vision-language models contrastive learning explainable AI medical imaging diffusion & inpainting
Nine years of production work, now mostly in service of shipping research.
Three first-author papers in computer vision and multimodal ML. Full list with abstracts and BibTeX: suxrobgm.net/research · Google Scholar
|
MorphoCLIP
Matches microscopy of drug-perturbed cells to plain-language descriptions of the treatment. Encoders stay frozen and only projection heads train, so it fits one consumer GPU. CPJUMP1 · 51 plates · 3M+ images
|
Localize, Don't Beautify
Ask a commercial editor to change one facial feature and it beautifies the whole face. Benchmarks three localization strategies; plain masking beat prompt-only steering. 6 editors · 196 edits · identity scored
|
MelanomaNet
Skin lesion classification across all nine ISIC 2019 classes. GradCAM++ attention is scored against the ABCDE criteria clinicians already use, so interpretability gets a number. ISIC 2019 · 25,331 images · 0.856 F1
|
Models built against real inputs rather than a clean benchmark split.
|
Pulls studies straight from hospital PACS over DICOM and runs detection models over them. Predictions show up as overlays in the viewer, alongside measurement and segmentation tools. HIPAA-ready.
|
Point a camera at a bookshelf and get back a list of what is on it. YOLO segmentation cuts out each spine, then a vision-language model reads the title and author off it.
|
Kept separate from the published work above.
|
Lightweight monocular depth estimation. Holds accuracy at 14.3M params where Depth Anything V2 needs 24.8M, runs 72% faster, and comes out slightly ahead on relative error on NYU Depth V2.
|
Reproduction of FSRCNN (Dong et al., ECCV 2016) for super-resolution at 2x/3x/4x. Upsampling is learned end to end, which is where the 40x speedup over SRCNN comes from (+1.78 dB PSNR on Set5).
|
60K+ Users on Meat.gg |
10+ Shipped Projects |
100% Upwork Job Success |
|
Multi-tenant TMS for intermodal trucking. Wired into the big load boards (DAT, Truckstop), with ELD/HOS compliance, Stripe Connect, route optimization, and live tracking. DDD + CQRS architecture.
|
Meat.gg Community platform for Counter-Strike 2 servers. Profiles and messaging, a shop running on Stripe, and a native plugin that lets admins ban, report, and moderate from inside the game.
|
|
Scans a project's dependencies across 8+ ecosystems for known vulnerabilities via OSV.dev, and doubles as an encrypted secrets vault: AES-256-GCM, one-time secret sharing, CI/CD token injection.
|
Drag-and-drop form designer that outputs JSON schema with a runtime renderer, so admin dashboards stop needing hand-written forms.
|
|
Hearts of Iron IV: Economic Crisis Steam Workshop · Releases Large-scale mod with custom mechanics, AI behaviors, and balance systems. 
|
Chestnut (MMO) Play Real-time MMO with authoritative server, custom physics, and sync for 100+ concurrent players with Web3 integration. 
|
|
ChessMate Repo Online chess platform with AI opponents, rated/friendly PvP matchmaking. 
|
Maze Repo 2D puzzle game with AI pathfinding and level progression. 
|
Open to research collaborations and PhD-adjacent work. Happy to talk about computer vision, multimodal ML, and explainable AI, or about .NET, TypeScript, and game dev.
