Neural-network-based dynamics models learned from observational data have shown strong predictive capabilities for scene dynamics in robotic manipulation tasks. However, their inherent non-linearity presents significant challenges for effective planning. Current planning methods, often dependent on extensive sampling or local gradient descent, struggle with long-horizon motion planning tasks involving complex contact events. In this paper, we present a GPU-accelerated branch-and-bound (BaB) framework for motion planning in manipulation tasks that require trajectory optimization over neural dynamics models. Our approach employs a specialized branching heuristic to divide the search space into sub-domains and applies a modified bound propagation method, inspired by the state-of-the-art neural network verifier $\alpha,\beta$-CROWN, to efficiently estimate objective bounds within these sub-domains. The branching process guides planning effectively, while the bounding process strategically reduces the search space. Our framework achieves superior planning performance, generating high-quality state-action trajectories and surpassing existing methods in challenging, contact-rich manipulation tasks such as non-prehensile planar pushing with obstacles, object sorting, and rope routing in both simulated and real-world settings. Furthermore, our framework supports various neural network architectures, ranging from simple multilayer perceptrons to advanced graph neural dynamics models, and scales efficiently with different model sizes.

Recent years have witnessed a remarkable success of large deep learning models. However, training these models is challenging due to high computational costs, painfully slow convergence, and overfitting issues. In this paper, we present Deep Incubation, a novel approach that enables the efficient and effective training of large models by dividing them into smaller sub-modules which can be trained separately and assembled seamlessly. A key challenge for implementing this idea is to ensure the compatibility of the independently trained sub-modules. To address this issue, we first introduce a global, shared meta model, which is leveraged to implicitly link all the modules together, and can be designed as an extremely small network with negligible computational overhead. Then we propose a module incubation algorithm, which trains each sub-module to replace the corresponding component of the meta model and accomplish a given learning task. Despite the simplicity, our approach effectively encourages each sub-module to be aware of its role in the target large model, such that the finally-learned sub-modules can collaborate with each other smoothly after being assembled. Empirically, our method can outperform end-to-end (E2E) training in well-established training setting and shows transferable performance gain for downstream tasks (e.g., object detection and image segmentation on COCO and ADE20K). Our code is available at https://github.com/LeapLabTHU/Deep-Incubation.

Daily objects commonly experience state changes. For example, slicing a cucumber changes its state from whole to sliced. Learning about object state changes in Video Object Segmentation (VOS) is crucial for understanding and interacting with the visual world. Conventional VOS benchmarks do not consider this challenging yet crucial problem. This paper makes a pioneering effort to introduce a weakly-supervised benchmark on Video State-Changing Object Segmentation (VSCOS). We construct our VSCOS benchmark by selecting state-changing videos from existing datasets. In advocate of an annotation-efficient approach towards state-changing object segmentation, we only annotate the first and last frames of training videos, which is different from conventional VOS. Notably, an open-vocabulary setting is included to evaluate the generalization to novel types of objects or state changes. We empirically illustrate that state-of-the-art VOS models struggle with state-changing objects and lose track after the state changes. We analyze the main difficulties of our VSCOS task and identify three technical improvements, namely, fine-tuning strategies, representation learning, and integrating motion information. Applying these improvements results in a strong baseline for segmenting state-changing objects consistently. Our benchmark and baseline methods are publicly available at https://github.com/venom12138/VSCOS.

Multicast benefits group communications in saving network traffic and improving application throughput, both of which are important for data center applications. However, the technical trend of data center design poses new challenges for efficient and scalable multicast routing. First, the densely connected networks make traditional receiver-driven multicast routing protocols inefficient in multicast tree formation. Second, it is quite difficult for the low-end switches widely used in data centers to hold the routing entries of massive multicast groups. In this paper, we propose ESM, an efficient and scalable multicast routing scheme for data center networks. ESM addresses the challenges above by exploiting the feature of modern data center networks. Based on the regular topology of data centers, ESM uses a source-to-receiver expansion approach to build efficient multicast trees, excluding many unnecessary intermediate switches used in receiver-driven multicast routing. For scalable multicast routing, ESM combines both in-packet Bloom Filters and in-switch entries to make the tradeoff between the number of multicast groups supported and the additional bandwidth overhead. Simulations show that ESM saves 40%$\sim$50% network traffic and doubles the application throughputs compared to receiver-driven multicast routing, and the combination routing scheme significantly reduces the number of in-switch entries required. We implement ESM on a Linux platform. The experimental results further demonstrate that ESM can well support online tree building for large-scale groups with churns, and the overhead of the combination forwarding engine is light-weighted.

Multicast benefits group communications in saving network traffic and improving application throughput, both of which are important for data center applications. However, the technical trend of future data center design poses new challenges for efficient and scalable Multicast routing. First, the densely connected networks make traditional receiver-driven Multicast routing protocols inefficient in Multicast tree formation. Second, it is quite difficult for the low-end switches largely used in data centers to hold the routing entries of massive Multicast groups.