Unified physics-based humanoid controllers are pivotal for robotics and character animation, yet models that excel on gentle, everyday motions still stumble on explosive actions, hampering real-world deployment. We bridge this gap with FARM (Frame-Accelerated Augmentation and Residual Mixture-of-Experts), an end-to-end framework composed of frame-accelerated augmentation, a robust base controller, and a residual mixture-of-experts (MoE). Frame-accelerated augmentation exposes the model to high-velocity pose changes by widening inter-frame gaps. The base controller reliably tracks everyday low-dynamic motions, while the residual MoE adaptively allocates additional network capacity to handle challenging high-dynamic actions, significantly enhancing tracking accuracy. In the absence of a public benchmark, we curate the High-Dynamic Humanoid Motion (HDHM) dataset, comprising 3593 physically plausible clips. On HDHM, FARM reduces the tracking failure rate by 42.8% and lowers global mean per-joint position error by 14.6% relative to the baseline, while preserving near-perfect accuracy on low-dynamic motions. These results establish FARM as a new baseline for high-dynamic humanoid control and introduce the first open benchmark dedicated to this challenge.

Given the rapid advancement of robotic technologies, robots will eventually enter our daily lives, performing complex long-horizon tasks. Complex long-horizon tasks, such as furniture assembly, typically contain dozens of subtasks with various scenes. Although complex, assembly is based on several reusable movements. Movement Primitive (MP) is a promising framework for learning reusable movements from demonstrations and adapting the learned movements to the test scenes. The critical step in employing MP methods is categorizing the unlabeled demonstrations into different MPs. However, current MP methods focus on individual MP learning using manually selected demonstrations, neglecting categorization. Manual categorization of demonstrations is easy to fall into suboptimal. If the demonstrations within the same category are too similar, the learned MP cannot be adapted to task scenes with various obstacles. Conversely, a significant distance between demonstrations leads to the MP’s failure in learning. To this end, we propose the following principle for MP categorization: balance the Learnability and Adaptability. Following this principle, we introduce an optimal transportation (OT)-based theoretical framework and a practical solution utilizing an auto-encoder network. We obtain the lower threshold of learnability by OT. Then we increase the adaptability of MP until it reaches the lower threshold of learnability. For complex long-horizon task learning, we propose a balanced MPs-based learning framework that contains four modules, termed BaMPs. BaMPs achieved success rates of 100% and 80%, respectively, in the 12-step and 20-step tasks.

Understanding the relationships between items can improve the accuracy and interpretability of recommender systems. Among these relationships, the substitute and complement relationships attract the most attention in e-commerce platforms. The substitutable items are interchangeable and might be compared with each other before purchasing, while the complementary items are used in conjunction and are usually bought together with the query item. In this paper, we focus on two issues of inferring the substitutable and complementary items: 1) how to model their mutual influence to improve the performance of downstream tasks, 2) how to further discriminate them by considering the strength of relationship for different item pairs. We propose a novel multi-task learning framework named Enhanced Multi-Relationships Integration Graph Convolutional Network (EMRIGCN). We regard the relationship inference task as a link prediction task in heterogeneous graph with different types of edges between nodes (items). To model the mutual influence between substitute and complement, EMRIGCN adopts a two-level integration module, i.e., feature and structure integration, based on experts sharing mechanism during message passing. To obtain the strength of relationship for item pairs, we build an auxiliary loss function to further increase or decrease the distances between embeddings of items with weak or strong relation in latent space. Extensive experiments on both public and industrial datasets prove that EMRIGCN significantly outperforms the state-of-the-art solutions. We also conducted A/B tests on real world recommender systems of Meituan Maicai, an online supermarket platform in China, and obtained 15.3% improvement on VBR and 15.34% improvement on RPM.

Deploying Convolutional Neural Network (CNN)-based applications to mobile platforms can be challenging due to the conflict between the restricted computing capacity of mobile devices and the heavy computational overhead of running a CNN. Network quantization is a promising way of alleviating this problem. However, network quantization can result in accuracy degradation and this is especially the case with the compact CNN architectures that are designed for mobile applications. This paper presents a novel and efficient mixed-precision quantization pipeline, called MBFQuant. It redefines the design space for mixed-precision quantization by keeping the bitwidth of the multiplier fixed, unlike other existing methods, because we have found that the quantized model can maintain almost the same running efficiency, so long as the sum of the quantization bitwidth of the weight and the input activation of a layer is a constant. To maximize the accuracy of a quantized CNN model, we have developed a Simulated Annealing (SA)-based optimizer that can automatically explore the design space, and rapidly find the optimal bitwidth assignment. Comprehensive evaluations applying ten CNN architectures to four datasets have served to demonstrate that MBFQuant can achieve improvements in accuracy of up to 19.34% for image classification and 1.12% for object detection, with respect to a corresponding uniform bitwidth quantized model.

A novel voltage sensor-less control technique, linear ramp follower (LRF), is proposed in this paper for a boost AC/DC pre-regulator. The power factor correction (PFC) pre-regulator controlled by the proposed technique, will require only an inductor current sensor and operate at a constant switching frequency with a simple control circuit. The AC input and DC output voltages are extracted individually from the charging and discharging rate of the sensed inductor current. Thus, this technique reduces the number of sensors required and also accomplishes the noise isolation between the power circuit and the controller. Furthermore, MATLAB simulation results are presented to verify the theoretical analysis

Spatial joins and spatial index creation are two of the most expensive operations in Oracle Spatial. Since spatial indexing is implemented in extensible indexing framework where queries only return rows from a single table, spatial joins could not be effectively and efficiently implemented in Oracle8i and prior releases. On the other hand, spatial indexcreationinvolvesmuchcomputationorI/Othatcouldbe easily parallelized. In this paper, we describe how Oracle Spatial applies parallel and pipelined table function technology to perform fast spatial joins and parallel index creation. This technologyhas been introduced in Oracle9i and allows users to iteratively return subsets of result rows to be used in the “from” clause of a SQL query. We present our experiences with these implementations and examine the performance on real datasets.