Autonomous roofline-guided GPU kernel optimization. Profiles whether a kernel is compute- or memory-bound, proposes a hypothesis from the optimization guide, modifies the kernel, benchmarks against the reference, and iterates — committing, benchmarking, and reverting autonomously.

Context assembly for LLM code repair under strict token budgets. Parses Python repos into a knowledge graph (AST → calls, imports, inheritance), runs BM25/dense/BCA retrieval, assembles context that fits the budget, and measures whether better retrieval actually fixes more bugs.

Calibration-first retrieval stack for exoplanet atmospheres + NEOs. Forward-model wrappers, opacity ensembles, contamination latents, and reproducible inference in one package.

Reproducible, evaluable reinforcement learning environments for training agents on computer-use tasks. Structured framework for generating diverse task batches, running sandboxed episodes, and scoring agent performance.

Activation-aware compression for transformer models. Profiles which attention heads and MLP neurons are most active on your data distribution, then applies more aggressive compression to dormant ones — better task-specific quality at the same compression ratio.

Multi-agent simulation measuring LLM strategic behavior in resource competition under asymmetric information and institutional constraints.

Object-storage-first hybrid search engine w/ IVF vector search + BM25 full‑text with metadata filters, immediate write visibility via a hot index, and async merge to an S3‑backed cold index. Features adaptive nprobe, NVMe caching, and RRF fusion for robust relevance.

Mech interp playground for tracking ICL emergence and induction heads. Built to understand what transformers actually learn during in-context learning.

Minimal FSDP implementation. Stripped down to the essentials so you can actually see how parameter sharding works under the hood.

CUDA-accelerated BM3D denoising. Gets you ~20% speedup over OpenCV and handles real-time video.

Vector db built from scratch. HNSW, KD-tree, IVF- multiple indexing strategies with proper metadata filtering because most vector DBs overcomplicate the basics.