This is the official implementation of our ACL 2025 Main paper "Balancing Diversity and Risk in LLM Sampling".

Real-time BCI platform used to assess performance of: (1) discrete trial vs continuous pursuit BCI training (2) source (EEG source imaging) vs sensor space decoding (3) continuous robotic arm control

Phase-aware context window governance framework for Large Language Models (LLMs). Provides invariant context length caps, entropy-based stability control, and probabilistic guarantees against degraded (fragmentation) states for production LLM systems.