ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control
From Daily Paper Cast by Jingwen Liang, Gengyu Wang
May 2, 2026 · 27 min · Episode 1826
About this episode
The episode discusses the ExoActor framework for improving humanoid control through exocentric video generation.
🤗 Upvotes: 32 | cs.RO Authors: Yanghao Zhou, Jingyu Ma, Yibo Peng, Zhenguo Sun, Yu Bai, Börje F. Karlsson Title: ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control Arxiv: http://arxiv.org/abs/2604.27711v1 Abstract: Humanoid control systems have made significant progress in recent years, yet modeling fluent interaction-rich behavior between a robot, its surrounding environment, and task-relevant objects remains a fundamental challenge. This difficulty arises from the need to jointly capture spatial context, temporal dynamics, robot actions, and task intent at scale, which is a poor match to conventional supervision. We propose ExoActor, a novel framework that leverages the generalization capabilities of large-scale video generation models to address this problem. The key insight in ExoActor is to use third-person video generation as a unified interface for modeling interaction dynamics. Given a task instruction and scene context, ExoActor synthesizes plausible execution processes that implicitly encode coordinated interactions between robot, environment, and objects. Such video output is then transformed into executable humanoid behaviors through…
People in this episode
Hosts: Jingwen Liang, Gengyu Wang
Topics covered
- humanoid control
- video generation
- robot interaction
- task execution
- machine learning
Keywords
- ExoActor
- humanoid control
- video generation
- robot behavior
- interaction dynamics
Mentioned in this episode
Organizations: Arxiv
More episodes of Daily Paper Cast
- EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments · June 13, 2026 · 24 min
- MiniMax Sparse Attention · June 13, 2026 · 26 min
- SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning · June 13, 2026 · 23 min
- InterleaveThinker: Reinforcing Agentic Interleaved Generation · June 13, 2026 · 21 min
- FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents · June 13, 2026 · 23 min
- Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? · June 13, 2026 · 20 min
Explore listener stats, chart rankings, contacts and more on the Daily Paper Cast podcast page.