EPISODE · Jun 3, 2026 · 10 MIN
EP224: HaM-World
from Learning GenAI via SOTA Papers - Video · host Yun Wu
Title: HaM-World: Soft-Hamiltonian World Models with Selective Memory for PlanningSource: http://arxiv.org/abs/2605.05951v1Summary:This paper introduces a foundational architectural primitive for world models by combining Hamiltonian geometric structures with Mamba-based selective memory to stabilize long-horizon planning. It provides agents with a structured latent state for dynamics, rewards, and action search, significantly improving robustness in out-of-distribution planning tasks.
What this episode covers
Title: HaM-World: Soft-Hamiltonian World Models with Selective Memory for PlanningSource: http://arxiv.org/abs/2605.05951v1Summary:This paper introduces a foundational architectural primitive for world models by combining Hamiltonian geometric structures with Mamba-based selective memory to stabilize long-horizon planning. It provides agents with a structured latent state for dynamics, rewards, and action search, significantly improving robustness in out-of-distribution planning tasks.
NOW PLAYING
EP224: HaM-World
No transcript for this episode yet
Similar Episodes
Apr 21, 2026 ·13m
Apr 19, 2026 ·16m
Apr 17, 2026 ·13m
Apr 13, 2026 ·11m
Apr 11, 2026 ·16m