Researcher @UCLA-StarAI. Interested in ML and optimization problems.
Pinned Loading
-
coup-RL-bot
coup-RL-bot PublicDeep RL strategies for the card game Coup. Works for 2-6 player environments with a playable human CLI. 1v1 the bot at https://coup-1v1-online.onrender.com/.
Python
-
heston-regime-lab
heston-regime-lab PublicStochastic-volatility research lab that calibrates the Heston model to SPX options, detects market regimes via hidden Markov models, and visualizes results through a live React dashboard and FastAPI.
Python
-
transformer-inference-lab
transformer-inference-lab PublicA from-scratch BERT-style transformer in PyTorch, instrumented and optimized for inference research; achieving 5.4X throughput and 3.47X latency improvements while preserving output parity across a…
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.
