Wenjie Yang

Wenjie Yang, Yiyi Chen, Yan Li et al.

Live commerce is the act of selling products online through live streaming. The customer's diverse demands for online products introduce more challenges to Livestreaming Product Recognition. Previous works have primarily focused on fashion clothing data or utilize single-modal input, which does not reflect the real-world scenario where multimodal data from various categories are present. In this paper, we present LPR4M, a large-scale multimodal dataset that covers 34 categories, comprises 3 modalities (image, video, and text), and is 50x larger than the largest publicly available dataset. LPR4M contains diverse videos and noise modality pairs while exhibiting a long-tailed distribution, resembling real-world problems. Moreover, a cRoss-vIew semantiC alignmEnt (RICE) model is proposed to learn discriminative instance features from the image and video views of the products. This is achieved through instance-level contrastive learning and cross-view patch-level feature propagation. A novel Patch Feature Reconstruction loss is proposed to penalize the semantic misalignment between cross-view patches. Extensive experiments demonstrate the effectiveness of RICE and provide insights into the importance of dataset diversity and expressivity. The dataset and code are available at https://github.com/adxcreative/RICE

Xuehan Bai, Yan Li, Yanhua Cheng et al.

The proliferation of short video and live-streaming platforms has revolutionized how consumers engage in online shopping. Instead of browsing product pages, consumers are now turning to rich-content e-commerce, where they can purchase products through dynamic and interactive media like short videos and live streams. This emerging form of online shopping has introduced technical challenges, as products may be presented differently across various media domains. Therefore, a unified product representation is essential for achieving cross-domain product recognition to ensure an optimal user search experience and effective product recommendations. Despite the urgent industrial need for a unified cross-domain product representation, previous studies have predominantly focused only on product pages without taking into account short videos and live streams. To fill the gap in the rich-content e-commerce area, in this paper, we introduce a large-scale cRoss-dOmain Product Ecognition dataset, called ROPE. ROPE covers a wide range of product categories and contains over 180,000 products, corresponding to millions of short videos and live streams. It is the first dataset to cover product pages, short videos, and live streams simultaneously, providing the basis for establishing a unified product representation across different media domains. Furthermore, we propose a Cross-dOmain Product rEpresentation framework, namely COPE, which unifies product representations in different domains through multimodal learning including text and vision. Extensive experiments on downstream tasks demonstrate the effectiveness of COPE in learning a joint feature space for all product domains.

Yuyu Guo, Wenjie Yang, Siyuan Yang et al.

To fulfill user instructions, autonomous web agents must contend with the inherent complexity and volatile nature of real-world websites. Conventional paradigms predominantly rely on Supervised Fine-Tuning (SFT) or Offline Reinforcement Learning (RL) using static datasets. However, these methods suffer from severe distributional shifts, as offline trajectories fail to capture the stochastic state transitions and real-time feedback of unconstrained wide web environments. In this paper, we propose a robust Online Reinforcement Learning WebAgent, designed to optimize its policy through direct, iterative interactions with unconstrained wide websites. Our approach comprises three core innovations: 1) Hierarchical Multi-Task Fine-tuning: We curate a comprehensive mixture of datasets categorized by functional primitives -- Planning, Acting, and Grounding -- establishing a Vision-Language Model (VLM) with strong instruction-following capabilities for Web GUI tasks. 2) Online Agentic RL in the Wild: We develop an online interaction environment and fine-tune the VLM using a specialized RL pipeline. We introduce a Hybrid Reward Mechanism that combines a ground-truth-agnostic WebJudge for holistic outcome assessment with a Rule-based Decision Tree (RDT) for progress reward. This system effectively mitigates the credit assignment challenge in long-horizon navigation. Notably, our RL-enhanced model achieves a 38.1\% success rate (pass@5) on WebArena, outperforming all existing monolithic baselines. 3) Operator Agent: We introduce a modular agentic framework, namely \textbf{OpAgent}, orchestrating a Planner, Grounder, Reflector, and Summarizer. This synergy enables robust error recovery and self-correction, elevating the agent's performance to a new State-of-the-Art (SOTA) success rate of \textbf{71.6\%}.

Codefuse, Ling Team, Wenting Cai et al.

Recent advancements in code large language models (LLMs) have demonstrated remarkable capabilities in code generation and understanding. It is still challenging to build a code LLM with comprehensive performance yet ultimate efficiency. Many attempts have been released in the open source community to break the trade-off between performance and efficiency, such as the Qwen Coder series and the DeepSeek Coder series. This paper introduces yet another attempt in this area, namely Ling-Coder-Lite. We leverage the efficient Mixture-of-Experts (MoE) architecture along with a set of high-quality data curation methods (especially those based on program analytics) to build an efficient yet powerful code LLM. Ling-Coder-Lite exhibits on-par performance on 12 representative coding benchmarks compared to state-of-the-art models of similar size, such as Qwen2.5-Coder-7B and DeepSeek-Coder-V2-Lite, while offering competitive latency and throughput. In practice, we achieve a 50\% reduction in deployment resources compared to the similar-sized dense model without performance loss. To facilitate further research and development in this area, we open-source our models as well as a substantial portion of high-quality data for the annealing and post-training stages. The models and data can be accessed at~\url{https://huggingface.co/inclusionAI/Ling-Coder-lite}.

Wenjie Yang, Shengzhong Zhang, Jiaxing Guo et al.

Graph recommender (GR) is a type of graph neural network (GNNs) encoder that is customized for extracting information from the user-item interaction graph. Due to its strong performance on the recommendation task, GR has gained significant attention recently. Graph contrastive learning (GCL) is also a popular research direction that aims to learn, often unsupervised, GNNs with certain contrastive objectives. As a general graph representation learning method, GCLs have been widely adopted with the supervised recommendation loss for joint training of GRs. Despite the intersection of GR and GCL research, theoretical understanding of the relationship between the two fields is surprisingly sparse. This vacancy inevitably leads to inefficient scientific research. In this paper, we aim to bridge the gap between the field of GR and GCL from the perspective of encoders and loss functions. With mild assumptions, we theoretically show an astonishing fact that graph recommender is equivalent to a commonly-used single-view graph contrastive model. Specifically, we find that (1) the classic encoder in GR is essentially a linear graph convolutional network with one-hot inputs, and (2) the loss function in GR is well bounded by a single-view GCL loss with certain hyperparameters. The first observation enables us to explain crucial designs of GR models, e.g., the removal of self-loop and nonlinearity. And the second finding can easily prompt many cross-field research directions. We empirically show a remarkable result that the recommendation loss and the GCL loss can be used interchangeably. The fact that we can train GR models solely with the GCL loss is particularly insightful, since before this work, GCLs were typically viewed as unsupervised methods that need fine-tuning. We also discuss some potential future works inspired by our theory.

Wenjie Yang, Hang Yu, Yuyu Guo et al.

In this work, we address the critical yet underexplored challenge of symmetric multimodal-to-multimodal (MM2MM) retrieval, where queries and contexts are interchangeable. Existing universal multimodal retrieval works struggle with this task, as they are constrained by the labeled asymmetric datasets used. We produce SOLAR (Self-supervised jOint LeArning for symmetric multimodal Retrieval), a novel two-stage self-supervised framework that leverages readily available unlabeled web-scale image-text pairs. Based on the observation that both semantic alignment and discrepancies exist between two modalities, in the first stage, we learn the intersection mask of image-text pair, allowing us to align intersection while preserving semantic of difference. In the second stage, the learned mask is further utilized to construct positive and hardnegative samples via masking different parts of image/text, which enable us to conduct self-supervised multimodal embedding learning. Complementing this framework, we present a new benchmark featuring high-quality human-verified positive and hard-negative pairs to evaluate symmetric MM2MM retrieval under realistic conditions, as well as the corresponding pipeline. Extensive experiments against ten SOTA methods show SOLAR surpasses the strongest supervised VLM by 7.08 points on this benchmark, with over 50x fewer model parameters and a 5x smaller embedding dimension. Code and benchmark will be available soon.

Wenjie Yang, Zengfeng Huang

Visual pointing, which aims to localize a target by predicting its coordinates on an image, has emerged as an important problem in the realm of vision-language models (VLMs). Despite its broad applicability, recent benchmarks show that current VLMs still fall far behind human performance on this task. A key limitation is that VLMs are typically required to complete the pointing task in a single step, akin to asking humans to point at an object without seeing their own fingers. To address this issue, we propose a simple yet effective self-refining procedure: Point, Visualize, then Refine (Poivre). This procedure enables a VLM to first mark its estimated point, then iteratively refine the coordinates if necessary. Inspired by advances of reasoning models in the natural language domain, we employ reinforcement learning (RL) to incentivize this self-refining ability. For the RL training, we design a neat process reward that is not only empirically effective but also grounded in appealing properties. Our trained model, Poivre-7B, sets a new state of the art on Point-Bench, outperforming both proprietary models such as Gemini-2.5-Pro and large open-source models such as Molmo-72B by over 3%. To support future research, we release our training and inference code, dataset, and the Poivre-7B checkpoint.

Wenjie Yang, Mao Zheng, Mingyang Song et al.

Large language models (LLMs) have recently demonstrated remarkable capabilities in machine translation (MT). However, most advanced MT-specific LLMs heavily rely on external supervision signals during training, such as human-annotated reference data or trained reward models (RMs), which are often expensive to obtain and challenging to scale. To overcome this limitation, we propose a Simple Self-Rewarding (SSR) Reinforcement Learning (RL) framework for MT that is reference-free, fully online, and relies solely on self-judging rewards. Training with SSR using 13K monolingual examples and Qwen-2.5-7B as the backbone, our model SSR-Zero-7B outperforms existing MT-specific LLMs, e.g., TowerInstruct-13B and GemmaX-28-9B, as well as larger general LLMs like Qwen2.5-32B-Instruct in English $\leftrightarrow$ Chinese translation tasks from WMT23, WMT24, and Flores200 benchmarks. Furthermore, by augmenting SSR with external supervision from COMET, our strongest model, SSR-X-Zero-7B, achieves state-of-the-art performance in English $\leftrightarrow$ Chinese translation, surpassing all existing open-source models under 72B parameters and even outperforming closed-source models, e.g., GPT-4o and Gemini 1.5 Pro. Our analysis highlights the effectiveness of the self-rewarding mechanism compared to the external LLM-as-a-judge approach in MT and demonstrates its complementary benefits when combined with trained RMs. Our findings provide valuable insight into the potential of self-improving RL methods. We have publicly released our code, data and models.

Yuxi Li, Ning Xu, Wenjie Yang et al.

Modern video object segmentation (VOS) algorithms have achieved remarkably high performance in a sequential processing order, while most of currently prevailing pipelines still show some obvious inadequacy like accumulative error, unknown robustness or lack of proper interpretation tools. In this paper, we place the semi-supervised video object segmentation problem into a cyclic workflow and find the defects above can be collectively addressed via the inherent cyclic property of semi-supervised VOS systems. Firstly, a cyclic mechanism incorporated to the standard sequential flow can produce more consistent representations for pixel-wise correspondance. Relying on the accurate reference mask in the starting frame, we show that the error propagation problem can be mitigated. Next, a simple gradient correction module, which naturally extends the offline cyclic pipeline to an online manner, can highlight the high-frequent and detailed part of results to further improve the segmentation quality while keeping feasible computation cost. Meanwhile such correction can protect the network from severe performance degration resulted from interference signals. Finally we develop cycle effective receptive field (cycle-ERF) based on gradient correction process to provide a new perspective into analyzing object-specific regions of interests. We conduct comprehensive comparison and detailed analysis on challenging benchmarks of DAVIS16, DAVIS17 and Youtube-VOS, demonstrating that the cyclic mechanism is helpful to enhance segmentation quality, improve the robustness of VOS systems, and further provide qualitative comparison and interpretation on how different VOS algorithms work. The code of this project can be found at https://github.com/lyxok1/STM-Training

Houjing Huang, Wenjie Yang, Xiaotang Chen et al.

Person re-identification (ReID) has achieved significant improvement under the single-domain setting. However, directly exploiting a model to new domains is always faced with huge performance drop, and adapting the model to new domains without target-domain identity labels is still challenging. In this paper, we address cross-domain ReID and make contributions for both model generalization and adaptation. First, we propose Part Aligned Pooling (PAP) that brings significant improvement for cross-domain testing. Second, we design a Part Segmentation (PS) constraint over ReID feature to enhance alignment and improve model generalization. Finally, we show that applying our PS constraint to unlabeled target domain images serves as effective domain adaptation. We conduct extensive experiments between three large datasets, Market1501, CUHK03 and DukeMTMC-reID. Our model achieves state-of-the-art performance under both source-domain and cross-domain settings. For completeness, we also demonstrate the complementarity of our model to existing domain adaptation methods. The code is available at https://github.com/huanghoujing/EANet.

Zicheng Lyu, Wenjie Yang, Shengzhong Zhang et al.

Large language models are increasingly capable at closed-world mathematical reasoning, but research assistance also requires source-grounded use of the literature. When a proof reaches a non-trivial step, a useful assistant should determine whether the needed tool (e.g., a lemma) already exists, identify a suitable scholarly source, and verify that its assumptions align with the current proof context. To rigorously evaluate such capabilities, we introduce Re$^2$Math, a benchmark for tool-grounded retrieval from partial mathematical proofs. Each instance is built from a candidate instrumental citation in the proof of a main theorem, with hierarchical context and an optional leakage-controlled anchor hint. We also make the task source-grounded yet citation-agnostic in that any admissible theorem sufficient for the proof transition is accepted. Evaluation uses a release-frozen retrieval artifact, ensuring reproducibility, while the benchmark itself supports automatic, continual expansion with newly constructed instances. On the current benchmark test set, the best fixed-judge ToolAcc reaches 7.0%, despite substantially higher rates of source grounding, indicating that current systems often retrieve valid statements but fail to establish their applicability to the local proof step. By decoupling citation recall, grounding, and proof-gap sufficiency, Re$^2$Math transforms literature-grounded mathematical tool use into a controlled diagnostic task.

Mingyang Song, Mao Zheng, Zheng Li et al.

Improving training efficiency continues to be one of the primary challenges in large-scale Reinforcement Learning (RL). In this paper, we investigate how context length and the complexity of training data influence the RL scaling training process of R1-distilled reasoning models, e.g., DeepSeek-R1-Distill-Qwen-1.5B. Our experimental results reveal that: (1) simply controlling the context length and curating the training data based on the input prompt length can effectively improve the training efficiency of RL scaling, achieving better performance with more concise CoT; (2) properly scaling the context length helps mitigate entropy collapse; and (3) carefully choosing the context length facilitates achieving efficient LLM training and reasoning. Inspired by these insights, we propose FastCuRL, a curriculum RL framework with stage-wise context scaling to achieve efficient LLM training and reasoning. Extensive experimental results demonstrate that FastCuRL-1.5B-V3 significantly outperforms state-of-the-art reasoning models on five competition-level benchmarks and achieves 49.6% accuracy on AIME 2024. Furthermore, FastCuRL-1.5B-Preview surpasses DeepScaleR-1.5B-Preview on five benchmarks while only using a single node with 8 GPUs and a total of 50% of training steps.

Shengzhong Zhang, Wenjie Yang, Xinyuan Cao et al.

Graph contrastive learning (GCL) has become a powerful tool for learning graph data, but its scalability remains a significant challenge. In this work, we propose a simple yet effective training framework called Structural Compression (StructComp) to address this issue. Inspired by a sparse low-rank approximation on the diffusion matrix, StructComp trains the encoder with the compressed nodes. This allows the encoder not to perform any message passing during the training stage, and significantly reduces the number of sample pairs in the contrastive loss. We theoretically prove that the original GCL loss can be approximated with the contrastive loss computed by StructComp. Moreover, StructComp can be regarded as an additional regularization term for GCL models, resulting in a more robust encoder. Empirical studies on various datasets show that StructComp greatly reduces the time and memory consumption while improving model performance compared to the vanilla GCL models and scalable training methods.

Zheng Li, Mao Zheng, Mingyang Song et al.

Recently, deep reasoning large language models(LLMs) like DeepSeek-R1 have made significant progress in tasks such as mathematics and coding. Inspired by this, several studies have employed reinforcement learning(RL) to enhance models' deep reasoning capabilities and improve machine translation(MT) quality. However, the terminology translation, an essential task in MT, remains unexplored in deep reasoning LLMs. In this paper, we propose \textbf{TAT-R1}, a terminology-aware translation model trained with reinforcement learning and word alignment. Specifically, we first extract the keyword translation pairs using a word alignment model. Then we carefully design three types of rule-based alignment rewards with the extracted alignment relationships. With those alignment rewards, the RL-trained translation model can learn to focus on the accurate translation of key information, including terminology in the source text. Experimental results show the effectiveness of TAT-R1. Our model significantly improves terminology translation accuracy compared to the baseline models while maintaining comparable performance on general translation tasks. In addition, we conduct detailed ablation studies of the DeepSeek-R1-like training paradigm for machine translation and reveal several key findings.

Jian Wu, Hang Yu, Bingchang Liu et al.

Adapting large language models (LLMs) to specific domains often faces a critical bottleneck: the scarcity of high-quality, human-curated data. While large volumes of unchecked data are readily available, indiscriminately using them for fine-tuning risks introducing noise and degrading performance. Strategic data selection is thus crucial, requiring a method that is both accurate and efficient. Existing approaches, categorized as similarity-based and direct optimization methods, struggle to simultaneously achieve these goals. In this paper, we introduce LAMDAS (LLM As an iMplicit classifier for domain-specific DAta Selection), a novel approach that leverages the pre-trained LLM itself as an implicit classifier, thereby bypassing explicit feature engineering and computationally intensive optimization process. LAMDAS reframes data selection as a one-class classification problem, identifying candidate data that "belongs" to the target domain defined by a small reference dataset. Extensive experimental results demonstrate that LAMDAS not only exceeds the performance of full-data training using a fraction of the data but also outperforms nine state-of-the-art (SOTA) baselines under various scenarios. Furthermore, LAMDAS achieves the most compelling balance between performance gains and computational efficiency compared to all evaluated baselines.

Wentao Tan, Bowen Wang, Heng Zhi et al.

Multimodal large language models (MLLMs) have advanced vision-language reasoning and are increasingly deployed in embodied agents. However, significant limitations remain: MLLMs generalize poorly across digital-physical spaces and embodiments; vision-language-action models (VLAs) produce low-level actions yet lack robust high-level embodied reasoning; and most embodied large language models (ELLMs) are constrained to digital-space with poor generalization to the physical world. Thus, unified models that operate seamlessly across digital and physical spaces while generalizing across embodiments and tasks remain absent. We introduce the \textbf{Boundless Large Model (BLM$_1$)}, a multimodal spatial foundation model that preserves instruction following and reasoning, incorporates embodied knowledge, and supports robust cross-embodiment control. BLM$_1$ integrates three key capabilities -- \textit{cross-space transfer, cross-task learning, and cross-embodiment generalization} -- via a two-stage training paradigm. Stage I injects embodied knowledge into the MLLM through curated digital corpora while maintaining language competence. Stage II trains a policy module through an intent-bridging interface that extracts high-level semantics from the MLLM to guide control, without fine-tuning the MLLM backbone. This process is supported by a self-collected cross-embodiment demonstration suite spanning four robot embodiments and six progressively challenging tasks. Evaluations across digital and physical benchmarks show that a single BLM$_1$ instance outperforms four model families -- MLLMs, ELLMs, VLAs, and GMLMs -- achieving $\sim\!\textbf{6%}$ gains in digital tasks and $\sim\!\textbf{3%}$ in physical tasks.

Shengzhong Zhang, Wenjie Yang, Yimin Zhang et al.

In this work, we discover a phenomenon of community bias amplification in graph representation learning, which refers to the exacerbation of performance bias between different classes by graph representation learning. We conduct an in-depth theoretical study of this phenomenon from a novel spectral perspective. Our analysis suggests that structural bias between communities results in varying local convergence speeds for node embeddings. This phenomenon leads to bias amplification in the classification results of downstream tasks. Based on the theoretical insights, we propose random graph coarsening, which is proved to be effective in dealing with the above issue. Finally, we propose a novel graph contrastive learning model called Random Graph Coarsening Contrastive Learning (RGCCL), which utilizes random coarsening as data augmentation and mitigates community bias by contrasting the coarsened graph with the original graph. Extensive experiments on various datasets demonstrate the advantage of our method when dealing with community bias amplification.

Ping Zhang, Zhenxiang Tao, Wenjie Yang et al.

Surveillance cameras are widely applied for indoor occupancy measurement and human movement perception, which benefit for building energy management and social security. To address the challenges of limited view angle of single camera as well as lacking of inter-camera collaboration, this study presents a non-overlapping multi-camera system to enlarge the surveillance area and devotes to retrieve the same person appeared from different camera views. The system is deployed in an office building and four-day videos are collected. By training a deep convolutional neural network, the proposed system first extracts the appearance feature embeddings of each personal image, which detected from different cameras, for similarity comparison. Then, a stochastic inter-camera transition matrix is associated with appearance feature for further improving the person re-identification ranking results. Finally, a noise-suppression explanation is given for analyzing the matching improvements. This paper expands the scope of indoor movement perception based on non-overlapping multiple cameras and improves the accuracy of pedestrian re-identification without introducing additional types of sensors.

Jian Jia, Houjing Huang, Wenjie Yang et al.

Despite various methods are proposed to make progress in pedestrian attribute recognition, a crucial problem on existing datasets is often neglected, namely, a large number of identical pedestrian identities in train and test set, which is not consistent with practical application. Thus, images of the same pedestrian identity in train set and test set are extremely similar, leading to overestimated performance of state-of-the-art methods on existing datasets. To address this problem, we propose two realistic datasets PETA\textsubscript{$zs$} and RAPv2\textsubscript{$zs$} following zero-shot setting of pedestrian identities based on PETA and RAPv2 datasets. Furthermore, compared to our strong baseline method, we have observed that recent state-of-the-art methods can not make performance improvement on PETA, RAPv2, PETA\textsubscript{$zs$} and RAPv2\textsubscript{$zs$}. Thus, through solving the inherent attribute imbalance in pedestrian attribute recognition, an efficient method is proposed to further improve the performance. Experiments on existing and proposed datasets verify the superiority of our method by achieving state-of-the-art performance.

Zewen Li, Wenjie Yang, Shouheng Peng et al.

Convolutional Neural Network (CNN) is one of the most significant networks in the deep learning field. Since CNN made impressive achievements in many areas, including but not limited to computer vision and natural language processing, it attracted much attention both of industry and academia in the past few years. The existing reviews mainly focus on the applications of CNN in different scenarios without considering CNN from a general perspective, and some novel ideas proposed recently are not covered. In this review, we aim to provide novel ideas and prospects in this fast-growing field as much as possible. Besides, not only two-dimensional convolution but also one-dimensional and multi-dimensional ones are involved. First, this review starts with a brief introduction to the history of CNN. Second, we provide an overview of CNN. Third, classic and advanced CNN models are introduced, especially those key points making them reach state-of-the-art results. Fourth, through experimental analysis, we draw some conclusions and provide several rules of thumb for function selection. Fifth, the applications of one-dimensional, two-dimensional, and multi-dimensional convolution are covered. Finally, some open issues and promising directions for CNN are discussed to serve as guidelines for future work.