At the ETH Zurich Probabilistic Computing Hackathon I reframed the recursion in TRM/PTRM/GRAM as annealed sampling on an energy-based model, ran the whole loop on Extropic’s THRML simulator, and solved the hardest known Sudoku as a ground-state problem. The recursion buys roughly 7x fewer sampling sweeps, and when the network is confidently wrong the physics rescues it. It won 2nd place.

We bring LeJEPA to biosignals for the first time and show that the choice of self-supervised objective (masked reconstruction, LeJEPA, or a mix) trades latent-space structure for cross-montage generalisation, all on a 4.6M-parameter bi-Mamba model that is 377× cheaper than LaBraM.

How learned queries and cross-attention let LUNA decouple compute from electrode count, cutting FLOPs by 300× and GPU memory by 10× while still hitting state-of-the-art on TUAR.

An introduction to dilated causal convolutions and a look into how Temporal Convolutional Networks (TCN) function.

Finding the total number of multiply and accumulate operations in a LSTM layer, and looking at how many parameters there are in an LSTM cell.