ManiSkillFormer: Demonstration-Free Compositional Manipulation via Task-Conditioned Geometric Contracts

Towards eliminating arbitrary stipulations related to parameters: linguistic innateness and the variational model

Collapsing the Hidden-Set Convex-Cover Inequality

: A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding

Knowledge Transfer, Alignment, and Interpretability: Modular Architectures and Inductive Biases in Deep Reinforcement

ManiSkillFormer: Demonstration-Free Compositional Manipulation via Geometric Contracts and Agentic Skill Graph

Adapting robotic manipulation to new objects and tasks often requires additional demonstrations or manual engineering. Reusable manipulation skills can reduce this effort, but adapting these skills to new scenes remains challenging. We present ManiSkillFormer, a framework for demonstration-free and compositional manipu...

BIMgent: Generating Building Models via Computer-use Agents