Popular repositories Loading
-
disco-torch
disco-torch PublicA PyTorch port of DeepMind's Disco103 — the meta-learned reinforcement learning update rule from Discovering State-of-the-art Reinforcement Learning Algorithms (Nature, 2025).
Python 11
-
sandcastles
sandcastles PublicA Python tool that compiles neural network weights directly into synthesizable Verilog for the ASIC toolchain.
-
-
prescient-credit
prescient-credit PublicIn progress work on LLM RL, not ready for its close up yet
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.



