporal Retrieval
Selective retrieval for time-series forecasting beyond long-context scaling.
ICLR 2026 · TSALM Workshop
Updates and awards
- Selected to attend the Google DeepMind APAC Research Symposium 2026 at Google Ananta.
- Selected to present ICFD-31k at ConfAI, Plaksha University.
- Selected as a summer intern at Cisco.
- Served as a reviewer for GlobalSouthAI at NeurIPS 2026.
- ICFD-31k published in the IJCAI–ECAI 2026 proceedings.
- Presented ICFD-31k at IJCAI–ECAI 2026 in Bremen.
- Received the Best Paper Presentation Award and placed runner-up in the GlobalSouthAI 3MT competition.
- Presented ScopeBench-PR at GlobalSouthAI, IJCAI–ECAI 2026.
- Served as a reviewer for the FSMD Workshop at ICML 2026.
- ScopeBench-PR accepted at GlobalSouthAI, IJCAI–ECAI 2026.
- Awarded an IJCAI–AIJ grant.
- ICFD-31k accepted to the IJCAI–ECAI 2026 main conference.
- Presented retrieval-augmented time-series forecasting research at the ICLR 2026 TSALM Workshop.
- Selected for and attended YC Startup School India 2026 in Bengaluru.
- Awarded an ICLR 2026 grant.
- Temporal retrieval paper accepted at the ICLR 2026 TSALM Workshop.
- Organised HackMol 7.0 at NIT Jalandhar and coordinated the judges.
- Won first place in the AWS Partner Track at HackCBS 8.0.
- Won first place in the Qyrus sponsor track at HackCBS 8.0.
- Placed second at the Level SuperMind National Hackathon in Mumbai.
- Placed third as a solo participant at the PEC × Prajna AI Hackathon.
Experience
Cisco
-
Summer Intern
Machine and Hybrid Intelligence Lab
Northwestern University
-
Visiting Scholar · Undergraduate Researcher
Zenbase Singapore
-
DevOps Engineer
Annam AI, IIT Ropar
-
Entrepreneur in Residence
-
Research Intern
Stack Wealth
-
Flutter Intern
Level SuperMind
-
Frontend Intern
GDGC, NIT Jalandhar
-
Mobile Development Lead
-
Core Member · Mobile Development
Writing
Towards the Modern Transformer Architecture
Tracing how the 2017 Transformer evolved into the recipes used by modern frontier models — norms, activations, attention variants, RoPE, KV cache, and more.
Jul 2026
You Don't Know WebSockets. Yet.
The WebSocket protocol, handshake to frames, and how bidirectional sockets actually work.
Aug 2025
Go Beneath the Abstraction: Building Interactive UIs with FernKit
Building interactive UIs from scratch in C++ with FernKit’s renderer and widgets.
Aug 2025
Academics
NIT Jalandhar
B.Tech. with Research in Information Technology
2024–2028
About
01 / Background
I am a 19-year-old undergraduate researcher pursuing a B.Tech. with Research in Information Technology at NIT Jalandhar. I study how AI systems can be evaluated reliably against the claims made about them.
02 / Research
My current work spans three projects: ICFD-31k in conversational fraud detection, ScopeBench-PR in scope fairness for LLM-assisted peer review, and selective retrieval for time-series forecasting. Across them, I care about reliable evaluation under realistic conditions.
03 / Beyond Research
I write about machine learning, systems, and building software from first principles. The full archive is in Writing. I also teach mobile development and help organise developer events through Community.
Outside work, I train hard in the gym and have lost a significant amount of weight over the past year.