content type videopublished February 23, 2026

Apple Workshop on Reasoning and Planning 2025: Reinforcement Learning for Long-Horizon Interactive LLM Agents

AuthorsPhilipp Krähenbühl (Apple)

Related readings and updates.

Dimensionality Reduction Meets Network Science: Sensemaking on UMAP’s kNN Graph

July 30, 2026research area Human-Computer Interaction, research area Methods and Algorithms

While UMAP is widely used for exploring high-dimensional data, typical workflows focus on its lower-dimensional embedding, largely overlooking the rich k-nearest-neighbor (kNN) graph that UMAP constructs internally. This graph encodes the data manifold in its original high-dimensional space, before the distortion that UMAP’s 2D projection introduces. We demonstrate the untapped potential of this internal representation, showing how standard graph…

Read more

MoMo: Dial Motion Mode in Robot Manipulation with Spatiotemporal Action Tokenization

July 30, 2026research area Human-Computer Interaction, research area Methods and Algorithms

To operate effectively across diverse contexts, robots must not only perform manipulation tasks accurately but also adapt how their actions unfold to the task, object, and interaction setting. We ask whether this execution-level variation can be learned as a reusable behavioral factor shared across tasks. We present MoMo, a two-stage imitation-learning framework consisting of a spatiotemporal action tokenizer and a behavior-cloning transformer…

Read more