Generating interaction-centric videos, such as those depicting humans or robots interacting with objects, is crucial for embodied intelligence, as they provide rich and diverse visual priors for robot learning, manipulation policy training, and affordance reasoning. However, existing methods often struggle to model such complex and dynamic interactions. While recent studies show that masks can serve as effective control signals and enhance generation quality, obtaining dense and precise mask annotations remains a major challenge for real-world use. To overcome this limitation, we introduce Mask2IV, a novel framework specifically designed for interaction-centric video generation. It adopts a decou-pled two-stage pipeline that first predicts plausible motion trajectories for both actor and object, then generates a video conditioned on these trajectories. This design eliminates the need for dense mask inputs from users while preserving the flexibility to manipulate the interaction process. Furthermore, Mask2IV supports versatile and intuitive control, allowing users to specify the target object of interaction and guide the motion trajectory through action descriptions or spatial position cues. To support systematic training and evaluation, we curate two benchmarks covering diverse action and object categories across both human-object interaction and robotic manipulation scenarios. Extensive experiments demonstrate that our method achieves superior visual realism and control-lability compared to existing baselines.

Humans can easily construct mental models of complex 3D objects and object categories from visual observations. This is remarkable because the dependency between an object's appearance

Image captioning models are becoming increasingly successful at describing the content of images in restricted domains. However, if these models are to function in the wild --- for example, as assistants for people with impaired vision --- a much larger number and variety of visual concepts must be understood. To address this problem, we teach image captioning models new visual concepts from labeled images and object detection datasets. Since image labels and object classes can be interpreted as partial captions, we formulate this problem as learning from partially-specified sequence data. We then propose a novel algorithm for training sequence models, such as recurrent neural networks, on partially-specified sequences which we represent using finite state automata. In the context of image captioning, our method lifts the restriction that previously required image captioning models to be trained on paired image-sentence corpora only, or otherwise required specialized model architectures to take advantage of alternative data modalities. Applying our approach to an existing neural captioning model, we achieve state of the art results on the novel object captioning task using the COCO dataset. We further show that we can train a captioning model to describe new visual concepts from the Open Images dataset while maintaining competitive COCO evaluation scores.

Holistic 3D indoor scene understanding refers to jointly recovering the i) object bounding boxes, ii) room layout, and iii) camera pose, all in 3D. The existing methods either are ineffective or only tackle the problem partially. In this paper, we propose an end-to-end model that simultaneously solves all three tasks in real-time given only a single RGB image. The essence of the proposed method is to improve the prediction by i) parametrizing the targets (e.g., 3D boxes) instead of directly estimating the targets, and ii) cooperative training across different modules in contrast to training these modules individually. Specifically, we parametrize the 3D object bounding boxes by the predictions from several modules, i.e., 3D camera pose and object attributes. The proposed method provides two major advantages: i) The parametrization helps maintain the consistency between the 2D image and the 3D world, thus largely reducing the prediction variances in 3D coordinates.

Generalization has been one of the major challenges for learning dynamics models in model-based reinforcement learning. However, previous work on action-conditioned dynamics prediction focuses on learning the pixel-level motion and thus does not generalize well to novel environments with different object layouts. In this paper, we present a novel object-oriented framework, called object-oriented dynamics predictor (OODP), which decomposes the environment into objects and predicts the dynamics of objects conditioned on both actions and object-to-object relations. It is an end-to-end neural network and can be trained in an unsupervised manner. To enable the generalization ability of dynamics learning, we design a novel CNN-based relation mechanism that is class-specific (rather than object-specific) and exploits the locality principle. Empirical results show that OODP significantly outperforms previous methods in terms of generalization over novel environments with various object layouts. OODP is able to learn from very few environments and accurately predict dynamics in a large number of unseen environments. In addition, OODP learns semantically and visually interpretable dynamics models.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Task-Oriented Grasping (TOG) requires robots to select grasps that are functionally appropriate for a specified task - a challenge that demands an understanding of task semantics, object affordances, and functional constraints. We present GRIM (Grasp Re-alignment via Iterative Matching), a training-free framework that addresses these challenges by leveraging Video Generation Models (VGMs) together with a retrieve-align-transfer pipeline. Beyond leveraging VGMs, GRIM can construct a memory of object-task exemplars sourced from web images, human demonstrations, or generative models. The retrieved task-oriented grasp is then transferred and refined by evaluating it against a set of geometrically stable candidate grasps to ensure both functional suitability and physical feasibility. GRIM demonstrates strong generalization and achieves state-of-the-art performance on standard TOG benchmarks. Project website: https://grim-tog.github.io

Foundation models applied in robotics, particularly \textbf{Vision--Language--Action (VLA)} models, hold great promise for achieving general-purpose manipulation. Yet, systematic real-world evaluations and cross-model comparisons remain scarce. This paper reports our \textbf{empirical experiences} from benchmarking four representative VLAs -- \textbf{ACT}, \textbf{OpenVLA--OFT}, \textbf{RDT-1B}, and \boldmath{$π_0$} -- across four manipulation tasks conducted in both simulation and on the \textbf{ALOHA Mobile} platform. We establish a \textbf{standardized evaluation framework} that measures performance along three key dimensions: (1) \textit{accuracy and efficiency} (success rate and time-to-success), (2) \textit{adaptability} across in-distribution, spatial out-of-distribution, and instance-plus-spatial out-of-distribution settings, and (3) \textit{language instruction-following accuracy}. Through this process, we observe that \boldmath{$π_0$} demonstrates superior adaptability in out-of-distribution scenarios, while \textbf{ACT} provides the highest stability in-distribution. Further analysis highlights differences in computational demands, data-scaling behavior, and recurring failure modes such as near-miss grasps, premature releases, and long-horizon state drift. These findings reveal practical trade-offs among VLA model architectures in balancing precision, generalization, and deployment cost, offering actionable insights for selecting and deploying VLAs in real-world robotic manipulation tasks.