The reviewed record of science sign in
Pith

arxiv: 2410.03441 · v1 · pith:MYFHID2S · submitted 2024-10-04 · cs.CV

CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:MYFHID2Srecord.jsonopen to challenge →

classification cs.CV
keywords diffusionmotionclosdcontrollercontrolcapableenvironmentgeneration
0
0 comments X
read the original abstract

Motion diffusion models and Reinforcement Learning (RL) based control for physics-based simulations have complementary strengths for human motion generation. The former is capable of generating a wide variety of motions, adhering to intuitive control such as text, while the latter offers physically plausible motion and direct interaction with the environment. In this work, we present a method that combines their respective strengths. CLoSD is a text-driven RL physics-based controller, guided by diffusion generation for various tasks. Our key insight is that motion diffusion can serve as an on-the-fly universal planner for a robust RL controller. To this end, CLoSD maintains a closed-loop interaction between two modules -- a Diffusion Planner (DiP), and a tracking controller. DiP is a fast-responding autoregressive diffusion model, controlled by textual prompts and target locations, and the controller is a simple and robust motion imitator that continuously receives motion plans from DiP and provides feedback from the environment. CLoSD is capable of seamlessly performing a sequence of different tasks, including navigation to a goal location, striking an object with a hand or foot as specified in a text prompt, sitting down, and getting up. https://guytevet.github.io/CLoSD-page/

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 13 Pith papers

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

  1. Policy-as-Data: Learning Generalizable HOI Diffusion Models from Simulated Physics

    cs.CV 2026-06 unverdicted novelty 7.0

    A framework called Policy-as-Data generates task-oriented synthetic HOI data via RL policies in physics simulators, retargets it, and trains diffusion models that generalize to unseen objects and long horizons.

  2. ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body

    cs.CV 2025-12 unverdicted novelty 7.0

    ViBES introduces a speech-language-behavior model using modality-specific transformer experts that jointly generates dialogue and 3D body actions, showing gains over separate co-speech and text-to-motion baselines on ...

  3. WristMimic: Full-Body Humanoid Control with Wrist-Guided Manipulation

    cs.RO 2026-07 accept novelty 6.0

    WristMimic achieves comparable or superior object manipulation retargeting by supervising wrist kinematics while letting finger behavior emerge from object and contact dynamics.

  4. In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics

    cs.RO 2026-06 unverdicted novelty 6.0

    ICMPG combines LLM-based candidate generation with MPC-style physical simulation and semantic scoring to produce text-driven human motions that are both plausible and faithful.

  5. MIND: Multi-Scale Intent Diffusion for Text-Driven Physics-Based Humanoid Control

    cs.CV 2026-05 unverdicted novelty 6.0

    MIND introduces a multi-scale intent diffusion framework that bridges text commands and low-level actions via holistic and immediate intent predictors for physics-based humanoid control.

  6. SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-based Humanoid Control

    cs.GR 2026-05 unverdicted novelty 6.0

    A new diffusion transformer policy with joint attention over actions, states, and text plus RL post-training outperforms prior methods on language alignment and motion quality for humanoid control.

  7. SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-based Humanoid Control

    cs.GR 2026-05 unverdicted novelty 6.0

    SCRIPT presents a scalable diffusion policy with JAST-DiT architecture, nonlinear history conditioning, and RLHR post-training that claims to outperform prior methods on text alignment, motion quality, and physical re...

  8. Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos

    cs.CV 2026-05 unverdicted novelty 6.0

    HA-HOI produces physically plausible 4D HOI animations from monocular videos by anchoring object reconstruction to human motion and refining the result in a physics-based humanoid-object simulator.

  9. IAM: Identity-Aware Human Motion and Shape Joint Generation

    cs.CV 2026-04 unverdicted novelty 6.0

    IAM jointly synthesizes motion sequences and body shape parameters conditioned on multimodal identity signals to achieve more realistic and identity-consistent human motions.

  10. Stability-Driven Motion Generation for Object-Guided Human-Human Co-Manipulation

    cs.CV 2026-04 unverdicted novelty 6.0

    A flow-matching model derives manipulation strategies from object affordance, adds an adversarial interaction prior, and uses stability simulation to generate natural, effective human-human co-manipulation motions.

  11. DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion

    cs.RO 2025-05 unverdicted novelty 6.0

    DreamPolicy integrates an autoregressive diffusion world model with policy learning to produce a single scalable policy that generalizes to unseen composite terrains for humanoid locomotion.

  12. GPC: Large-Scale Generative Pretraining for Transferable Motor Control

    cs.CV 2026-06 unverdicted novelty 5.0

    GPC learns a motion vocabulary via Finite Scalar Quantization and end-to-end RL, then trains an autoregressive transformer for next-token control generation, achieving 99.98% motion reproduction success with emergent ...

  13. UMo: Unified Sparse Motion Modeling for Real-Time Co-Speech Avatars

    cs.GR 2026-05 unverdicted novelty 4.0

    UMo presents a sparse MoE-based unified model for real-time co-speech avatar animation that claims superior quality under latency constraints via keyframe-centric design and multi-stage audio-augmented training.