Inverse Dynamics

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 28

All topics

Preserving Unstable Modes Through Inverse Dynamics in JEPA World Models
Oct 6, 2026Leonardo F. Toso, Yann LeCun, James Anderson +1Representation Learning World Model Learning
Columbia University · New York University, AMI Labs · New York University
Beyond Prediction: Steering VLM Agents with Retrospective World Modeling
Sep 30, 2026Yongjiang Liu, Jie Zhang, Haoyue Zhang +3World Model Learning World Models
The Hong Kong University of Science and Technology · The Hong Kong Polytechnic University · China University of Geoscience
Bounded Channel-Adaptive Spectral Learning for Forward-Consistent Inverse Flapping-Wing Aerodynamics
Sep 30, 2026Haichuan LiRecurrent Neural Networks Spectral Methods
University of Turku
FlapKAD: A Simulation Dataset of Coupled Wing Kinematics and Aerodynamic Dynamics for Flapping-Wing Aerial Vehicles
Sep 30, 2026Haichuan LiAerial Robotics Vehicle Dynamics
University of Turku
Pixels to Keys: Exploring Spatial and Motion Cues in Gameplay Inverse Dynamics
Sep 29, 2026Abhishek Pillai, Ekta Prashnani, Joohwan Kim +1Inverse Dynamics
NVIDIA
Analytic Dynamics: Learning Physics-Grounded Representation for Fast Intrinsic Dynamics Inference from Monocular Videos
Aug 31, 2026Jailing Lin, Jikuan Zhang, Jianhua SunMaterials Property Prediction Video Representation Learning
School of Artificial Intelligence, Shanghai Jiao Tong University
Learning human joint torques from pixels
Aug 10, 2026Chen Chen, Rui ChengInverse Dynamics
Beijing Normal-Hong Kong Baptist University, Zhuhai, China · AnHui University, Hefei, China
Linear Stability Analysis of an INDI Pitch-Rate Controller under Model Mismatch for a Tilt-Rotor VTOL UAV
Jul 17, 2026Lorenzo Schenk, Guillaume Ducard, Christopher OnderAerial Robotics Robust Control
Conditional Invertible Neural Networks for Data-Driven UAV Control: A 2-D Proof of Concept
Jul 15, 2026Christian Wittke, Stephan Myschik, Oliver NiggemannInvertible Neural Networks Quadrotor Control
Computer Science in Mechanical Engineering, Helmut Schmidt University, Hamburg, Germany. · Institute for Aeronautical Engineering, University of the Bundeswehr Munich, Bavaria, Germany
An Opticalmechanics Framework for Dynamic Estimation of Multibody Systems
Jun 8, 2026Banglei Guan, Xuanyu Bai, Qingquan Chen +5Dynamical Systems Multibody Dynamics
National University of Defense Technology
Hybrid Dynamics Modeling for a Flexible 2-DoF Robotic Arm
Jun 2, 2026Maciek Popik, Daniel Yang, Mahdis BishebanRobot Dynamics Identification Nonlinear System Identification
Dept. of Mechanical and Manufacturing Eng at the Schulich School of Engineering, University of Calgary, Alberta, Canada · Intelligent Dynamics and Control Lab, University of Calgary, Alberta, Canada
Identifying Explicit Parsimonious Piece-wise Polynomial Relationships in Industrial time-series: Application to manipulator robots
May 27, 2026Mazen Alamir, Sacha ClavelNonlinear System Identification Inverse Dynamics
Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-lab, 38000 Grenoble, France · Staubli company. Auvergne-Rhône-Alpes, 74210, Faverges, France.
Turning Video Models into Generalist Robot Policies
May 27, 2026Sizhe Lester Li, Evan Kim, Xingjian Bai +4Robot Policy Learning Cross-Embodiment Robot Learning
1MIT · 2Independent Researcher · 3CMU +1
How Noisy Poses Break Inverse Dynamics: Analysis and Mitigation for Video-Based Joint Torque Estimation
May 23, 2026Donghyun Kim, Chanyoung Kim, Eunseo Jeong +2Multibody Dynamics Inverse Dynamics
Emory University · Yonsei University
Benchmarking Empirical and Learning-Based Approaches for Feedforward Steering Control in Autonomous Racing
May 20, 2026Georg Jank, Mattia Piccinini, Sebastian Wenk +3Robotic Control Autonomous Racing
Chair of Automatic Control, Department of Engineering Physics and Computation, Technical University of Munich, Boltzmannstraße 15, 85748 Garching bei München, Germany · Professorship of Autonomous Vehicle Systems (AVS), Department of Mobility Systems Engineering, Technical University of Munich, Boltzmannstraße 15, 85748 Garching bei München, Germany
Trajectory Planning and Control near the Limits: an Open Experimental Benchmark on the RoboRacer Platform
May 19, 2026Mattia Piccinini, Patrick Zambiasi, Aniello Mungiello +3Autonomous Driving Benchmarks Robot Trajectory Tracking
Professorship of Autonomous Vehicle Systems, Technical University of Munich, 85748 Garching, Germany; Munich Institute of Robotics and Machine Intelligence (MIRMI). · Avilus GmbH, Germany. · Department of Information Technology and Electrical Engineering (DIETI), University of Naples Federico II, Naples 80125, Italy. +1
Dynamics Computation of Soft-Rigid Hybrid-Link System and Its Application to Motion Analysis of an Athlete Wearing Sport Prosthesis
May 13, 2026Sunghee Kim, Yuta Shimane, Taiki Ishigaki +1Inverse Dynamics
Department of Mechano-Informatics, University of Tokyo, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, Japan · Research Institute for Science and Technology, Tokyo University of Science, Katsushika-ku, Tokyo, Japan
Control of Fully Actuated Aerial Vehicles: A Comparison of Model-based and Sensor-based Dynamic Inversion
May 12, 2026Ali Sidar Yilmaz, Buday Turan, Lukas Pries +1Aerial Robotics Robust Control
Professorship of Autonomous Aerial Systems, School of Engineering and Design, Technical University of Munich, Lise-Meitner-Str. 9, 85521 Ottobrunn, Germany
Latent Geometry Beyond Search: Amortizing Planning in World Models
May 9, 2026Hoang Nguyen, Xiaohao Xu, Xiaonan HuangWorld Model-Based Planning Model-Based Planning
Department of Robotics, University of Michigan, Ann Arbor
Lie Group Formulation of Recursive Dynamics Algorithms of Higher Order for Floating-Base Robots
May 7, 2026Ahmed Ali, Chiara Gabellieri, Antonio FranchiMultibody Dynamics Robotics
Robotics and Mechatronics Department, Electrical Engineering, Mathematics, and Computer Science (EEMCS) Faculty, University of Twente, 7500 AE Enschede, The Netherlands. · Department of Computer, Control and Management Engineering, Sapienza University of Rome, 00185 Rome, Italy.
A Comparative Study of INDI and NDI with Nonlinear Disturbance Observer for Aerial Robotics
May 7, 2026Benedetta Rota, Mirko Mizzoni, Amr Afifi +2Aerial Robotics Robust Control
Department of Computer, Control and Management Engineering, Sapienza University of Rome, 00185 Rome, Italy · Robotics and Mechatronics group, Faculty of Electrical Engineering, Mathematics, and Computer Science (EEMCS), University of Twente, 7500 AE Enschede, The Netherlands · School of Aerospace, Mechanical, and Mechatronic Engineering (AMME), Faculty of Engineering, University of Sydney, NSW, 2006, Australia
Dynamics Aware Quadrupedal Locomotion via Intrinsic Dynamics Head
May 2, 2026Aman Arora, Nalini RathaRobot Dynamics Learning RL for Legged Locomotion
Department of Computer Science, University at Buffalo, The State University of New York, Buffalo, USA
StableIDM: Stabilizing Inverse Dynamics Model against Manipulator Truncation via Spatio-Temporal Refinement
Apr 20, 2026Kerui Li, Zhe Jing, Xiaofeng Wang +6Robot Policy Learning Embodied AI
1GigaAI · 3Beijing Institute of Technology · Institute of Automation, Chinese Academy of Sciences
IRIS: A Real-World Benchmark for Inverse Recovery and Identification of Physical Dynamic Systems from Monocular Video
Mar 17, 2026Rasul Khanbayov, Mohamed Rayan Barhdadi, Erchin Serpedin +1Parameter Identifiability System Identification
Hamad Bin Khalifa University · Texas A&M University
Coordinate-Independent Robot Model Identification
Mar 15, 2026Yanhao Yang, Ross L. HattonRobot Dynamics Identification System Identification
Collaborative Robotics and Intelligent Systems (CoRIS) Institute at Oregon State University, Corvallis, OR USA
On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning
Feb 2, 2026Sacha Morin, Moonsub Byeon, Alexia Jolicoeur-Martineau +1Latent Action Learning Imitation Learning
Département d’informatique et de recherche opérationnelle, Université de Montréal · Mila – Quebec AI Institute · Samsung AI Lab, Montreal +1
When Does Predictive Inverse Dynamics Outperform Behavior Cloning?
Jan 29, 2026Lukas Schäfer, Pallavi Choudhury, Abdelhak Lemkhenter +10Imitation Learning Behavior Cloning
Microsoft · McGill University, Mila · Tsinghua University
MonoMSK: Monocular 3D Musculoskeletal Dynamics Estimation
Nov 24, 2025Farnoosh Koleini, Hongfei Xue, Ahmed Helmy +1Markerless Motion Capture 3D Human Pose Estimation
University of North Carolina at Charlotte

Oct 6, 2026, cs.LGJ/K move · Enter open · S save

Preserving Unstable Modes Through Inverse Dynamics in JEPA World Models

Leonardo F. Toso, Yann LeCun, James Anderson, Oumayma Bounou

Columbia University · New York University, AMI Labs · New York University

Representation Learning World Model Learning Joint-Embedding Predictive Architecture Vision-Based Robot Control Inverse Dynamics

Open paper AskPDF arXiv

Robotic systems often exhibit unstable modes, along which small perturbations and disturbances can cause unbounded growth unless corrected through feedback. Controlling such systems from high-dimensional visual observations requires representations that preserve these modes. Joint-embedding predictive architectures (JEPAs) provide a natural framework for learning such representations and their dynamics from visual data. However, we demonstrate that next step prediction combined with anti-collapse regularization does not guarantee that controllable unstable modes are preserved: the training loss can be minimized while these modes are collapsed, making stabilization from the learned representation impossible. To address this, we augment world-model training with an action reconstruction objective (i.e., an inverse dynamics loss) that encourages control-aware representations, namely, visual representations that preserve crucial features for control. We prove that exact action reconstruction makes the encoder injective on the finite-horizon reachable subspace. Thus, the encoder cannot discard any state direction reachable by an action sequence within

H

steps. Moreover, we show that, as

H

grows, the dominant eigenspace of the finite-horizon controllability Gramian converges to the controllable unstable subspace. We establish our theoretical results for linear systems and demonstrate empirically that our findings extend to nonlinear visual control tasks (CartPole, Walker2D, and PointMaze), highlighting the benefits of control-aware representation learning.

Momentum

Related topics

Latest papers 28