arXiv subjects

Weijun Wang

Publications and source records attributed to Weijun Wang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Trajectory Planning of a Curtain Wall Installation Robot Based on Biomimetic Mechanisms

As the robotics market rapidly evolves, energy consumption has become a critical issue, particularly restricting the application of construction robots. To tackle this challenge, our study innovatively draws inspiration from the mechanics of human upper limb movements during weight lifting, proposing a bio-inspired trajectory planning framework that incorporates human energy conversion principles. By collecting motion trajectories and electromyography (EMG) signals during dumbbell curls, we construct an anthropomorphic trajectory planning that integrates human force exertion patterns and energy consumption patterns. Utilizing the Particle Swarm Optimization (PSO) algorithm, we achieve dynamic load distribution for robotic arm trajectory planning based on human-like movement features. In practical application, these bio-inspired movement characteristics are applied to curtain wall installation tasks, validating the correctness and superiority of our trajectory planning method. Simulation results demonstrate a 48.4% reduction in energy consumption through intelligent conversion between kinetic and potential energy. This approach provides new insights and theoretical support for optimizing energy use in curtain wall installation robots during actual handling tasks.

cs.RO↗

arXiv2025

Design and Dimensional Optimization of Legged Structures for Construction Robots

Faced with complex and unstructured construction environments, wheeled and tracked robots exhibit significant limitations in terrain adaptability and flexibility, making it difficult to meet the requirements of autonomous operation. Inspired by ants in nature, this paper proposes a leg configuration design and optimization method tailored for construction scenarios, aiming to enhance the autonomous mobility of construction robots. This paper analyzes the full operational motion performance of the leg during both swing and stance phases. First, based on kinematic modeling and multi-dimensional workspace analysis, the concept of an "improved workspace" is introduced, and graphical methods are used to optimize the leg dimensions during the swing phase. Furthermore, a new concept of "average manipulability" is introduced based on the velocity Jacobian matrix, and numerical solutions are applied to obtain the leg segment ratio that maximizes manipulability. To overcome the difficulties associated with traditional analytical methods, virtual prototype simulations are conducted in ADAMS to explore the relationship between the robot body's optimal flexibility and leg segment proportions. In summary, the leg segment proportions with the best comprehensive motion performance are obtained. This study presents the first multi-dimensional quantitative evaluation framework for leg motion performance tailored for construction environments, providing a structural design foundation for legged construction robots to achieve autonomous mobility in complex terrains.

cs.RO↗

arXiv2025

Topology Optimization of Leg Structures for Construction Robots Based on Variable Density Method

In complex terrain construction environments, there are high demands for robots to achieve both high payload capacity and mobility flexibility. As the key load-bearing component, the optimization of robotic leg structures is of particular importance. Therefore, this study focuses on the optimization of leg structures for construction robots, proposing a topology optimization strategy based on the SIMP (Solid Isotropic Microstructures with Penalization) variable density method along with a structural re-design approach. The design performance is comprehensively validated through finite element analysis using ANSYS. First, static and modal analyses are conducted to evaluate the rationality of the initial design. Then, topology optimization using the SIMP-based variable density method is applied to the femur section, which accounts for the largest proportion of the leg's weight. Based on iterative calculations, the femur undergoes secondary structural reconstruction. After optimization, the mass of the femur is reduced by 19.45\%, and the overall leg mass decreases by 7.92\%, achieving the goal of lightweight design. Finally, static and modal analyses are conducted on the reconstructed leg. The results demonstrate that the optimized leg still meets structural performance requirements, validating the feasibility of lightweight design. This research provides robust theoretical and technical support for lightweight construction robot design and lays a foundation for their efficient operation in complex construction environments.

cs.RO↗

arXiv2025

Decision PCR: Decision version of the Point Cloud Registration task

Low-overlap point cloud registration (PCR) remains a significant challenge in 3D vision. Traditional evaluation metrics, such as Maximum Inlier Count, become ineffective under extremely low inlier ratios. In this paper, we revisit the registration result evaluation problem and identify the Decision version of the PCR task as the fundamental problem. To address this Decision PCR task, we propose a data-driven approach. First, we construct a corresponding dataset based on the 3DMatch dataset. Then, a deep learning-based classifier is trained to reliably assess registration quality, overcoming the limitations of traditional metrics. To our knowledge, this is the first comprehensive study to address this task through a deep learning framework. We incorporate this classifier into standard PCR pipelines. When integrated with our approach, existing state-of-the-art PCR methods exhibit significantly enhanced registration performance. For example, combining our framework with GeoTransformer achieves a new SOTA registration recall of 86.97\% on the challenging 3DLoMatch benchmark. Our method also demonstrates strong generalization capabilities on the unseen outdoor ETH dataset.

cs.CV↗

arXiv2025

KVShare: An LLM Service System with Efficient and Effective Multi-Tenant KV Cache Reuse

Recent advances in long-text understanding have pushed the context length of large language models (LLMs) up to one million tokens. It boosts LLMs's accuracy and reasoning capacity but causes exorbitant computational costs and unsatisfactory Time to First Token (TTFT). KV cache reuse, which reuses the exact same KV cache of prefixes and templates or shares similar ones but with extra selective recomputation, offers a promising way to tackle this issue. However, prior studies overlook the cross-request KV reuse and the attention deviations introduced by new tokens during the decoding stage. In this paper, we present a KV cache management module that shares the KV cache across requests under multi-tenant scenarios without sacrificing model accuracy. Our system, KVShare, enables accurate and efficient LLM serving by 1) a Dual-Stage High Deviation algorithm (DHD) that conditionally selects a small portion of KV cache to be recomputed during both prefill and decode phases, and 2) a cache-aware scheduler that prioritizes requests based on their KV cache hit rates and orchestrates continuous batching to achieve enhanced system efficiency and faster TTFT. Multi-task experiments conducted on models such as Qwen2.5-7B,Llama3.1-8B and Yi1.5-9B demonstrate that KVShare reduces TTFT by up to 9.39x and increases 1.2x of the throughput compared to the full KV recompute. Moreover, KVShare achieves 20.38% boost in terms of accuracy compared to SOTA methods.

cs.CL↗

arXiv2025

Region-based Content Enhancement for Efficient Video Analytics at the Edge

Video analytics is widespread in various applications serving our society. Recent advances of content enhancement in video analytics offer significant benefits for the bandwidth saving and accuracy improvement. However, existing content-enhanced video analytics systems are excessively computationally expensive and provide extremely low throughput. In this paper, we present region-based content enhancement, that enhances only the important regions in videos, to improve analytical accuracy. Our system, RegenHance, enables high-accuracy and high-throughput video analytics at the edge by 1) a macroblock-based region importance predictor that identifies the important regions fast and precisely, 2) a region-aware enhancer that stitches sparsely distributed regions into dense tensors and enhances them efficiently, and 3) a profile-based execution planer that allocates appropriate resources for enhancement and analytics components. We prototype RegenHance on five heterogeneous edge devices. Experiments on two analytical tasks reveal that region-based enhancement improves the overall accuracy of 10-19% and achieves 2-3x throughput compared to the state-of-the-art frame-based enhancement methods.

cs.NI↗

arXiv2025

Empower Vision Applications with LoRA LMM

Large Multimodal Models (LMMs) have shown significant progress in various complex vision tasks with the solid linguistic and reasoning capacity inherited from large language models (LMMs). Low-rank adaptation (LoRA) offers a promising method to integrate external knowledge into LMMs, compensating for their limitations on domain-specific tasks. However, the existing LoRA model serving is excessively computationally expensive and causes extremely high latency. In this paper, we present an end-to-end solution that empowers diverse vision tasks and enriches vision applications with LoRA LMMs. Our system, VaLoRA, enables accurate and efficient vision tasks by 1) an accuracy-aware LoRA adapter generation approach that generates LoRA adapters rich in domain-specific knowledge to meet application-specific accuracy requirements, 2) an adaptive-tiling LoRA adapters batching operator that efficiently computes concurrent heterogeneous LoRA adapters, and 3) a flexible LoRA adapter orchestration mechanism that manages application requests and LoRA adapters to achieve the lowest average response latency. We prototype VaLoRA on five popular vision tasks on three LMMs. Experiment results reveal that VaLoRA improves 24-62% of the accuracy compared to the original LMMs and reduces 20-89% of the latency compared to the state-of-the-art LoRA model serving systems.

cs.CV↗

arXiv2024

GS-Matching: Reconsidering Feature Matching task in Point Cloud Registration

Traditional point cloud registration (PCR) methods for feature matching often employ the nearest neighbor policy. This leads to many-to-one matches and numerous potential inliers without any corresponding point. Recently, some approaches have framed the feature matching task as an assignment problem to achieve optimal one-to-one matches. We argue that the transition to the Assignment problem is not reliable for general correspondence-based PCR. In this paper, we propose a heuristics stable matching policy called GS-matching, inspired by the Gale-Shapley algorithm. Compared to the other matching policies, our method can perform efficiently and find more non-repetitive inliers under low overlapping conditions. Furthermore, we employ the probability theory to analyze the feature matching task, providing new insights into this research problem. Extensive experiments validate the effectiveness of our matching policy, achieving better registration recall on multiple datasets.

cs.CV↗

arXiv2024

MobileNetV4 -- Universal Models for the Mobile Ecosystem

We present the latest generation of MobileNets, known as MobileNetV4 (MNv4), featuring universally efficient architecture designs for mobile devices. At its core, we introduce the Universal Inverted Bottleneck (UIB) search block, a unified and flexible structure that merges Inverted Bottleneck (IB), ConvNext, Feed Forward Network (FFN), and a novel Extra Depthwise (ExtraDW) variant. Alongside UIB, we present Mobile MQA, an attention block tailored for mobile accelerators, delivering a significant 39% speedup. An optimized neural architecture search (NAS) recipe is also introduced which improves MNv4 search effectiveness. The integration of UIB, Mobile MQA and the refined NAS recipe results in a new suite of MNv4 models that are mostly Pareto optimal across mobile CPUs, DSPs, GPUs, as well as specialized accelerators like Apple Neural Engine and Google Pixel EdgeTPU - a characteristic not found in any other models tested. Finally, to further boost accuracy, we introduce a novel distillation technique. Enhanced by this technique, our MNv4-Hybrid-Large model delivers 87% ImageNet-1K accuracy, with a Pixel 8 EdgeTPU runtime of just 3.8ms.

cs.CV↗

arXiv2024

Sight View Constraint for Robust Point Cloud Registration

Partial to Partial Point Cloud Registration (partial PCR) remains a challenging task, particularly when dealing with a low overlap rate. In comparison to the full-to-full registration task, we find that the objective of partial PCR is still not well-defined, indicating no metric can reliably identify the true transformation. We identify this as the most fundamental challenge in partial PCR tasks. In this paper, instead of directly seeking the optimal transformation, we propose a novel and general Sight View Constraint (SVC) to conclusively identify incorrect transformations, thereby enhancing the robustness of existing PCR methods. Extensive experiments validate the effectiveness of SVC on both indoor and outdoor scenes. On the challenging 3DLoMatch dataset, our approach increases the registration recall from 78\% to 82\%, achieving the state-of-the-art result. This research also highlights the significance of the decision version problem of partial PCR, which has the potential to provide novel insights into the partial PCR problem.

cs.CV↗

arXiv2024

Robust Multi-Robot Global Localization with Unknown Initial Pose based on Neighbor Constraints

Multi-robot global localization (MR-GL) with unknown initial positions in a large scale environment is a challenging task. The key point is the data association between different robots' viewpoints. It also makes traditional Appearance-based localization methods unusable. Recently, researchers have utilized the object's semantic invariance to generate a semantic graph to address this issue. However, previous works lack robustness and are sensitive to overlap rate of maps, resulting in unpredictable performance in real-world environments. In this paper, we propose a data association algorithm based on neighbor constraints to improve the robustness of the system. We demonstrate the effectiveness of our method on three different datasets, indicating a significant improvement in robustness compared to previous works.

cs.RO↗

arXiv2024

SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget

Mixture of experts (MoE) is a popular technique to improve capacity of Large Language Models (LLMs) with conditionally-activated parallel experts. However, serving MoE models on memory-constrained devices is challenging due to the large parameter size. Typical solutions such as memory swapping or expert pruning may lead to significantly higher latency or severe accuracy loss. In this paper, we introduce SwapMoE, a framework for efficient serving of MoE-based large language models with tunable memory budgets. The main idea of SwapMoE is to keep a small dynamic set of important experts, namely Virtual Experts, in the main memory for inference, while seamlessly maintaining how the Virtual Experts map to the actual experts. Experiments have shown that SwapMoE can reduce the memory footprint while maintaining reasonable accuracy. For example, on text summarization tasks with Switch Transformer, SwapMoE can reduce the memory consumption from 14.2 GiB to 4.7 GiB, together with 50\% latency reduction and a slight Rouge-2 score drop of 0.041.

cs.AI↗

arXiv2024

LoRA-Switch: Boosting the Efficiency of Dynamic LLM Adapters via System-Algorithm Co-design

Recent literature has found that an effective method to customize or further improve large language models (LLMs) is to add dynamic adapters, such as low-rank adapters (LoRA) with Mixture-of-Experts (MoE) structures. Though such dynamic adapters incur modest computational complexity, they surprisingly lead to huge inference latency overhead, slowing down the decoding speed by 2.5+ times. In this paper, we analyze the fine-grained costs of the dynamic adapters and find that the fragmented CUDA kernel calls are the root cause. Therefore, we propose LoRA-Switch, a system-algorithm co-designed architecture for efficient dynamic adapters. Unlike most existing dynamic structures that adopt layer-wise or block-wise dynamic routing, LoRA-Switch introduces a token-wise routing mechanism. It switches the LoRA adapters and weights for each token and merges them into the backbone for inference. For efficiency, this switching is implemented with an optimized CUDA kernel, which fuses the merging operations for all LoRA adapters at once. Based on experiments with popular open-source LLMs on common benchmarks, our approach has demonstrated similar accuracy improvement as existing dynamic adapters, while reducing the decoding latency by more than 2.4 times.

cs.AI↗

arXiv2024

Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security

Since the advent of personal computing devices, intelligent personal assistants (IPAs) have been one of the key technologies that researchers and engineers have focused on, aiming to help users efficiently obtain information and execute tasks, and provide users with more intelligent, convenient, and rich interaction experiences. With the development of smartphones and IoT, computing and sensing devices have become ubiquitous, greatly expanding the boundaries of IPAs. However, due to the lack of capabilities such as user intent understanding, task planning, tool using, and personal data management etc., existing IPAs still have limited practicality and scalability. Recently, the emergence of foundation models, represented by large language models (LLMs), brings new opportunities for the development of IPAs. With the powerful semantic understanding and reasoning capabilities, LLM can enable intelligent agents to solve complex problems autonomously. In this paper, we focus on Personal LLM Agents, which are LLM-based agents that are deeply integrated with personal data and personal devices and used for personal assistance. We envision that Personal LLM Agents will become a major software paradigm for end-users in the upcoming era. To realize this vision, we take the first step to discuss several important questions about Personal LLM Agents, including their architecture, capability, efficiency and security. We start by summarizing the key components and design choices in the architecture of Personal LLM Agents, followed by an in-depth analysis of the opinions collected from domain experts. Next, we discuss several key challenges to achieve intelligent, efficient and secure Personal LLM Agents, followed by a comprehensive survey of representative solutions to address these challenges.

cs.HC↗

arXiv2024

BiSwift: Bandwidth Orchestrator for Multi-Stream Video Analytics on Edge

High-definition (HD) cameras for surveillance and road traffic have experienced tremendous growth, demanding intensive computation resources for real-time analytics. Recently, offloading frames from the front-end device to the back-end edge server has shown great promise. In multi-stream competitive environments, efficient bandwidth management and proper scheduling are crucial to ensure both high inference accuracy and high throughput. To achieve this goal, we propose BiSwift, a bi-level framework that scales the concurrent real-time video analytics by a novel adaptive hybrid codec integrated with multi-level pipelines, and a global bandwidth controller for multiple video streams. The lower-level front-back-end collaborative mechanism (called adaptive hybrid codec) locally optimizes the accuracy and accelerates end-to-end video analytics for a single stream. The upper-level scheduler aims to accuracy fairness among multiple streams via the global bandwidth controller. The evaluation of BiSwift shows that BiSwift is able to real-time object detection on 9 streams with an edge device only equipped with an NVIDIA RTX3070 (8G) GPU. BiSwift improves 10%$\sim$21% accuracy and presents 1.2$\sim$9$\times$ throughput compared with the state-of-the-art video analytics pipelines.

cs.NI↗

arXiv2023

ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation

This paper presents a new mechanism to facilitate the training of mask transformers for efficient panoptic segmentation, democratizing its deployment. We observe that due to its high complexity, the training objective of panoptic segmentation will inevitably lead to much higher false positive penalization. Such unbalanced loss makes the training process of the end-to-end mask-transformer based architectures difficult, especially for efficient models. In this paper, we present ReMaX that adds relaxation to mask predictions and class predictions during training for panoptic segmentation. We demonstrate that via these simple relaxation techniques during training, our model can be consistently improved by a clear margin \textbf{without} any extra computational cost on inference. By combining our method with efficient backbones like MobileNetV3-Small, our method achieves new state-of-the-art results for efficient panoptic segmentation on COCO, ADE20K and Cityscapes. Code and pre-trained checkpoints will be available at \url{https://github.com/google-research/deeplab2}.

cs.CV↗

arXiv2023

AccDecoder: Accelerated Decoding for Neural-enhanced Video Analytics

The quality of the video stream is key to neural network-based video analytics. However, low-quality video is inevitably collected by existing surveillance systems because of poor quality cameras or over-compressed/pruned video streaming protocols, e.g., as a result of upstream bandwidth limit. To address this issue, existing studies use quality enhancers (e.g., neural super-resolution) to improve the quality of videos (e.g., resolution) and eventually ensure inference accuracy. Nevertheless, directly applying quality enhancers does not work in practice because it will introduce unacceptable latency. In this paper, we present AccDecoder, a novel accelerated decoder for real-time and neural-enhanced video analytics. AccDecoder can select a few frames adaptively via Deep Reinforcement Learning (DRL) to enhance the quality by neural super-resolution and then up-scale the unselected frames that reference them, which leads to 6-21% accuracy improvement. AccDecoder provides efficient inference capability via filtering important frames using DRL for DNN-based inference and reusing the results for the other frames via extracting the reference relationship among frames and blocks, which results in a latency reduction of 20-80% than baselines.

cs.CV↗

arXiv2021

MOSAIC: Mobile Segmentation via decoding Aggregated Information and encoded Context

We present a next-generation neural network architecture, MOSAIC, for efficient and accurate semantic image segmentation on mobile devices. MOSAIC is designed using commonly supported neural operations by diverse mobile hardware platforms for flexible deployment across various mobile platforms. With a simple asymmetric encoder-decoder structure which consists of an efficient multi-scale context encoder and a light-weight hybrid decoder to recover spatial details from aggregated information, MOSAIC achieves new state-of-the-art performance while balancing accuracy and computational cost. Deployed on top of a tailored feature extraction backbone based on a searched classification network, MOSAIC achieves a 5% absolute accuracy gain surpassing the current industry standard MLPerf models and state-of-the-art architectures.

cs.CV↗