I'm a junior studying computer science and electrical engineering at UC Berkeley. Currently, I am interning at Q Labs, focusing on efficient pretraining for generalization.
At Berkeley Sky Computing Lab, I've been fortunate to collaborate with Mert Cemri on ML systems and evolutionary algorithms. Previously, I worked with Lisa Dunlap at Berkeley AI Research on model behavior and safety. I've also trained and harnessed agents at Standard Kernel, developed AI tooling at AMD, and built evals at AfterQuery.
In my spare time, I enjoy playing golf, basketball, chess, and (occasionally) poker.
Latest
- Atlas for ML Research
- Hadamard and Monarch: Compressing GPT-2 Small
- Moravec's Paradox
- Autoencoders
- Is EAGLE-3 Speculative Decoding Lossless?
- From QK-Clip to Muon-Clip
- Parallel Transformer Blocks
- Token Embeddings Violate the Manifold Hypothesis
- Reflections on BayLearn
- Our project, Dementor, was accepted to BayLearn 2025 as an oral presentation (<5%)!
- Representative Sampling of High-Dimensional Point Sets
- We release VADER, a security benchmark for LLMs!
