← back · workshop
Things I've built & explored
A working catalog — research systems I built end-to-end, weekend prototypes that never quite finished, and forks I keep around because the code taught me something. Sorted by intent, not by polish.
★ Featured
-
SemanticSentry
2025 · library · under reviewResearch code and pre-registrations accompanying our BlackboxNLP @ EMNLP 2026 submission, Geometric Drift Metrics are Insufficient. Implements CKA, NPS, and isotropy diagnostics; the matched-Frobenius perturbation and matched-corpus MLM controls; the cross-validated linear-probe pipeline; and pre-registration documents for every experiment in the paper.
- python
- pytorch
- faiss
- transformers
- clip
- w&b
- mlflow
-
AdLovin
Oct 2025 · CalHacks-12 winnerA multi-agent advertisement analysis pipeline combining computer vision, vector retrieval, and LLM reasoning to extract marketing and business signals from video. Reaches 70–90% frame deduplication and reduces vision-API cost by roughly 70% while preserving downstream extraction quality. The pipeline behind our ACM MM 2026 paper, AdaFrame.
- python
- claude api
- chromadb
- opencv
- pytorch
- hubert
- ffmpeg
01 : Research Systems
-
Wally
2025 · autonomous roboticsAutonomous mobile robot built during my robotics-research internship at Wabash. Fuses GPS, computer vision, and LiDAR streams for real-time outdoor navigation, reaching 97% obstacle detection and avoidance with ~2 m positional precision in the field. Includes emergency-stop protocols and a configuration-driven control stack.
- python
- ros
- opencv
- lidar
- gps
- pid control
-
Financial Knowledge Graph
2025 · retrieval · ragEnd-to-end platform for extracting financial entities from unstructured filings, storing them as vector embeddings alongside a typed knowledge graph, and exposing an intelligent query layer that combines graph traversal with semantic retrieval.
- python
- neo4j
- chromadb
- transformers
- langchain
-
ADos
Jan 2026 · Gemini 3 hackathonAI-powered system for automatic video advertisement analysis built on top of Google's Gemini 3 multimodal models — extracting structured signals about messaging, pacing, and brand cues from raw advertising footage. A follow-up to AdLovin, swapping in Gemini's native long-video reasoning.
- python
- gemini api
- ffmpeg
- chromadb
02 : Experiments & Prototypes
-
RacePace
Apr 2026 · multi-agentSim-racing telemetry copilot. Three agents observe a live sim session — one watches inputs and pace, one watches the car state, one talks to the driver — coordinating to surface coaching cues mid-stint. Built to test whether cooperative agents beat a single oracle on a hard real-time perception task.
- python
- multi-agent
- llm
- realtime
The rest lives at
github.com/abtonmoy —
mostly course work, half-finished branches, and
shameful formative early commits.