Guess Random Additive Noise Decoder (GRAND) has emerged as a noise-centric universal decoder in classical systems, enabling low-energy, low-latency decoding of short codewords. It is particularly effective for handling hard-to-decode encodings, such as random linear codes, and for fast decoding of low-density parity-check (LDPC) codes. In this talk, Bruno will present his work extending GRAND to quantum error correction and entanglement purification. He'll show how this approach can be applied to hash-based purification protocols — previously regarded as impractical due to their prohibitive computational requirements. Bruno will also briefly discuss his current research direction of integrating noise statistics with hardware-accelerated decoders (GPUs and FPGAs) to achieve low-latency error correction necessary for quantum computation, where corrections must be performed rapidly in order to minimize decoherence.