Learning predictive world models from raw visual observations is a central challenge in reinforcement learning (RL), especially for robotics and continuous control. Conventional model-based RL frameworks directly condition future predictions on absolute actions, which makes optimization unstable: the optimal action distributions are task-dependent, unknown a priori, and often lead to oscillatory or inefficient control. To address this, we introduce the Residual-Action World Model (ResWM), a new framework that reformulates the control variable from absolute actions to residual actions -- incremental adjustments relative to the previous step. This design aligns with the inherent smoothness of real-world control, reduces the effective search space, and stabilizes long-horizon planning. To further strengthen the representation, we propose an Observation Difference Encoder that explicitly models the changes between adjacent frames, yielding compact latent dynamics that are naturally coupled with residual actions. ResWM is integrated into a Dreamer-style latent dynamics model with minimal modifications and no extra hyperparameters. Both imagination rollouts and policy optimization are conducted in the residual-action space, enabling smoother exploration, lower control variance, and more reliable planning. Empirical results on the DeepMind Control Suite demonstrate that ResWM achieves consistent improvements in sample efficiency, asymptotic returns, and control smoothness, significantly surpassing strong baselines such as Dreamer and TD-MPC. Beyond performance, ResWM produces more stable and energy-efficient action trajectories, a property critical for robotic systems deployed in real-world environments. These findings suggest that residual action modeling provides a simple yet powerful principle for bridging algorithmic advances in RL with the practical requirements of robotics.
Iterative Residual Cross-Attention Mechanism: An Integrated Approach for Audio-Visual Navigation Tasks
Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center, School of Computer Science and Technology, Xinjiang University(新疆多模态智能处理与信息安全工程技术创新中心,计算机科学与技术学院,新疆大学);Department of Computer Science and Technology, Tsinghua University(计算机科学与技术系,清华大学);School of Electrical Engineering and Automation, Tianjin University of Technology(电气工程与自动化学院,天津工业大学)
Momentum-constrained Hybrid Heuristic Trajectory Optimization Framework with Residual-enhanced DRL for Visually Impaired Scenarios
School of Information;Software Engineering, University of Electronic Science;Sichuan Provincial Key Laboratory for Human Disease Gene Study, Sichuan Academy of Medical Sciences \& Sichuan Provincial People's Hospital, University of Electronic Science;Research Unit for Blindness Prevention, Chinese Academy of Medical Sciences, Sichuan Academy of Medical Sciences;Sichuan Provincial People’s Hospital, Chengdu, Sichuan, China.
Self-supervised Hierarchical Visual Reasoning with World Model
Department of Electronic Engineering and Information Science, University of Science and Technology of China(电子工程与信息科学系,中国科学技术大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(人工智能研究院,合肥综合性国家科学中心)
FiberTune: Preserving Action-Fiber Visual Residuals in Vision-Language-Action Fine-Tuning
University of Chinese Academy of Sciences(中国科学院大学);Hebei Key Laboratory of Cognitive Intelligence, Xiong’an Institute of Innovation(河北省认知智能重点实验室,雄安创新研究院);Hebei University of Technology(河北工业大学);Beijing Information Science and Technology University(北京信息科技大学)
Residual Cross-Modal Fusion Networks for Audio-Visual Navigation
School of Computer Science and Technology, Xinjiang University, Urumqi, China(新疆大学计算机科学与技术学院);Joint International Research Laboratory of Silk Road Multilingual Cognitive(丝绸之路多语认知联合国际实验室);School of Mechatronic Engineering and Automation Shanghai University, Shanghai, China(上海大学机电工程与自动化学院)
Feeling the Unexpected: ResTacVLA for Contact-Rich Manipulation via Residual Tactile Representation
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Zhongguancun Academy(中关村科学城);Dexmal(德克斯马尔)
Imagine-RL: Residual-Confidence-Guided Cross-Attention for World-Model-Augmented VLA Reinforcement Learning
Korea Advanced Institute of Science and Technology(韩国科学技术院);University of Science and Technology Beijing(北京科技大学);Shanghai Jiao Tong University(上海交通大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)
SA-LIVO: Efficient LiDAR-Inertial-Visual Odometry with Subspace-Aware Degeneracy Handling
Key Laboratory of Space Active Opto-Electronics Technology, Shanghai Institute of Technical Physics, Chinese Academy of Sciences(中国科学院上海技术物理研究所空间主动光电技术重点实验室);Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences(中国科学院大学杭州高等研究院)