Suryansh Sijwali

Penn State CS · AI/ML Engineer & Researcher

IEEE AITest 2025 · LCTES 2026 · Patishnock Undergraduate Research Award

Currently working on
Causality-aware security reward design for RL-based C code generation.
Recently submitted
Match Your Loss to Your Cost · CNSM 2026

Research that ships and systems that get used.

GitHub LinkedIn ORCID Scholar Email
About

A little context

I'm a Computer Science student at Penn State, passionate about building intelligent systems at the intersection of AI research and practical software engineering. Currently focused on LLM-powered code analysis, full-stack development, and exploring how AI can solve real-world problems in manufacturing, education, and beyond.

Education

B.S. Computer Science

School
Penn State University · Schreyer Honors College · College of Engineering · Eberly College of Science
Expected
Expected May 2027
Minors
Mathematics · Computer Engineering · Computational Cybersecurity
Selected work

Warren

Building

In active development for Mind the Product's World Product Day 2026

Turn your Wikipedia rabbit hole into a beautiful, shareable map. Your actual clicked path becomes a bright animated spine; all other links sit as faint context so the graph never becomes a hairball.

Match Your Loss to Your Cost

Submitted

CNSM 2026 Submission

Decision-aware traffic forecasting for backbone capacity planning. Asymmetric losses and conformal capacity bands trained against operator cost, not RMSE. Three real backbones, 20 seeds, paired-bootstrap CIs.

Abilene +76%
GÉANT +75%
CESNET +54%

Operator-cost reduction vs MSE-trained LSTM, cusp-linear loss at top operator asymmetry

Scheduled Partial-Credit RL for Reliable Code Generation with Small Language Models (WIP)

Published

LCTES 2026

Reliability-first RL for small language models in code generation. Joint reward R = 0.6·R_func + 0.4·R_sec with a five-stage partial-credit functional ladder.

syntax error 0.0
valid syntax 0.2
runs, no crash 0.4
produces output 0.6
passes k of T 0.6 + 0.4·k/T

All research →

All engineering →

Writing

Recent notes

All writing →