ExGes: Expressive Human Motion Retrieval and Modulation for Audio-Driven Gesture Synthesis

Audio-driven human gesture synthesis is a crucial task with broad applications in virtual avatars, human-computer interaction, and creative content generation. Despite notable progress, existing methods often produce gestures that are coarse, lack expressiveness, and fail to fully align with audio semantics. To address these challenges, we propose ExGes, a novel retrieval-enhanced diffusion framework with three key designs: (1) a Motion Base Construction, which builds a gesture library using training dataset; (2) a Motion Retrieval Module, employing constrative learning and momentum distillation for fine-grained reference poses retreiving; and (3) a Precision Control Module, integrating partial masking and stochastic masking to enable flexible and fine-grained control. Experimental evaluations on BEAT2 demonstrate that ExGes reduces Fr\'echet Gesture Distance by 6.2\% and improves motion diversity by 5.3\% over EMAGE, with user studies revealing a 71.3\% preference for its naturalness and semantic relevance. Code will be released upon acceptance.

Introducing Context Information in Lifelong Sequential Modeling using Temporal Convolutional Networks

The importance of lifelong sequential modeling (LSM) is growing in the realm of social media recommendation systems. A key component in this process is the attention module, which derives interest representations with respect to candidate items from the sequence. Typically, attention modules function in a point-wise fashion, concentrating only on the relevance of individual items in the sequence to the candidate item. However, the context information in the neighboring items that is useful for more accurately evaluating the significance of each item has not been taken into account. In this study, we introduce a novel network which employs the Temporal Convolutional Network (TCN) to generate context-aware representations for each item throughout the lifelong sequence. These improved representations are then utilized in the attention module to produce context-aware interest representations. Expanding on this TCN framework, we present a enhancement module which includes multiple TCN layers and their respective attention modules to capture interest representations across different context scopes. Additionally, we also incorporate a lightweight sub-network to create convolution filters based on users' basic profile features. These personalized filters are then applied in the TCN layers instead of the original global filters to produce more user-specific representations. We performed experiments on both a public dataset and a proprietary dataset. The findings indicate that the proposed network surpasses existing methods in terms of prediction accuracy and online performance metrics.

Revolutionizing Battery Disassembly: The Design and Implementation of a Battery Disassembly Autonomous Mobile Manipulator Robot(BEAM-1)

The efficient disassembly of end-of-life electric vehicle batteries(EOL-EVBs) is crucial for green manufacturing and sustainable development. The current pre-programmed disassembly conducted by the Autonomous Mobile Manipulator Robot(AMMR) struggles to meet the disassembly requirements in dynamic environments, complex scenarios, and unstructured processes. In this paper, we propose a Battery Disassembly AMMR(BEAM-1) system based on NeuralSymbolic AI. It detects the environmental state by leveraging a combination of multi-sensors and neural predicates and then translates this information into a quasi-symbolic space. In real-time, it identifies the optimal sequence of action primitives through LLM-heuristic tree search, ensuring high-precision execution of these primitives. Additionally, it employs positional speculative sampling using intuitive networks and achieves the disassembly of various bolt types with a meticulously designed end-effector. Importantly, BEAM-1 is a continuously learning embodied intelligence system capable of subjective reasoning like a human, and possessing intuition. A large number of real scene experiments have proved that it can autonomously perceive, decide, and execute to complete the continuous disassembly of bolts in multiple, multi-category, and complex situations, with a success rate of 98.78%. This research attempts to use NeuroSymbolic AI to give robots real autonomous reasoning, planning, and learning capabilities. BEAM-1 realizes the revolution of battery disassembly. Its framework can be easily ported to any robotic system to realize different application scenarios, which provides a ground-breaking idea for the design and implementation of future embodied intelligent robotic systems.

SimpleFusion: A Simple Fusion Framework for Infrared and Visible Images

Integrating visible and infrared images into one high-quality image, also known as visible and infrared image fusion, is a challenging yet critical task for many downstream vision tasks. Most existing works utilize pretrained deep neural networks or design sophisticated frameworks with strong priors for this task, which may be unsuitable or lack flexibility. This paper presents SimpleFusion, a simple yet effective framework for visible and infrared image fusion. Our framework follows the decompose-and-fusion paradigm, where the visible and the infrared images are decomposed into reflectance and illumination components via Retinex theory and followed by the fusion of these corresponding elements. The whole framework is designed with two plain convolutional neural networks without downsampling, which can perform image decomposition and fusion efficiently. Moreover, we introduce decomposition loss and a detail-to-semantic loss to preserve the complementary information between the two modalities for fusion. We conduct extensive experiments on the challenging benchmarks, verifying the superiority of our method over previous state-of-the-arts. Code is available at \href{https://github.com/hxwxss/SimpleFusion-A-Simple-Fusion-Framework-for-Infrared-and-Visible-Images}{https://github.com/hxwxss/SimpleFusion-A-Simple-Fusion-Framework-for-Infrared-and-Visible-Images}

TCMD: A Traditional Chinese Medicine QA Dataset for Evaluating Large Language Models

The recently unprecedented advancements in Large Language Models (LLMs) have propelled the medical community by establishing advanced medical-domain models. However, due to the limited collection of medical datasets, there are only a few comprehensive benchmarks available to gauge progress in this area. In this paper, we introduce a new medical question-answering (QA) dataset that contains massive manual instruction for solving Traditional Chinese Medicine examination tasks, called TCMD. Specifically, our TCMD collects massive questions across diverse domains with their annotated medical subjects and thus supports us in comprehensively assessing the capability of LLMs in the TCM domain. Extensive evaluation of various general LLMs and medical-domain-specific LLMs is conducted. Moreover, we also analyze the robustness of current LLMs in solving TCM QA tasks by introducing randomness. The inconsistency of the experimental results also reveals the shortcomings of current LLMs in solving QA tasks. We also expect that our dataset can further facilitate the development of LLMs in the TCM area.

OTFS vs OFDM: Which is Superior in Multiuser LEO Satellite Communications

Orthogonal time frequency space (OTFS) modulation, a delay-Doppler (DD) domain communication scheme exhibiting strong robustness against the Doppler shifts, has the potentials to be employed in LEO satellite communications. However, the performance comparison with the orthogonal frequency division multiplexing (OFDM) modulation and the resource allocation scheme for multiuser OTFS-based LEO satellite communication system have rarely been investigated. In this paper, we conduct a performance comparison under various channel conditions between the OTFS and OFDM modulations, encompassing evaluations of sum-rate and bit error ratio (BER). Additionally, we investigate the joint optimal allocation of power and delay-Doppler resource blocks aiming at maximizing sum-rate for multiuser downlink OTFS-based LEO satellite communication systems. Unlike the conventional modulations relaying on complex input-output relations within the Time-Frequency (TF) domain, the OTFS modulation exploits both time and frequency diversities, i.e., delay and Doppler shifts remain constant during a OTFS frame, which facilitates a DD domain input-output simple relation for our investigation. We transform the resulting non-convex and combinatorial optimization problem into an equivalent difference of convex problem by decoupling the conditional constraints, and solve the transformed problem via penalty convex-concave procedure algorithm. Simulation results demonstrate that the OTFS modulation is robust to carrier frequency offsets (CFO) caused by high-mobility of LEO satellites, and has superior performance to the OFDM modulation. Moreover, numerical results indicate that our proposed resource allocation scheme has higher sum-rate than existed schemes for the OTFS modulation, such as delay divided multiple access and Doppler divided multiple access, especially in the high signal-to-noise ratio (SNR) regime.

Towards Agile Robots: Intuitive Robot Position Speculation with Neural Networks

The robot position speculation, which determines where the chassis should move, is one key step to control the mobile manipulators. The target position must ensure the feasibility of chassis movement and manipulability, which is guaranteed by randomized sampling and kinematic checking in traditional methods. Addressing the demands of agile robotics, this paper proposes a robot position speculation network(RPSN), a learning-based approach to enhance the agility of mobile manipulators. The RPSN incorporates a differentiable inverse kinematic algorithm and a neural network. Through end-to-end training, the RPSN can speculate positions with a high success rate. We apply the RPSN to mobile manipulators disassembling end-of-life electric vehicle batteries (EOL-EVBs). Extensive experiments on various simulated environments and physical mobile manipulators demonstrate that the probability of the initial position provided by RPSN being the ideal position is 96.67%. From the kinematic constraint perspective, it achieves 100% generation of the ideal position on average within 1.28 attempts. Much lower than that of random sampling, 31.04. Moreover, the proposed method demonstrates superior data efficiency over pure neural network approaches. The proposed RPSN enables the robot to quickly infer feasible target positions by intuition. This work moves towards building agile robots that can act swiftly like humans.

Joint User Scheduling and Computing Resource Allocation Optimization in Asynchronous Mobile Edge Computing Networks

In this paper, the problem of joint user scheduling and computing resource allocation in asynchronous mobile edge computing (MEC) networks is studied. In such networks, edge devices will offload their computational tasks to an MEC server, using the energy they harvest from this server. To get their tasks processed on time using the harvested energy, edge devices will strategically schedule their task offloading, and compete for the computational resource at the MEC server. Then, the MEC server will execute these tasks asynchronously based on the arrival of the tasks. This joint user scheduling, time and computation resource allocation problem is posed as an optimization framework whose goal is to find the optimal scheduling and allocation strategy that minimizes the energy consumption of these mobile computing tasks. To solve this mixed-integer non-linear programming problem, the general benders decomposition method is adopted which decomposes the original problem into a primal problem and a master problem. Specifically, the primal problem is related to computation resource and time slot allocation, of which the optimal closed-form solution is obtained. The master problem regarding discrete user scheduling variables is constructed by adding optimality cuts or feasibility cuts according to whether the primal problem is feasible, which is a standard mixed-integer linear programming problem and can be efficiently solved. By iteratively solving the primal problem and master problem, the optimal scheduling and resource allocation scheme is obtained. Simulation results demonstrate that the proposed asynchronous computing framework reduces 87.17% energy consumption compared with conventional synchronous computing counterpart.

Unbiasing Enhanced Sampling on a High-dimensional Free Energy Surface with Deep Generative Model

Biased enhanced sampling methods utilizing collective variables (CVs) are powerful tools for sampling conformational ensembles. Due to high intrinsic dimensions, efficiently generating conformational ensembles for complex systems requires enhanced sampling on high-dimensional free energy surfaces. While methods like temperature-accelerated molecular dynamics (TAMD) can adopt many CVs in a simulation, unbiasing the simulation requires accurate modeling of a high-dimensional CV probability distribution, which is challenging for traditional density estimation techniques. Here we propose an unbiasing method based on the score-based diffusion model, a deep generative learning method that excels in density estimation across complex data landscapes. We test the score-based diffusion unbiasing method on TAMD simulations. The results demonstrate that this unbiasing approach significantly outperforms traditional unbiasing methods, and can generate accurate unbiased conformational ensembles for simulations with a number of CVs higher than usual ranges.

Cross Domain LifeLong Sequential Modeling for Online Click-Through Rate Prediction

Deep neural networks (DNNs) that incorporated lifelong sequential modeling (LSM) have brought great success to recommendation systems in various social media platforms. While continuous improvements have been made in domain-specific LSM, limited work has been done in cross-domain LSM, which considers modeling of lifelong sequences of both target domain and source domain. In this paper, we propose Lifelong Cross Network (LCN) to incorporate cross-domain LSM to improve the click-through rate (CTR) prediction in the target domain. The proposed LCN contains a LifeLong Attention Pyramid (LAP) module that comprises of three levels of cascaded attentions to effectively extract interest representations with respect to the candidate item from lifelong sequences. We also propose Cross Representation Production (CRP) module to enforce additional supervision on the learning and alignment of cross-domain representations so that they can be better reused on learning of the CTR prediction in the target domain. We conducted extensive experiments on WeChat Channels industrial dataset as well as on benchmark dataset. Results have revealed that the proposed LCN outperforms existing work in terms of both prediction accuracy and online performance.