Kui Jia

Ruixiang Wang, Qingming Liu, Yueci Deng et al.

Video generative models are increasingly used as world models for robotics, where a model generates a future visual rollout conditioned on the current observation and task instruction, and an inverse dynamics model (IDM) converts the generated frames into executable robot actions. However, current video world models lack explicit executability constraints. As a result, visually coherent rollouts may still violate rigid-body and kinematic consistency, producing unstable or infeasible control commands when decoded by an IDM. We refer to this mismatch between visual generation and physically executable control as the executability gap. While this gap can be mitigated at inference time using techniques such as rejection sampling, such approaches are inefficient due to the high cost of video generation. In this paper, we leverage the executability gap as a training signal and introduce Executable Video Alignment (EVA), a reinforcement-learning post-training framework for aligning video world models. EVA trains an inverse dynamics model on real robot trajectories and repurposes it as a reward model that evaluates generated videos through the action sequences they induce, encouraging smooth motions measured by velocity, acceleration, and jerk while penalizing actions that violate embodiment constraints. Importantly, the reward remains informative even when generated videos contain severe visual artifacts, since such artifacts typically translate into unstable or out-of-bound actions. Experiments on the RoboTwin benchmark and a real bimanual robot show that EVA reduces embodiment-specific artifacts in generated rollouts and improves downstream task execution success.

Longkun Zou, Kangjun Liu, Ke Chen et al.

Learning semantic representations from point sets of 3D object shapes is often challenged by significant geometric variations, primarily due to differences in data acquisition methods. Typically, training data is generated using point simulators, while testing data is collected with distinct 3D sensors, leading to a simulation-to-reality (Sim2Real) domain gap that limits the generalization ability of point classifiers. Current unsupervised domain adaptation (UDA) techniques struggle with this gap, as they often lack robust, domain-insensitive descriptors capable of capturing global topological information, resulting in overfitting to the limited semantic patterns of the source domain. To address this issue, we introduce a novel Topology-Aware Modeling (TAM) framework for Sim2Real UDA on object point clouds. Our approach mitigates the domain gap by leveraging global spatial topology, characterized by low-level, high-frequency 3D structures, and by modeling the topological relations of local geometric features through a novel self-supervised learning task. Additionally, we propose an advanced self-training strategy that combines cross-domain contrastive learning with self-training, effectively reducing the impact of noisy pseudo-labels and enhancing the robustness of the adaptation process. Experimental results on three public Sim2Real benchmarks validate the effectiveness of our TAM framework, showing consistent improvements over state-of-the-art methods across all evaluated tasks. The source code of this work will be available at https://github.com/zou-longkun/TAG.git.

Qingming Liu, Xinyue Yao, Shuyuan Zhang et al.

Articulated objects are central to interactive 3D applications, including embodied AI, robotics, and VR/AR, where functional part decomposition and kinematic motion are essential. Yet producing high-fidelity articulated assets remains difficult to scale because it requires reliable part decomposition and kinematic rigging. Existing approaches largely fall into two paradigms: optimization-based reconstruction or distillation, which can be accurate but often takes tens of minutes to hours per instance, and inference-time methods that rely on template or part retrieval, producing plausible results that may not match the specific structure and appearance in the input observation. We introduce a part-centric generative framework for articulated object creation that synthesizes part geometry, composition, and articulation under explicit part-aware conditioning. Our representation models an object as a set of movable parts, each encoded by latent tokens augmented with part identity and articulation cues. Conditioned on a single image, the model generates articulated 3D assets that preserve instance-level correspondence while maintaining valid part structure and motion. The resulting approach avoids per-instance optimization, enables fast feed-forward inference, and supports controllable assembly and articulation, which are important for embodied interaction. Experiments on common articulated categories (e.g., drawers and doors) show improved input consistency, part accuracy, and articulation plausibility over optimization-based and retrieval-driven baselines, while substantially reducing inference time.

Yangkai Lin, Jiabao Lei, Kui Jia

Our project page: https://scutyklin.github.io/SceneLCM/. Automated generation of complex, interactive indoor scenes tailored to user prompt remains a formidable challenge. While existing methods achieve indoor scene synthesis, they struggle with rigid editing constraints, physical incoherence, excessive human effort, single-room limitations, and suboptimal material quality. To address these limitations, we propose SceneLCM, an end-to-end framework that synergizes Large Language Model (LLM) for layout design with Latent Consistency Model(LCM) for scene optimization. Our approach decomposes scene generation into four modular pipelines: (1) Layout Generation. We employ LLM-guided 3D spatial reasoning to convert textual descriptions into parametric blueprints(3D layout). And an iterative programmatic validation mechanism iteratively refines layout parameters through LLM-mediated dialogue loops; (2) Furniture Generation. SceneLCM employs Consistency Trajectory Sampling(CTS), a consistency distillation sampling loss guided by LCM, to form fast, semantically rich, and high-quality representations. We also offer two theoretical justification to demonstrate that our CTS loss is equivalent to consistency loss and its distillation error is bounded by the truncation error of the Euler solver; (3) Environment Optimization. We use a multiresolution texture field to encode the appearance of the scene, and optimize via CTS loss. To maintain cross-geometric texture coherence, we introduce a normal-aware cross-attention decoder to predict RGB by cross-attending to the anchors locations in geometrically heterogeneous instance. (4)Physically Editing. SceneLCM supports physically editing by integrating physical simulation, achieved persistent physical realism. Extensive experiments validate SceneLCM's superiority over state-of-the-art techniques, showing its wide-ranging potential for diverse applications.