Logan Luna
Logan Luna
I study how semantically informative training signals can be quantified and incorporated into the training and generation of mathematical reasoning models.
Symbolic feedback rewards output that compiles or type-checks, but that does not certify that it expresses the intended mathematics.
Erdős's conjecture on large totient fibers
Full replay →Started a contract role supporting Meta FAIR as a Research Collaborator V, contributing to the ATLAS project. ATLAS, the Autoformalized Textbook Library At Scale, is a verified Lean 4 library built with AutoformBot, an open-source multi-agent framework that translates informal textbook mathematics into machine-checked definitions and proofs.
Research
Under reviewICLR 2027
Contribution: RL pipeline and reward, BEq+ extension, distillation pipeline and dataset, Semantic Alignment Model. Results: pass@4 semantic correctness from 15.7% to 36.7% standalone (above GPT-5.6-Sol and Codex); 41.9% to 79.8% as a Claude Code skill.
ConferenceIEEE SoutheastCon 2025, Best Paper Award
99.68% multi-class accuracy on 2.18M CIC-IDS2018 flows, against 88% for prior DQN-based detection and 98.4–99% for tree-ensemble and random-forest IDSs; SHAP attribution of the learned policy.
JournalIEEE Access, 2026
97.5% collision-avoidance success over 1,000 deterministic GEO episodes, 76.8 and 70.0 percentage points above the rule-based and impulsive Δv baselines.

Under reviewACM International Conference on Trustworthy and Responsible AI and Computing Systems
A verification framework for compiling Isaac Lab policies directly into Crazyflie nano-UAV firmware, with executable checks from observation replay to source-to-binary traceability; 2–3 cm hover altitude error onboard.
ConferenceIEEE SoutheastCon 2025, Concord, NC
91.2% reduction in total sonar processing time (13.1% in filtering alone) against image-based CV processing, while preserving target structure the image pipeline removed.
WorkshopIEEE eScience 2026 (ReWorDS Workshop), Naples, Italy
One analytical core carried across spacecraft telemetry, ECG, and climate data with small domain adapters and no core changes; bit-identical outputs under fixed seeds.
Research
AI4Math
AI4Math
AI4Math
Earlier work