stochastic

Introduces Stochastic Token Steering (STS) and Stochastic Block Steering (SBS) for LLM activation steering, which probabilistically gate steering signals per token or per sequence. Shows that steering only 50% of tokens recovers most of the dense-steering effect while preserving fluency, and that the behavioral outcome is rate-limited by cumulative signal dosage.

VaSE is a training-free method for KV cache eviction that protects large-magnitude value states and introduces stochasticity to improve reasoning model accuracy under compression, outperforming existing methods.

Thermocompute is a PyTorch emulator for thermodynamic probabilistic computing that enables neural network layers to achieve constant modeled physical time inference by exploiting parallel thermodynamic substrate, with immediate GPU-usable stochastic layers.