./vla-book-picking
2026Fine-tuning ACT and SmolVLA to pick colored books off a shelf in MuJoCo on one 5070 Ti. Peaked at 60%, then found out the model had memorized shelf slots. Mostly a negative result, written up in full.
whoami
i write deep-learning kernels (layernorm, softmax, etc.) for TI's DL library, targeting inference on TDAx edge accelerators. on the side, i train small robot models and work on the infrastructure to deploy them.
work ML inference kernels @ Texas Instruments into robot learning, edge inference, SIMD, low-precision formats langs c · c++ · python · rust
ls ~/projects | head -4
Fine-tuning ACT and SmolVLA to pick colored books off a shelf in MuJoCo on one 5070 Ti. Peaked at 60%, then found out the model had memorized shelf slots. Mostly a negative result, written up in full.
Pipelines that turn egocentric human video into VLA training data, plus a harness to measure whether a processing choice actually helps the policy. Splits GPU work from cheap CPU ablations.
Kubernetes-native orchestration for robot inference. Robot, Model and Fleet CRDs, an operator loop, and an edge agent that syncs and loads models on the robot.
Fantasy Premier League lineups solved as an MILP across multiple prediction horizons. Bolting on an auto-research loop so it can swap in better predictors over time.
ls -t ~/blog | head -2