Shiguo Lian

Yajun Xu, Chuwen Huang, Yibing Nan et al.

Automatic traffic accidents detection has appealed to the machine vision community due to its implications on the development of autonomous intelligent transportation systems (ITS) and importance to traffic safety. Most previous studies on efficient analysis and prediction of traffic accidents, however, have used small-scale datasets with limited coverage, which limits their effect and applicability. Existing datasets in traffic accidents are either small-scale, not from surveillance cameras, not open-sourced, or not built for freeway scenes. Since accidents happened in freeways tend to cause serious damage and are too fast to catch the spot. An open-sourced datasets targeting on freeway traffic accidents collected from surveillance cameras is in great need and of practical importance. In order to help the vision community address these shortcomings, we endeavor to collect video data of real traffic accidents that covered abundant scenes. After integration and annotation by various dimensions, a large-scale traffic accidents dataset named TAD is proposed in this work. Various experiments on image classification, object detection, and video classification tasks, using public mainstream vision algorithms or frameworks are conducted in this work to demonstrate performance of different methods. The proposed dataset together with the experimental results are presented as a new benchmark to improve computer vision research, especially in ITS.

Huan Hu, Yajie Cui, Zhaoxiang Liu et al.

Deep learning has a wide range of applications in industrial scenario, but reducing false alarm (FA) remains a major difficulty. Optimizing network architecture or network parameters is used to tackle this challenge in academic circles, while ignoring the essential characteristics of data in application scenarios, which often results in increased FA in new scenarios. In this paper, we propose a novel paradigm for fine-grained design of datasets, driven by industrial applications. We flexibly select positive and negative sample sets according to the essential features of the data and application requirements, and add the remaining samples to the training set as uncertainty classes. We collect more than 10,000 mask-wearing recognition samples covering various application scenarios as our experimental data. Compared with the traditional data design methods, our method achieves better results and effectively reduces FA. We make all contributions available to the research community for broader use. The contributions will be available at https://github.com/huh30/OpenDatasets.

Zezhou Chen, Yajie Cui, Kaikai Zhao et al.

Human action recognition in computer vision has been widely studied in recent years. However, most algorithms consider only certain action specially with even high computational cost. That is not suitable for practical applications with multiple actions to be identified with low computational cost. To meet various application scenarios, this paper presents a unified human action recognition framework composed of two modules, i.e., multi-form human detection and corresponding action classification. Among them, an open-source dataset is constructed to train a multi-form human detection model that distinguishes a human being's whole body, upper body or part body, and the followed action classification model is adopted to recognize such action as falling, sleeping or on-duty, etc. Some experimental results show that the unified framework is effective for various application scenarios. It is expected to be a new application-driven AI paradigm for human action recognition.

Yajie Cui, Zhaoxiang Liu, Shiguo Lian

In line with the development of Industry 4.0, surface defect detection/anomaly detection becomes a topical subject in the industry field. Improving efficiency as well as saving labor costs has steadily become a matter of great concern in practice, where deep learning-based algorithms perform better than traditional vision inspection methods in recent years. While existing deep learning-based algorithms are biased towards supervised learning, which not only necessitates a huge amount of labeled data and human labor, but also brings about inefficiency and limitations. In contrast, recent research shows that unsupervised learning has great potential in tackling the above disadvantages for visual industrial anomaly detection. In this survey, we summarize current challenges and provide a thorough overview of recently proposed unsupervised algorithms for visual industrial anomaly detection covering five categories, whose innovation points and frameworks are described in detail. Meanwhile, publicly available datasets for industrial anomaly detection are introduced. By comparing different classes of methods, the advantages and disadvantages of anomaly detection algorithms are summarized. Based on the current research framework, we point out the core issue that remains to be resolved and provide further improvement directions. Meanwhile, based on the latest technological trends, we offer insights into future research directions. It is expected to assist both the research community and industry in developing a broader and cross-domain perspective.

Yanyang Wang, Zhaoxiang Liu, Shiguo Lian

In recent years, deep learning technology has been maturely applied in the field of object detection, and most algorithms tend to be supervised learning. However, a large amount of labeled data requires high costs of human resources, which brings about low efficiency and limitations. Semi-supervised object detection (SSOD) has been paid more and more attentions due to its high research value and practicability. It is designed to learn information by using small amounts of labeled data and large amounts of unlabeled data. In this paper, we present a comprehensive and up-to-date survey on the SSOD approaches from five aspects. We first briefly introduce several ways of data augmentation. Then, we dive the mainstream semi-supervised strategies into pseudo labels, consistent regularization, graph based and transfer learning based methods, and introduce some methods in challenging settings. We further present widely-used loss functions, and then we outline the common benchmark datasets and compare the accuracy among different representative approaches. Finally, we conclude this paper and present some promising research directions for the future. Our survey aims to provide researchers and practitioners new to the field as well as more advanced readers with a solid understanding of the main approaches developed over the past few years.

Jianfeng Huang, Chenyang Li, Yimin Lin et al.

It is hard to collect enough flaw images for training deep learning network in industrial production. Therefore, existing industrial anomaly detection methods prefer to use CNN-based unsupervised detection and localization network to achieve this task. However, these methods always fail when there are varieties happened in new signals since traditional end-to-end networks suffer barriers of fitting nonlinear model in high-dimensional space. Moreover, they have a memory library by clustering the feature of normal images essentially, which cause it is not robust to texture change. To this end, we propose the Vision Transformer based (VIT-based) unsupervised anomaly detection network. It utilizes a hierarchical task learning and human experience to enhance its interpretability. Our network consists of pattern generation and comparison networks. Pattern generation network uses two VIT-based encoder modules to extract the feature of two consecutive image patches, then uses VIT-based decoder module to learn the human designed style of these features and predict the third image patch. After this, we use the Siamese-based network to compute the similarity of the generation image patch and original image patch. Finally, we refine the anomaly localization by the bi-directional inference strategy. Comparison experiments on public dataset MVTec dataset show our method achieves 99.8% AUC, which surpasses previous state-of-the-art methods. In addition, we give a qualitative illustration on our own leather and cloth datasets. The accurate segment results strongly prove the accuracy of our method in anomaly detection.

Xiaohong Li, Xiang Wang, Kai Wang et al.

Generating synchronized and natural lip movement with speech is one of the most important tasks in creating realistic virtual characters. In this paper, we present a combined deep neural network of one-dimensional convolutions and LSTM to generate vertex displacement of a 3D template face model from variable-length speech input. The motion of the lower part of the face, which is represented by the vertex movement of 3D lip shapes, is consistent with the input speech. In order to enhance the robustness of the network to different sound signals, we adapt a trained speech recognition model to extract speech feature, and a velocity loss term is adopted to reduce the jitter of generated facial animation. We recorded a series of videos of a Chinese adult speaking Mandarin and created a new speech-animation dataset to compensate the lack of such public data. Qualitative and quantitative evaluations indicate that our model is able to generate smooth and natural lip movements synchronized with speech.

Yajie Cui, Zhaoxiang Liu, Shiguo Lian

Anomaly detection without priors of the anomalies is challenging. In the field of unsupervised anomaly detection, traditional auto-encoder (AE) tends to fail based on the assumption that by training only on normal images, the model will not be able to reconstruct abnormal images correctly. On the contrary, we propose a novel patch-wise auto-encoder (Patch AE) framework, which aims at enhancing the reconstruction ability of AE to anomalies instead of weakening it. Each patch of image is reconstructed by corresponding spatially distributed feature vector of the learned feature representation, i.e., patch-wise reconstruction, which ensures anomaly-sensitivity of AE. Our method is simple and efficient. It advances the state-of-the-art performances on Mvtec AD benchmark, which proves the effectiveness of our model. It shows great potential in practical industrial application scenarios.

Shaoan Zhao, Huanlin Gao, Qiang Hui et al.

MediaClaw is a multimodal agent platform built on the OpenClaw ecosystem. Its core design follows a three-layer architecture of unified abstraction, pluginized extension, and workflow orchestration. The system is intended to address practical deployment pain points in AIGC adoption, including fragmented capabilities, heterogeneous interfaces, disconnected production processes, and limited reuse of high-quality production workflows. \system{} abstracts full-category AIGC capabilities into a unified invocation model, uses plugins to support hot-pluggable capability expansion, and uses task-oriented Skills to turn complex production processes into reusable workflow assets. This report focuses on the architectural design philosophy of MediaClaw, the design logic of its core capability model, and the key engineering trade-offs in implementation. It aims to provide reusable practical reference for building multimodal capability platforms.

Zhicheng Ma, Xiang Liu, Zhaoxiang Liu et al.

Large Language Models (LLMs) based on Mixture-of-Experts (MoE) are pivotal in industrial applications for their ability to scale performance efficiently. However, standard MoEs enforce uniform expert sizes,creating a rigidity that fails to align computational costs with varying token-level complexity. While heterogeneous expert architectures attempt to address this by diversifying expert sizes, they often suffer from significant system-level challenges, specifically unbalanced GPU utilization and inefficient parameter utilization, which hinder practical deployment. To bridge the gap between theoretical heterogeneity and robust industrial application, we propose Mixture of Heterogeneous Grouped Experts (MoHGE) which introduces a two-level routing mechanism to enable flexible, resource-aware expert combinations. To optimize inference efficiency, we propose a Group-Wise Auxiliary Loss, which dynamically steers tokens to the most parameter-efficient expert groups based on task difficulty. To address the critical deployment challenge of GPU load balancing, we introduce an All-size Group-decoupling Allocation strategy coupled with an Intra-Group Experts Auxiliary Loss. These mechanisms collectively ensure uniform computation distribution across GPUs. Extensive evaluations demonstrate that MoHGE matches the performance of MoE architectures while reducing the total parameters by approximately 20% and maintaining balanced GPU utilization. Our work establishes a scalable paradigm for resource-efficient MoE design, offering a practical solution for optimizing inference costs in real-world scenarios.

Minjie Hua, Yibing Nan, Shiguo Lian

Person counting is considered as a fundamental task in video surveillance. However, the scenario diversity in practical applications makes it difficult to exploit a single person counting model for general use. Consequently, engineers must preview the video stream and manually specify an appropriate person counting model based on the scenario of camera shot, which is time-consuming, especially for large-scale deployments. In this paper, we propose a person counting paradigm that utilizes a scenario classifier to automatically select a suitable person counting model for each captured frame. First, the input image is passed through the scenario classifier to obtain a scenario label, which is then used to allocate the frame to one of five fine-tuned models for person counting. Additionally, we present five augmentation datasets collected from different scenarios, including side-view, long-shot, top-view, customized and crowd, which are also integrated to form a scenario classification dataset containing 26323 samples. In our comparative experiments, the proposed paradigm achieves better balance than any single model on the integrated dataset, thus its generalization in various scenarios has been proved.

Kohou Wang, Zhaoxiang Liu, Shiguo Lian

In practical applications especially with safety requirement, some hand-held actions need to be monitored closely, including smoking cigarettes, dialing, eating, etc. Taking smoking cigarettes as example, existing smoke detection algorithms usually detect the cigarette or cigarette with hand as the target object only, which leads to low accuracy. In this paper, we propose an application-driven AI paradigm for hand-held action detection based on hierarchical object detection. It is a coarse-to-fine hierarchical detection framework composed of two modules. The first one is a coarse detection module with the human pose consisting of the whole hand, cigarette and head as target object. The followed second one is a fine detection module with the fingers holding cigarette, mouth area and the whole cigarette as target. Some experiments are done with the dataset collected from real-world scenarios, and the results show that the proposed framework achieve higher detection rate with good adaptation and robustness in complex environments.

Kaikai Zhao, Yajie Cui, Zhaoxiang Liu et al.

In the field of waste copper granules recycling, engineers should be able to identify all different sorts of impurities in waste copper granules and estimate their mass proportion relying on experience before rating. This manual rating method is costly, lacking in objectivity and comprehensiveness. To tackle this problem, we propose a waste copper granules rating system based on machine vision and deep learning. We firstly formulate the rating task into a 2D image recognition and purity regression task. Then we design a two-stage convolutional rating network to compute the mass purity and rating level of waste copper granules. Our rating network includes a segmentation network and a purity regression network, which respectively calculate the semantic segmentation heatmaps and purity results of the waste copper granules. After training the rating network on the augmented datasets, experiments on real waste copper granules demonstrate the effectiveness and superiority of the proposed network. Specifically, our system is superior to the manual method in terms of accuracy, effectiveness, robustness, and objectivity.

Yi Shen, Jian Zhang, Jieyun Huang et al.

Recent advancements in slow thinking reasoning models have shown exceptional performance in complex reasoning tasks. However, these models often exhibit overthinking (generating redundant reasoning steps for simple problems), leading to excessive computational resource usage. While current mitigation strategies uniformly reduce reasoning tokens, they risk degrading performance on challenging tasks that require extended reasoning. This paper introduces Difficulty-Adaptive Slow Thinking (DAST), a novel framework that enables models to autonomously adjust the length of Chain-of-Thought (CoT) based on problem difficulty. We first propose a Token Length Budget (TLB) metric to quantify difficulty, then leverage budget-aware reward shaping and budget preference optimization to implement DAST. DAST penalizes overlong responses for simple tasks while incentivizing sufficient reasoning for complex problems. Experiments on diverse datasets and model scales demonstrate that DAST effectively mitigates overthinking (reducing token usage by over 30\% on average) while preserving reasoning accuracy on complex problems. Our codes and models are available at https://github.com/AnonymousUser0520/AnonymousRepo01.

Ruijia Wu, Ping Chen, Fei Shen et al.

Contrastive vision-language models like CLIP have achieved impressive results in image-text retrieval by aligning image and text representations in a shared embedding space. However, these models often treat text as flat sequences, limiting their ability to handle complex, compositional, and long-form descriptions. In particular, they fail to capture two essential properties of language: semantic hierarchy, which reflects the multi-level compositional structure of text, and semantic monotonicity, where richer descriptions should result in stronger alignment with visual content.To address these limitations, we propose HiMo-CLIP, a representation-level framework that enhances CLIP-style models without modifying the encoder architecture. HiMo-CLIP introduces two key components: a hierarchical decomposition (HiDe) module that extracts latent semantic components from long-form text via in-batch PCA, enabling flexible, batch-aware alignment across different semantic granularities, and a monotonicity-aware contrastive loss (MoLo) that jointly aligns global and component-level representations, encouraging the model to internalize semantic ordering and alignment strength as a function of textual completeness.These components work in concert to produce structured, cognitively-aligned cross-modal representations. Experiments on multiple image-text retrieval benchmarks show that HiMo-CLIP consistently outperforms strong baselines, particularly under long or compositional descriptions. The code is available at https://github.com/UnicomAI/HiMo-CLIP.

Huanlin Gao, Ping Chen, Fuyuan Shi et al.

We present LeMiCa, a training-free and efficient acceleration framework for diffusion-based video generation. While existing caching strategies primarily focus on reducing local heuristic errors, they often overlook the accumulation of global errors, leading to noticeable content degradation between accelerated and original videos. To address this issue, we formulate cache scheduling as a directed graph with error-weighted edges and introduce a Lexicographic Minimax Path Optimization strategy that explicitly bounds the worst-case path error. This approach substantially improves the consistency of global content and style across generated frames. Extensive experiments on multiple text-to-video benchmarks demonstrate that LeMiCa delivers dual improvements in both inference speed and generation quality. Notably, our method achieves a 2.9x speedup on the Latte model and reaches an LPIPS score of 0.05 on Open-Sora, outperforming prior caching techniques. Importantly, these gains come with minimal perceptual quality degradation, making LeMiCa a robust and generalizable paradigm for accelerating diffusion-based video generation. We believe this approach can serve as a strong foundation for future research on efficient and reliable video synthesis. Our code is available at :https://github.com/UnicomAI/LeMiCa

Wenjing Zhang, Xuejiao Lei, Zhaoxiang Liu et al.

Recently, the DeepSeek series of models, leveraging their exceptional reasoning capabilities and open-source strategy, is reshaping the global AI landscape. Despite these advantages, they exhibit significant safety deficiencies. Research conducted by Robust Intelligence, a subsidiary of Cisco, in collaboration with the University of Pennsylvania, revealed that DeepSeek-R1 has a 100\% attack success rate when processing harmful prompts. Additionally, multiple safety companies and research institutions have confirmed critical safety vulnerabilities in this model. As models demonstrating robust performance in Chinese and English, DeepSeek models require equally crucial safety assessments in both language contexts. However, current research has predominantly focused on safety evaluations in English environments, leaving a gap in comprehensive assessments of their safety performance in Chinese contexts. In response to this gap, this study introduces CHiSafetyBench, a Chinese-specific safety evaluation benchmark. This benchmark systematically evaluates the safety of DeepSeek-R1 and DeepSeek-V3 in Chinese contexts, revealing their performance across safety categories. The experimental results quantify the deficiencies of these two models in Chinese contexts, providing key insights for subsequent improvements. It should be noted that, despite our efforts to establish a comprehensive, objective, and authoritative evaluation benchmark, the selection of test samples, characteristics of data distribution, and the setting of evaluation criteria may inevitably introduce certain biases into the evaluation results. We will continuously optimize the evaluation benchmark and periodically update this report to provide more comprehensive and accurate assessment outcomes. Please refer to the latest version of the paper for the most recent evaluation results and conclusions.

Xiang Liu, Zhaoxiang Liu, Huan Hu et al.

While conversational generative AI has shown considerable potential in enhancing decision-making for agricultural professionals, its exploration has predominantly been anchored in text-based interactions. The evolution of multimodal conversational AI, leveraging vast amounts of image-text data from diverse sources, marks a significant stride forward. However, the application of such advanced vision-language models in the agricultural domain, particularly for crop disease diagnosis, remains underexplored. In this work, we present the crop disease domain multimodal (CDDM) dataset, a pioneering resource designed to advance the field of agricultural research through the application of multimodal learning techniques. The dataset comprises 137,000 images of various crop diseases, accompanied by 1 million question-answer pairs that span a broad spectrum of agricultural knowledge, from disease identification to management practices. By integrating visual and textual data, CDDM facilitates the development of sophisticated question-answering systems capable of providing precise, useful advice to farmers and agricultural professionals. We demonstrate the utility of the dataset by finetuning state-of-the-art multimodal models, showcasing significant improvements in crop disease diagnosis. Specifically, we employed a novel finetuning strategy that utilizes low-rank adaptation (LoRA) to finetune the visual encoder, adapter and language model simultaneously. Our contributions include not only the dataset but also a finetuning strategy and a benchmark to stimulate further research in agricultural technology, aiming to bridge the gap between advanced AI techniques and practical agricultural applications. The dataset is available at https: //github.com/UnicomAI/UnicomBenchmark/tree/main/CDDMBench.

Wenjing Zhang, Xuejiao Lei, Zhaoxiang Liu et al.

DeepSeek-R1, renowned for its exceptional reasoning capabilities and open-source strategy, is significantly influencing the global artificial intelligence landscape. However, it exhibits notable safety shortcomings. Recent research conducted by Robust Intelligence, a subsidiary of Cisco, in collaboration with the University of Pennsylvania, revealed that DeepSeek-R1 achieves a 100\% attack success rate when processing harmful prompts. Furthermore, multiple security firms and research institutions have identified critical security vulnerabilities within the model. Although China Unicom has uncovered safety vulnerabilities of R1 in Chinese contexts, the safety capabilities of the remaining distilled models in the R1 series have not yet been comprehensively evaluated. To address this gap, this study utilizes the comprehensive Chinese safety benchmark CHiSafetyBench to conduct an in-depth safety evaluation of the DeepSeek-R1 series distilled models. The objective is to assess the safety capabilities of these models in Chinese contexts both before and after distillation, and to further elucidate the adverse effects of distillation on model safety. Building on these findings, we implement targeted safety enhancements for the entire DeepSeek-R1 model series. Evaluation results indicate that the enhanced models achieve significant improvements in safety while maintaining reasoning capabilities without notable degradation. We open-source the safety-enhanced models at https://github.com/UnicomAI/DeepSeek-R1-Safe to serve as a valuable resource for future research and optimization of DeepSeek models.

Ping Chen, Xingpeng Zhang, Zhaoxiang Liu et al.

In this research, we propose a novel denoising diffusion model based on shortest-path modeling that optimizes residual propagation to enhance both denoising efficiency and quality. Drawing on Denoising Diffusion Implicit Models (DDIM) and insights from graph theory, our model, termed the Shortest Path Diffusion Model (ShortDF), treats the denoising process as a shortest-path problem aimed at minimizing reconstruction error. By optimizing the initial residuals, we improve the efficiency of the reverse diffusion process and the quality of the generated samples. Extensive experiments on multiple standard benchmarks demonstrate that ShortDF significantly reduces diffusion time (or steps) while enhancing the visual fidelity of generated samples compared to prior arts. This work, we suppose, paves the way for interactive diffusion-based applications and establishes a foundation for rapid data generation. Code is available at https://github.com/UnicomAI/ShortDF.

Zihui Wu, Haichang Gao, Ping Wang et al.

Glitch tokens, inputs that trigger unpredictable or anomalous behavior in Large Language Models (LLMs), pose significant challenges to model reliability and safety. Existing detection methods primarily rely on heuristic embedding patterns or statistical anomalies within internal representations, limiting their generalizability across different model architectures and potentially missing anomalies that deviate from observed patterns. We introduce GlitchMiner, an behavior-driven framework designed to identify glitch tokens by maximizing predictive entropy. Leveraging a gradient-guided local search strategy, GlitchMiner efficiently explores the discrete token space without relying on model-specific heuristics or large-batch sampling. Extensive experiments across ten LLMs from five major model families demonstrate that GlitchMiner consistently outperforms existing approaches in detection accuracy and query efficiency, providing a generalizable and scalable solution for effective glitch token discovery. Code is available at [https://github.com/wooozihu/GlitchMiner]

Ping Chen, Zezhou Chen, Xingpeng Zhang et al.

Current 2D-to-3D conversion methods achieve geometric accuracy but are artistically deficient, failing to replicate the immersive and emotionally resonant experience of professional 3D cinema. This is because geometric reconstruction paradigms mistake deliberate artistic intent, such as strategic zero-plane shifts for pop-out effects and local depth sculpting, for data noise or ambiguity. This paper argues for a new paradigm: Artistic Disparity Synthesis, shifting the goal from physically accurate disparity estimation to artistically coherent disparity synthesis. We propose Art3D, a preliminary framework exploring this paradigm. Art3D uses a dual-path architecture to decouple global depth parameters (macro-intent) from local artistic effects (visual brushstrokes) and learns from professional 3D film data via indirect supervision. We also introduce a preliminary evaluation method to quantify cinematic alignment. Experiments show our approach demonstrates potential in replicating key local out-of-screen effects and aligning with the global depth styles of cinematic 3D content, laying the groundwork for a new class of artistically-driven conversion tools.

Kaikai Zhao, Zhaoxiang Liu, Peng Wang et al.

General-domain large multimodal models (LMMs) have achieved significant advances in various image-text tasks. However, their performance in the Intelligent Traffic Surveillance (ITS) domain remains limited due to the absence of dedicated multimodal datasets. To address this gap, we introduce MITS (Multimodal Intelligent Traffic Surveillance), the first large-scale multimodal benchmark dataset specifically designed for ITS. MITS includes 170,400 independently collected real-world ITS images sourced from traffic surveillance cameras, annotated with eight main categories and 24 subcategories of ITS-specific objects and events under diverse environmental conditions. Additionally, through a systematic data generation pipeline, we generate high-quality image captions and 5 million instruction-following visual question-answer pairs, addressing five critical ITS tasks: object and event recognition, object counting, object localization, background analysis, and event reasoning. To demonstrate MITS's effectiveness, we fine-tune mainstream LMMs on this dataset, enabling the development of ITS-specific applications. Experimental results show that MITS significantly improves LMM performance in ITS applications, increasing LLaVA-1.5's performance from 0.494 to 0.905 (+83.2%), LLaVA-1.6's from 0.678 to 0.921 (+35.8%), Qwen2-VL's from 0.584 to 0.926 (+58.6%), and Qwen2.5-VL's from 0.732 to 0.930 (+27.0%). We release the dataset, code, and models as open-source, providing high-value resources to advance both ITS and LMM research.

Enbo Zhao, Yi Shen, Shuming Shi et al.

Recently, there is a high demand for deploying DeepSeek-R1 and V3 locally, possibly because the official service often suffers from being busy and some organizations have data privacy concerns. While single-machine deployment offers infrastructure simplicity, the models' 671B FP8 parameter configuration exceeds the practical memory limits of a standard 8-GPU machine. Quantization is a widely used technique that helps reduce model memory consumption. However, it is unclear what the performance of DeepSeek-R1 and V3 will be after being quantized. This technical report presents the first quantitative evaluation of multi-bitwidth quantization across the complete DeepSeek model spectrum. Key findings reveal that 4-bit quantization maintains little performance degradation versus FP8 while enabling single-machine deployment on standard NVIDIA GPU devices. We further propose DQ3_K_M, a dynamic 3-bit quantization method that significantly outperforms traditional Q3_K_M variant on various benchmarks, which is also comparable with 4-bit quantization (Q4_K_M) approach in most tasks. Moreover, DQ3_K_M supports single-machine deployment configurations for both NVIDIA H100/A100 and Huawei 910B. Our implementation of DQ3\_K\_M is released at https://github.com/UnicomAI/DeepSeek-Eval, containing optimized 3-bit quantized variants of both DeepSeek-R1 and DeepSeek-V3.

Wenjing Zhang, Xuejiao Lei, Zhaoxiang Liu et al.

With the profound development of large language models(LLMs), their safety concerns have garnered increasing attention. However, there is a scarcity of Chinese safety benchmarks for LLMs, and the existing safety taxonomies are inadequate, lacking comprehensive safety detection capabilities in authentic Chinese scenarios. In this work, we introduce CHiSafetyBench, a dedicated safety benchmark for evaluating LLMs' capabilities in identifying risky content and refusing answering risky questions in Chinese contexts. CHiSafetyBench incorporates a dataset that covers a hierarchical Chinese safety taxonomy consisting of 5 risk areas and 31 categories. This dataset comprises two types of tasks: multiple-choice questions and question-answering, evaluating LLMs from the perspectives of risk content identification and the ability to refuse answering risky questions respectively. Utilizing this benchmark, we validate the feasibility of automatic evaluation as a substitute for human evaluation and conduct comprehensive automatic safety assessments on mainstream Chinese LLMs. Our experiments reveal the varying performance of different models across various safety domains, indicating that all models possess considerable potential for improvement in Chinese safety capabilities. Our dataset is publicly available at https://github.com/UnicomAI/UnicomBenchmark/tree/main/CHiSafetyBench.

Shiguo Lian, Kaikai Zhao, Xinhui Liu et al.

General large language models enhanced with supervised fine-tuning and reinforcement learning from human feedback are increasingly popular in academia and industry as they generalize foundation models to various practical tasks in a prompt manner. To assist users in selecting the best model in practical application scenarios, i.e., choosing the model that meets the application requirements while minimizing cost, we introduce A-Eval, an application-driven LLMs evaluation benchmark for general large language models. First, we categorize evaluation tasks into five main categories and 27 sub-categories from a practical application perspective. Next, we construct a dataset comprising 678 question-and-answer pairs through a process of collecting, annotating, and reviewing. Then, we design an objective and effective evaluation method and evaluate a series of LLMs of different scales on A-Eval. Finally, we reveal interesting laws regarding model scale and task difficulty level and propose a feasible method for selecting the best model. Through A-Eval, we provide clear empirical and engineer guidance for selecting the best model, reducing barriers to selecting and using LLMs and promoting their application and development. Our benchmark is publicly available at https://github.com/UnicomAI/DataSet/tree/main/TestData/GeneralAbility.

Kohou Wang, Xiang Liu, Zhaoxiang Liu et al.

Multimodal Large Language Models (MLLMs) have made significant progress in bridging the gap between visual and language modalities. However, hallucinations in MLLMs, where the generated text does not align with image content, continue to be a major challenge. Existing methods for addressing hallucinations often rely on instruction-tuning, which requires retraining the model with specific data, which increases the cost of utilizing MLLMs further. In this paper, we introduce a novel training-free method, named Piculet, for enhancing the input representation of MLLMs. Piculet leverages multiple specialized models to extract descriptions of visual information from the input image and combine these descriptions with the original image and query as input to the MLLM. We evaluate our method both quantitively and qualitatively, and the results demonstrate that Piculet greatly decreases hallucinations of MLLMs. Our method can be easily extended to different MLLMs while being universal.

Shiguo Lian, Kai Wang, Zhaoxiang Liu et al.

Large model inference optimization serves as a key foundation for supporting the scalable, low-cost, and highly stable operation of large model services. Centered on token-oriented inference optimization technology, this paper proposes for the first time a four-layer technical architecture consisting of Multi-model Fusion, Model Optimization, Compute-Model Fusion, and Compute-Network-Model Fusion. It systematically reviews the key technologies and current industry status across these four levels and analyzes the application value of related technologies in real-world business scenarios. This paper provides a practical technical path for reducing token production costs, improving token service efficiency, ensuring the stability of token supply, and driving the transition of large model services from being merely callable to being operable.

Kaikai Zhao, Zhaoxiang Liu, Xuejiao Lei et al.

DeepSeek-R1, known for its low training cost and exceptional reasoning capabilities, has achieved state-of-the-art performance on various benchmarks. However, detailed evaluations for DeepSeek Series models from the perspective of real-world applications are lacking, making it challenging for users to select the most suitable DeepSeek models for their specific needs. To address this gap, we presents the first comprehensive evaluation of the DeepSeek and its related models (including DeepSeek-V3, DeepSeek-R1, DeepSeek-R1-Distill-Qwen series, DeepSeek-R1-Distill-Llama series, their corresponding 4-bit quantized models, and the reasoning model QwQ-32B) using our enhanced A-Eval benchmark, A-Eval-2.0. Our systematic analysis reveals several key insights: (1) Given identical model architectures and training data, larger parameter models demonstrate superior performance, aligning with the scaling law. However, smaller models may achieve enhanced capabilities when employing optimized training strategies and higher-quality data; (2) Reasoning-enhanced model show significant performance gains in logical reasoning tasks but may underperform in text understanding and generation tasks; (3) As the data difficulty increases, distillation or reasoning enhancements yield higher performance gains for the models. Interestingly, reasoning enhancements can even have a negative impact on simpler problems; (4) Quantization impacts different capabilities unevenly, with significant drop on logical reasoning and minimal impact on text generation. Based on these results and findings, we design an model selection handbook enabling users to select the most cost-effective models without efforts.

Liming Han, Zhaoxiang Liu, Shiguo Lian

Image matching is still challenging in such scenes with large viewpoints or illumination changes or with low textures. In this paper, we propose a Transformer-based pseudo 3D image matching method. It upgrades the 2D features extracted from the source image to 3D features with the help of a reference image and matches to the 2D features extracted from the destination image by the coarse-to-fine 3D matching. Our key discovery is that by introducing the reference image, the source image's fine points are screened and furtherly their feature descriptors are enriched from 2D to 3D, which improves the match performance with the destination image. Experimental results on multiple datasets show that the proposed method achieves the state-of-the-art on the tasks of homography estimation, pose estimation and visual localization especially in challenging scenes.

Kohou Wang, ZhaoXiang Liu, Lin Bai et al.

It is crucial that robots' performance can be improved after deployment, as they are inherently likely to encounter novel scenarios never seen before. This paper presents an innovative solution: an interactive learning-based robot system powered by a Multi-modal Large Language Model(MLLM). A key feature of our system is its ability to learn from natural dialogues with non-expert users. We also propose chain of question to clarify the exact intent of the question before providing an answer and dual-modality retrieval modules to leverage these interaction events to avoid repeating same mistakes, ensuring a seamless user experience before model updates, which is in contrast to current mainstream MLLM-based robotic systems. Our system marks a novel approach in robotics by integrating interactive learning, paving the way for superior adaptability and performance in diverse environments. We demonstrate the effectiveness and improvement of our method through experiments, both quantitively and qualitatively.

Zezhou Chen, Zhaoxiang Liu, Kai Wang et al.

It is a challenging task for visually impaired people to perceive their surrounding environment due to the complexity of the natural scenes. Their personal and social activities are thus highly limited. This paper introduces a Large Vision-Language Model(LVLM) based environment perception system which helps them to better understand the surrounding environment, by capturing the current scene they face with a wearable device, and then letting them retrieve the analysis results through the device. The visually impaired people could acquire a global description of the scene by long pressing the screen to activate the LVLM output, retrieve the categories of the objects in the scene resulting from a segmentation model by tapping or swiping the screen, and get a detailed description of the objects they are interested in by double-tapping the screen. To help visually impaired people more accurately perceive the world, this paper proposes incorporating the segmentation result of the RGB image as external knowledge into the input of LVLM to reduce the LVLM's hallucination. Technical experiments on POPE, MME and LLaVA-QA90 show that the system could provide a more accurate description of the scene compared to Qwen-VL-Chat, exploratory experiments show that the system helps visually impaired people to perceive the surrounding environment effectively.

Wenjing Zhang, Siqi Xiao, Xuejiao Lei et al.

The rapid growth of large language models(LLMs) has emerged as a prominent trend in the field of artificial intelligence. However, current state-of-the-art LLMs are predominantly based on English. They encounter limitations when directly applied to tasks in specific cultural domains, due to deficiencies in domain-specific knowledge and misunderstandings caused by differences in cultural values. To address this challenge, our paper proposes a rapid adaptation method for large models in specific cultural contexts, which leverages instruction-tuning based on specific cultural knowledge and safety values data. Taking Chinese as the specific cultural context and utilizing the LLaMA3-8B as the experimental English LLM, the evaluation results demonstrate that the adapted LLM significantly enhances its capabilities in domain-specific knowledge and adaptability to safety values, while maintaining its original expertise advantages.

Yimin Lin, Jianfeng Huang, Shiguo Lian

We propose a novel visual localization network when outside environment has changed such as different illumination, weather and season. The visual localization network is composed of a feature extraction network and pose regression network. The feature extraction network is made up of an encoder network based on the Generative Adversarial Network CycleGAN, which can capture intrinsic appearance-invariant feature maps from unpaired samples of different weathers and seasons. With such an invariant feature, we use a 6-DoF pose regression network to tackle long-term visual localization in the presence of outdoor illumination, weather and season changes. A variety of challenging datasets for place recognition and localization are used to prove our visual localization network, and the results show that our method outperforms state-of-the-art methods in the scenarios with various environment changes.

Zipeng Wang, Zhaoxiang Liu, Jianfeng Huang et al.

We present a novel framework to generate images of different age while preserving identity information, which is known as face aging. Different from most recent popular face aging networks utilizing Generative Adversarial Networks(GANs) application, our approach do not simply transfer a young face to an old one. Instead, we employ the edge map as intermediate representations, firstly edge maps of young faces are extracted, a CycleGAN-based network is adopted to transfer them into edge maps of old faces, then another pix2pixHD-based network is adopted to transfer the synthesized edge maps, concatenated with identity information, into old faces. In this way, our method can generate more realistic transfered images, simultaneously ensuring that face identity information be preserved well, and the apparent age of the generated image be accurately appropriate. Experimental results demonstrate that our method is feasible for face age translation.

Minjie Hua, Yibing Nan, Shiguo Lian

This paper presents a novel obstacle avoidance system for road robots equipped with RGB-D sensor that captures scenes of its way forward. The purpose of the system is to have road robots move around autonomously and constantly without any collision even with small obstacles, which are often missed by existing solutions. For each input RGB-D image, the system uses a new two-stage semantic segmentation network followed by the morphological processing to generate the accurate semantic map containing road and obstacles. Based on the map, the local path planning is applied to avoid possible collision. Additionally, optical flow supervision and motion blurring augmented training scheme is applied to improve temporal consistency between adjacent frames and overcome the disturbance caused by camera shake. Various experiments are conducted to show that the proposed architecture obtains high performance both in indoor and outdoor scenarios.

Zezhou Chen, Zhaoxiang Liu, Huan Hu et al.

To improve the experiences of face-to-face conversation with avatar, this paper presents a novel conversation system. It is composed of two sequence-to-sequence models respectively for listening and speaking and a Generative Adversarial Network (GAN) based realistic avatar synthesizer. The models exploit the facial action and head pose to learn natural human reactions. Based on the models' output, the synthesizer uses the Pixel2Pixel model to generate realistic facial images. To show the improvement of our system, we use a 3D model based avatar driving scheme as a reference. We train and evaluate our neural networks with the data from ESPN shows. Experimental results show that our conversation system can generate natural facial reactions and realistic facial images.

Zipeng Wang, Zhaoxiang Liu, Zezhou Chen et al.

This paper presents a novel framework to generate realistic face video of an anchor, who is reading certain news. This task is also known as Virtual Anchor. Given some paragraphs of words, we first utilize a pretrained Word2Vec model to embed each word into a vector; then we utilize a Seq2Seq-based model to translate these word embeddings into action units and head poses of the target anchor; these action units and head poses will be concatenated with facial landmarks as well as the former $n$ synthesized frames, and the concatenation serves as input of a Pix2PixHD-based model to synthesize realistic facial images for the virtual anchor. The experimental results demonstrate our framework is feasible for the synthesis of virtual anchor.

Zhaoxiang Liu, Huan Hu, Zipeng Wang et al.

This paper presents a generative adversarial learning-based human upper body video synthesis approach to generate an upper body video of target person that is consistent with the body motion, face expression, and pose of the person in source video. We use upper body keypoints, facial action units and poses as intermediate representations between source video and target video. Instead of directly transferring the source video to the target video, we firstly map the source person's facial action units and poses into the target person's facial landmarks, then combine the normalized upper body keypoints and generated facial landmarks with spatio-temporal smoothing to generate the corresponding target video's image. Experimental results demonstrated the effectiveness of our method.

Yimin Lin, Kai Wang, Wanxin Yi et al.

In this paper, we propose a deep learning based assistive system to improve the environment perception experience of visually impaired (VI). The system is composed of a wearable terminal equipped with an RGBD camera and an earphone, a powerful processor mainly for deep learning inferences and a smart phone for touch-based interaction. A data-driven learning approach is proposed to predict safe and reliable walkable instructions using RGBD data and the established semantic map. This map is also used to help VI understand their 3D surrounding objects and layout through well-designed touchscreen interactions. The quantitative and qualitative experimental results show that our learning based obstacle avoidance approach achieves excellent results in both indoor and outdoor datasets with low-lying obstacles. Meanwhile, user studies have also been carried out in various scenarios and showed the improvement of VI's environment perception experience with our system.

Minjie Hua, Yibing Nan, Shiguo Lian

This paper presents a novel approach for predicting the falls of people in advance from monocular video. First, all persons in the observed frames are detected and tracked with the coordinates of their body keypoints being extracted meanwhile. A keypoints vectorization method is exploited to eliminate irrelevant information in the initial coordinate representation. Then, the observed keypoint sequence of each person is input to the pose prediction module adapted from sequence-to-sequence(seq2seq) architecture to predict the future keypoint sequence. Finally, the predicted pose is analyzed by the falls classifier to judge whether the person will fall down in the future. The pose prediction module and falls classifier are trained separately and tuned jointly using Le2i dataset, which contains 191 videos of various normal daily activities as well as falls performed by several actors. The contrast experiments with mainstream raw RGB-based models show the accuracy improvement of utilizing body keypoints in falls classification. Moreover, the precognition of falls is proved effective by comparisons between models that with and without the pose prediction module.

Liming Han, Yimin Lin, Guoguang Du et al.

This paper presents an self-supervised deep learning network for monocular visual inertial odometry (named DeepVIO). DeepVIO provides absolute trajectory estimation by directly merging 2D optical flow feature (OFF) and Inertial Measurement Unit (IMU) data. Specifically, it firstly estimates the depth and dense 3D point cloud of each scene by using stereo sequences, and then obtains 3D geometric constraints including 3D optical flow and 6-DoF pose as supervisory signals. Note that such 3D optical flow shows robustness and accuracy to dynamic objects and textureless environments. In DeepVIO training, 2D optical flow network is constrained by the projection of its corresponding 3D optical flow, and LSTM-style IMU preintegration network and the fusion network are learned by minimizing the loss functions from ego-motion constraints. Furthermore, we employ an IMU status update scheme to improve IMU pose estimation through updating the additional gyroscope and accelerometer bias. The experimental results on KITTI and EuRoC datasets show that DeepVIO outperforms state-of-the-art learning based methods in terms of accuracy and data adaptability. Compared to the traditional methods, DeepVIO reduces the impacts of inaccurate Camera-IMU calibrations, unsynchronized and missing data.

Zhaoxiang Liu, Huan Hu, Jinqiang Bai et al.

This paper aims to learn a compact representation of a video for video face recognition task. We make the following contributions: first, we propose a meta attention-based aggregation scheme which adaptively and fine-grained weighs the feature along each feature dimension among all frames to form a compact and discriminative representation. It makes the best to exploit the valuable or discriminative part of each frame to promote the performance of face recognition, without discarding or despising low quality frames as usual methods do. Second, we build a feature aggregation network comprised of a feature embedding module and a feature aggregation module. The embedding module is a convolutional neural network used to extract a feature vector from a face image, while the aggregation module consists of cascaded two meta attention blocks which adaptively aggregate the feature vectors into a single fixed-length representation. The network can deal with arbitrary number of frames, and is insensitive to frame order. Third, we validate the performance of proposed aggregation scheme. Experiments on publicly available datasets, such as YouTube face dataset and IJB-A dataset, show the effectiveness of our method, and it achieves competitive performances on both the verification and identification protocols.

Minjie Hua, Fuyuan Shi, Yibing Nan et al.

This paper presents a novel system that enables intelligent robots to exhibit realistic body gestures while communicating with humans. The proposed system consists of a listening model and a speaking model used in corresponding conversational phases. Both models are adapted from the sequence-to-sequence (seq2seq) architecture to synthesize body gestures represented by the movements of twelve upper-body keypoints. All the extracted 2D keypoints are firstly 3D-transformed, then rotated and normalized to discard irrelevant information. Substantial videos of human conversations from Youtube are collected and preprocessed to train the listening and speaking models separately, after which the two models are evaluated using metrics of mean squared error (MSE) and cosine similarity on the test dataset. The tuned system is implemented to drive a virtual avatar as well as Pepper, a physical humanoid robot, to demonstrate the improvement on conversational interaction abilities of our method in practice.

Zhaoxiang Liu, Zezhou Chen, Jinqiang Bai et al.

Facial pose estimation has gained a lot of attentions in many practical applications, such as human-robot interaction, gaze estimation and driver monitoring. Meanwhile, end-to-end deep learning-based facial pose estimation is becoming more and more popular. However, facial pose estimation suffers from a key challenge: the lack of sufficient training data for many poses, especially for large poses. Inspired by the observation that the faces under close poses look similar, we reformulate the facial pose estimation as a label distribution learning problem, considering each face image as an example associated with a Gaussian label distribution rather than a single label, and construct a convolutional neural network which is trained with a multi-loss function on AFLW dataset and 300W-LP dataset to predict the facial poses directly from color image. Extensive experiments are conducted on several popular benchmarks, including AFLW2000, BIWI, AFLW and AFW, where our approach shows a significant advantage over other state-of-the-art methods.

Jinqiang Bai, Zhaoxiang Liu, Yimin Lin et al.

This paper presents a wearable assistive device with the shape of a pair of eyeglasses that allows visually impaired people to navigate safely and quickly in unfamiliar environment, as well as perceive the complicated environment to automatically make decisions on the direction to move. The device uses a consumer Red, Green, Blue and Depth (RGB-D) camera and an Inertial Measurement Unit (IMU) to detect obstacles. As the device leverages the ground height continuity among adjacent image frames, it is able to segment the ground from obstacles accurately and rapidly. Based on the detected ground, the optimal walkable direction is computed and the user is then informed via converted beep sound. Moreover, by utilizing deep learning techniques, the device can semantically categorize the detected obstacles to improve the users' perception of surroundings. It combines a Convolutional Neural Network (CNN) deployed on a smartphone with a depth-image-based object detection to decide what the object type is and where the object is located, and then notifies the user of such information via speech. We evaluated the device's performance with different experiments in which 20 visually impaired people were asked to wear the device and move in an office, and found that they were able to avoid obstacle collisions and find the way in complicated scenarios.

Jinqiang Bai, Shiguo Lian, Zhaoxiang Liu et al.

This paper presents a novel garbage pickup robot which operates on the grass. The robot is able to detect the garbage accurately and autonomously by using a deep neural network for garbage recognition. In addition, with the ground segmentation using a deep neural network, a novel navigation strategy is proposed to guide the robot to move around. With the garbage recognition and automatic navigation functions, the robot can clean garbage on the ground in places like parks or schools efficiently and autonomously. Experimental results show that the garbage recognition accuracy can reach as high as 95%, and even without path planning, the navigation strategy can reach almost the same cleaning efficiency with traditional methods. Thus, the proposed robot can serve as a good assistance to relieve dustman's physical labor on garbage cleaning tasks.

Jinqiang Bai, Shiguo Lian, Zhaoxiang Liu et al.

To help the blind people walk to the destination efficiently and safely in indoor environment, a novel wearable navigation device is presented in this paper. The locating, way-finding, route following and obstacle avoiding modules are the essential components in a navigation system, while it remains a challenging task to consider obstacle avoiding during route following, as the indoor environment is complex, changeable and possibly with dynamic objects. To address this issue, we propose a novel scheme which utilizes a dynamic sub-goal selecting strategy to guide the users to the destination and help them bypass obstacles at the same time. This scheme serves as the key component of a complete navigation system deployed on a pair of wearable optical see-through glasses for the ease of use of blind people's daily walks. The proposed navigation device has been tested on a collection of individuals and proved to be effective on indoor navigation tasks. The sensors embedded are of low cost, small volume and easy integration, making it possible for the glasses to be widely used as a wearable consumer device.

Kai Wang, Fuyuan Shi, Wenqi Wang et al.

This paper presents an improved scheme for the generation and adaption of synthetic images for the training of deep Convolutional Neural Networks(CNNs) to perform the object detection task in smart vending machines. While generating synthetic data has proved to be effective for complementing the training data in supervised learning methods, challenges still exist for generating virtual images which are similar to those of the complex real scenes and minimizing redundant training data. To solve these problems, we consider the simulation of cluttered objects placed in a virtual scene and the wide-angle camera with distortions used to capture the whole scene in the data generation process, and post-processed the generated images with a elaborately-designed generative network to make them more similar to the real images. Various experiments have been conducted to prove the efficiency of using the generated virtual images to enhance the detection precision on existing datasets with limited real training data and the generalization ability of applying the trained network to datasets collected in new environment.

Yimin Lin, Zhaoxiang Liu, Jianfeng Huang et al.

Although a wide variety of deep neural networks for robust Visual Odometry (VO) can be found in the literature, they are still unable to solve the drift problem in long-term robot navigation. Thus, this paper aims to propose novel deep end-to-end networks for long-term 6-DoF VO task. It mainly fuses relative and global networks based on Recurrent Convolutional Neural Networks (RCNNs) to improve the monocular localization accuracy. Indeed, the relative sub-networks are implemented to smooth the VO trajectory, while global subnetworks are designed to avoid drift problem. All the parameters are jointly optimized using Cross Transformation Constraints (CTC), which represents temporal geometric consistency of the consecutive frames, and Mean Square Error (MSE) between the predicted pose and ground truth. The experimental results on both indoor and outdoor datasets show that our method outperforms other state-of-the-art learning-based VO methods in terms of pose accuracy.