Conference
Open access
Sep 2026
Context-Adaptive World Models for Visual Out-of-Distribution Generalization
This thesis is developing a context-adaptive Mamba-based world model that infers K context vectors from short pixel-trajectory windows, and shows that its suboptimality is bounded by √K times the context-inference error along a Lipschitz chain through FiLM, the SSM, and the decoder.
Shubham Subhnil
· Proceedings of the Thirty-Fi... · 0 citations