- 🎓 M.S. in Information Science at UIUC, applying to Ph.D. programs in ML systems for Fall 2028.
- ⚙️ I work between the model and the machine: MoE inference and expert streaming, KV-cache compression, distributed training and RL rollout, GPU compilers and kernels.
- 🔬 Upstream-first: reproduce the failure in the real stack, fix it there, and ship the regression test with before/after numbers.
| Project | What I fixed | PR |
|---|---|---|
| PyTorch | int32 overflow in the cdist CUDA backward kernel, where indices wrapped negative past 2³¹ into an illegal memory access |
#198452 |
| LLVM | ValueTracking proves x != y from any condition on x - y that excludes zero (Alive2-verified); the Attributor's AAPointerInfo tracked non-pointer casts as pointers and asserted at PHIs, and now follows only address-space casts |
#225200 · #225290 |
| JAX | jax.scipy.linalg.lu accepts the batched (..., M, N) inputs its documentation promises |
#40931 |
| Triton | nested-loop fusion trusted an llvm.assume outside the loop and dropped a zero-trip guard; fp64 atomic_xchg on AMD buffer atomics crashed codegen |
#11521 · #11904 |
| Apache TVM | ONNX Hardmax lowers when the reduced axis has a symbolic extent | #20416 |
Every fix ships with a reproducer or regression test. Write-ups for each one are in the portfolio.
- Certified Sparse Attention — Certified Sparse Attention via Perturbed Retrieval — single author, arXiv 2026
- BreadthKV — Spend Bytes on Breadth: Precision–Count Trade-offs for Decode-Time KV Compression in Long Chain-of-Thought Reasoning — single author, arXiv 2026
- FinVault — Benchmarking Financial Agent Safety in Execution-Grounded Environments — co-first author, arXiv 2026 · code
- RVCFT — Reasoning-Visual Critical Token Fine-Tuning for Multimodal Reasoning — co-first author, under review at AAAI 2027
- VeriBRT — Plan-Guided, Evidence-Based Automated Bug Reproduction — co-first author, under review at ICSE 2027
- ARH — AI Research Helper: a CLI-first research assistant agent with tool use, plan/execute safety, three-layer memory, skill self-learning and multi-LLM fallback.
