Omninwm

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 15

All topics

AD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control
Sep 24, 2026Jiabin Qiu, Zixuan Chen, Hongye Cao +3World Models Model Predictive Control
Nanjing University
OnlineWM: Causality-Aware Active Online Learning for Effective World Modeling
Sep 20, 2026Yikun Miao, Fangqi Zhu, Quanxin Shou +6Efficient World-Action Model World Models
Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong SAR, China
What Breaks Local Watermarks? A Robustness Benchmark for Local Invisible Image Watermarking
Sep 15, 2026Kai Yao, Bence Szilágyi, Sebestyén Kamp +4Watermarks Localization
University of Edinburgh · Garandor · Garandor; University of Edinburgh
CorrRisk-WM: Corridor-Conditioned Risk World Modeling for Safety-Critical Trajectory Planning
Sep 15, 2026Tingyu Guo, Reza LangariWorld Model Planning World Models
J. Mike Walker ’66 Department of Mechanical Engineering, Texas A&M University, College Station, TX 77843, USA
PV-WM: A Heterogeneous Micro-Macro World Model for Articulated Pedestrian-Vehicle Co-Rollout
Sep 7, 2026Haozhuang Chi, Jingsong Liang, Ziying Song +4Pedestrian Trajectory Prediction World Models
Nanyang Technological University, Singapore · Beijing Institute of Technology, Beijing, China
MemWM: Memory-Augmented Text-Based World Model
Aug 7, 2026Yujun Wang, Tao Zhang, Jinhe Bi +9World Models Next-State Prediction
LMU Munich · Munich Center for Machine Learning (MCML) · Huawei Heisenberg Research Center +4
PhaseWin: An Efficient Search Algorithm for Faithful Visual Attribution
Jun 16, 2026Zihan Gu, Junchi Zhang, Li Liu +2Multiple Vision Tasks Search Algorithms
Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing 100049, China · Shanghai Center for Mathematical Sciences, Fudan University, Shanghai 200438, China +2
ARB4WM: An Adversarial Robustness Benchmark for World Models in Continuous Control
Jun 15, 2026Junjian Zhang, Hao Tan, Ruonan Li +3World Models Omninwm
College of Computer Science, National University of Defense Technology, Changsha, 410073, China · National Key Laboratory of Advanced Communication Networks, Shijiazhuang, 050081, Hebei, China · College of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, 518055, China +1
EV-WM: Event-Verified World Models for Long-Horizon Robotic Manipulation
Jun 11, 2026Kailin Wang, Haoxiang Jie, Yaoyuan Yan +2World Model Planning Omninwm
1AI Lab, Country Garden Services Group · 2Fudan University · 3Omni AI
STRIPS-WM: Learning Grounded Propositional STRIPS-style World Models from Images
Jun 5, 2026Abhiroop Ajith, Constantinos ChamzasWorld Model Planning Classical Planning
Department of Robotics Engineering · Worcester Polytechnic Institute · United States
WALL-WM: Carving World Action Modeling at the Event Joints
Jun 1, 2026Shalfun Li, Victor Yao, Charles Yang +28Efficient World-Action Model Omninwm
X Square Robot Team
$τ_0$ -WM: A Unified Video-Action World Model for Robotic Manipulation
May 31, 2026Pengfei Zhou, Shengcong Chen, Di Chen +17Efficient World-Action Model Video World Models
1Shanghai Innovation Institute · 2AGIBOT Finch
EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields
May 7, 2026Zhaoyang Yang, Yurun Jin, Lizhe Qi +2Efficient World-Action Model Recent World-Action Models
Fudan University · Zhongguancun Institute of Artificial Intelligence · University of Science and Technology of China +2
Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout
May 6, 2026Haozhuang Chi, Daosheng Qiu, Hao Su +4Latent World Models Omninwm
Nanyang Technological University, Singapore · Hubei University, Wuhan, China · Osaka University, Osaka, Japan
OmniNWM: Omniscient Driving Navigation World Models
Oct 21, 2025Bohan Li, Zhuang Ma, Dalong Du +10Efficient World-Action Model Autonomous Driving
Shanghai Jiao Tong University · Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China · PhiGent +3

Sep 24, 2026, cs.AIJ/K move · Enter open · S save

AD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control

Jiabin Qiu, Zixuan Chen, Hongye Cao, Jieqi Shi+2

Nanjing University

World Models Model Predictive Control Omninwm

Open paper AskPDF arXiv

Latent world models are typically trained to predict factual transitions, whereas model predictive control (MPC) must compare alternative actions from the same state. A model can therefore achieve low factual prediction error yet poorly distinguish candidate actions. We introduce AD-WM, an action-discriminative joint-embedding world model for counterfactual MPC. AD-WM combines residual latent dynamics with predictor-level action-recovery regularization, using inverse dynamics and a normalized recovery objective motivated by conditional mutual information. Both objectives encourage planning transitions to preserve action information; their auxiliary heads are discarded at test time, leaving MPC unchanged. On OGBench-Cube, AD-WM improves hard-start success from 3.7% to 52.0% over a matched LeWM baseline and improves mean success over the reproduced baseline in four of five simulation environments. Planning diagnostics show that factual prediction error and whole-bank action ranking do not follow the closed-loop success ordering, whereas CEM-aligned elite regret tracks success more closely. With a frozen V-JEPA 2 encoder and matched DROID post-training, AD-WM also improves zero-shot transfer to our Franka setup, increasing basic pick-and-place success from 42.2% to 71.1% without lab-specific adaptation. These results suggest that world models for planning should preserve action-dependent differences needed for counterfactual selection, rather than optimize factual prediction accuracy alone. More videos and code are available at https://ad-wm.github.io/.

Momentum

Related topics

Latest papers 15