Université de Technologie de Compiègne

LLM-driven interactive narrative systems have been hard to compare because each experience manager is tied to its own bespoke scenario. An LLM-based narrative platform turns experience managers into interchangeable modules over a shared symbolic world model of facts, operations and goals, and every applied operation carries explicit preconditions and effects, so any session can be replayed as a common state-transition path. On a Little Red Riding Hood scenario, open generation, Monte Carlo repair and autonomous characters each ran 100 simulated sessions, and no manager led on all four properties: player agency, manager controllability, author intent and robustness.

LLM-driven interactive narrative systems have been hard to compare because each experience manager is tied to its own bespoke scenario. An LLM-based narrative platform turns experience managers into interchangeable modules over a shared symbolic world model of facts, operations and goals, and every applied operation carries explicit preconditions and effects, so any session can be replayed as a common state-transition path. On a Little Red Riding Hood scenario, open generation, Monte Carlo repair and autonomous characters each ran 100 simulated sessions, and no manager led on all four properties: player agency, manager controllability, author intent and robustness.

This work adapts modern binary neural networks (BNNs) to event-camera data, introduces the Polar-wise Binary Event Volume (PBEV) binary representation and binarizes the network input layer, and shows that with knowledge distillation and RGB cross-modal pretraining BNNs match or exceed full-precision ResNet-18 on N-Caltech101 and N-ImageNet-mini classification, with a best result of 90.58% at fewer operations.

This work adapts modern binary neural networks (BNNs) to event-camera data, introduces the Polar-wise Binary Event Volume (PBEV) binary representation and binarizes the network input layer, and shows that with knowledge distillation and RGB cross-modal pretraining BNNs match or exceed full-precision ResNet-18 on N-Caltech101 and N-ImageNet-mini classification, with a best result of 90.58% at fewer operations.