About

I am a final-year Computer Science and Engineering student at the College of Engineering Munnar (APJ Abdul Kalam Technological University), focused on AI/ML and open-source systems.

Since February 2025, I have conducted undergraduate research under Prof. Rajeev Rajan at GEC Idukki, working on computer vision, medical image analysis, and representation learning for rare disease diagnosis and video activity understanding (see Publications).

I build and maintain open-source tools for AI agent reliability: CONTINUUM, an execution and recovery layer for long-running agents, and SNAGLINE, a real-time failure detector. I have also contributed 24 pull requests to TensorFlow (21 merged, 3 approved; see Code).

I chair the IEEE Computer Society chapter at my college.

Currently exploring robust evaluation and fault-tolerant architectures for autonomous agents, and open to research internships, collaborations, and engineering roles.

You can reach me at reach.anandhu.me@gmail.com.

GitHub / Hugging Face / LinkedIn / Google Scholar / Email

Recent updates

2026 Aug	Published Hunting Compiler Bugs and Numerical Traps in TensorFlow, detailing 24 PRs across Grappler, XLA, and numerical stability.
2026 Jul	Positional Prüfer Sequences for Ordered Trees, FSTTCS (under review, rebuttal).
2026 Jun	WaveCrossAttNet submitted to Springer Nature; H-CoAtNet in rebuttal at BMC Bioinformatics.
2026 Jan	HI-MobileNet published at 7th International Conference on Recent Advances in Intelligent Computational Systems (RAICS).
2025 Dec	Deep Temporal Representation Learning for Video Activity Recognition published at PICC.