Pith. sign in

REVIEW 8 cited by

Hierarchical World Models as Visual Whole-Body Humanoid Controllers

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.18418 v3 pith:MV47MSE3 submitted 2024-05-28 cs.LG cs.CVcs.RO

classification cs.LGcs.CVcs.RO
keywords visualcontrolhumanoidwhole-bodyagenthierarchicalhighlylearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Whole-body control for humanoids is challenging due to the high-dimensional nature of the problem, coupled with the inherent instability of a bipedal morphology. Learning from visual observations further exacerbates this difficulty. In this work, we explore highly data-driven approaches to visual whole-body humanoid control based on reinforcement learning, without any simplifying assumptions, reward design, or skill primitives. Specifically, we propose a hierarchical world model in which a high-level agent generates commands based on visual observations for a low-level agent to execute, both of which are trained with rewards. Our approach produces highly performant control policies in 8 tasks with a simulated 56-DoF humanoid, while synthesizing motions that are broadly preferred by humans.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Human Cognition in Machines: A Unified Perspective of World Models

    cs.RO 2026-04 unverdicted novelty 6.0 of 10

    The paper introduces a unified framework for world models that fully incorporates all cognitive functions from Cognitive Architecture Theory, highlights under-researched areas in motivation and meta-cognition, and pro...

  2. Hierarchical Planning with Latent World Models

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    Hierarchical planning over multi-scale latent world models enables 70% success on real robotic pick-and-place with goal-only input where flat models achieve 0%, while cutting planning compute up to 4x in simulations.

  3. HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model

    cs.RO 2026-02 unverdicted novelty 6.0 of 10

    HAIC enables robust humanoid interactions with underactuated objects by predicting their dynamics from proprioceptive history and using a world model for adaptive control.

  4. RISE: Self-Improving Robot Policy with Compositional World Model

    cs.RO 2026-02 unverdicted novelty 6.0 of 10

    RISE combines a controllable dynamics model and progress value model into a closed-loop self-improving pipeline that updates robot policies entirely in imagination, reporting over 35% absolute gains on three real-world tasks.

  5. TOP: Time Optimization Policy for Stable and Accurate Standing Manipulation with Humanoid Robots

    cs.RO 2025-08 conditional novelty 6.0 of 10

    A reinforcement-learned time optimization policy that adaptively slows upper-body motion clips improves stability and precision of humanoid standing manipulation at a modest time cost.

  6. PhyWorld: Physics-Faithful World Model for Video Generation

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    PhyWorld improves temporal consistency and physical plausibility in video world models via flow matching fine-tuning followed by DPO on physics preference pairs, with reported gains on VBench and a custom physical-fai...

  7. Hierarchical Planning with Latent World Models

    cs.LG 2026-04 unverdicted novelty 5.0 of 10

    Hierarchical latent world models with macro-actions solve long-horizon visual planning (70% Franka pick-and-place vs 0% flat planning) with up to 3× less compute.

  8. Emotion-Conditioned Short-Horizon Human Pose Forecasting with a Lightweight Predictive World Model

    cs.CV 2026-04 unverdicted novelty 3.0 of 10

    Facial emotion embeddings improve short-term pose forecasting accuracy for emotion-driven motions when fused via normalized gating in a lightweight LSTM world model, but not with simple multimodal fusion.

Pith tools