Xi Zhao

Linkai Liu, Wei Feng, Xi Zhao et al.

Creative Generation (CG) leverages generative models to automatically produce advertising content that highlights product features, and it has been a significant focus of recent research. However, while CG has advanced considerably, most efforts have concentrated on generating advertising text and images, leaving Creative Video Generation (CVG) relatively underexplored. This gap is largely due to two major challenges faced by Text-to-Video (T2V) models: (a) \textbf{ambiguous semantic alignment}, where models struggle to accurately correlate product selling points with creative video content, and (b) \textbf{inadequate motion adaptability}, resulting in unrealistic movements and distortions. To address these challenges, we develop a comprehensive Advertising Creative Knowledge Base (ACKB) as a foundational resource and propose a knowledge-driven approach (KD-CVG) to overcome the knowledge limitations of existing models. KD-CVG consists of two primary modules: Semantic-Aware Retrieval (SAR) and Multimodal Knowledge Reference (MKR). SAR utilizes the semantic awareness of graph attention networks and reinforcement learning feedback to enhance the model's comprehension of the connections between selling points and creative videos. Building on this, MKR incorporates semantic and motion priors into the T2V model to address existing knowledge gaps. Extensive experiments have demonstrated KD-CVG's superior performance in achieving semantic alignment and motion adaptability, validating its effectiveness over other state-of-the-art methods. The code and dataset will be open source at https://kdcvg.github.io/KDCVG/.

Xi Zhao, Wei Feng, Zheng Zhang et al.

Recently, segmentation-based methods are quite popular in scene text detection, which mainly contain two steps: text kernel segmentation and expansion. However, the segmentation process only considers each pixel independently, and the expansion process is difficult to achieve a favorable accuracy-speed trade-off. In this paper, we propose a Context-aware and Boundary-guided Network (CBN) to tackle these problems. In CBN, a basic text detector is firstly used to predict initial segmentation results. Then, we propose a context-aware module to enhance text kernel feature representations, which considers both global and local contexts. Finally, we introduce a boundary-guided module to expand enhanced text kernels adaptively with only the pixels on the contours, which not only obtains accurate text boundaries but also keeps high speed, especially on high-resolution output maps. In particular, with a lightweight backbone, the basic detector equipped with our proposed CBN achieves state-of-the-art results on several popular benchmarks, and our proposed CBN can be plugged into several segmentation-based methods. Code is available at https://github.com/XiiZhao/cbn.pytorch.

Yao Tian, Tingyun Yan, Xi Zhao et al.

Indexing is an effective way to support efficient query processing in large databases. Recently the concept of learned index, which replaces or complements traditional index structures with machine learning models, has been actively explored to reduce storage and search costs. However, accurate and efficient similarity query processing in high-dimensional metric spaces remains to be an open challenge. In this paper, we propose a novel indexing approach called LIMS that uses data clustering, pivot-based data transformation techniques and learned indexes to support efficient similarity query processing in metric spaces. In LIMS, the underlying data is partitioned into clusters such that each cluster follows a relatively uniform data distribution. Data redistribution is achieved by utilizing a small number of pivots for each cluster. Similar data are mapped into compact regions and the mapped values are totally ordinal. Machine learning models are developed to approximate the position of each data record on disk. Efficient algorithms are designed for processing range queries and nearest neighbor queries based on LIMS, and for index maintenance with dynamic updates. Extensive experiments on real-world and synthetic datasets demonstrate the superiority of LIMS compared with traditional indexes and state-of-the-art learned indexes.

Haifeng Wang, Hua Wu, Tian Wu et al.

In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio. All modalities are trained from scratch under a unified next-group-of-tokens prediction objective, based on an ultra-sparse mixture-of-experts (MoE) architecture with modality-agnostic expert routing. To address practical challenges in large-scale deployment under diverse resource constraints, ERNIE 5.0 adopts a novel elastic training paradigm. Within a single pre-training run, the model learns a family of sub-models with varying depths, expert capacities, and routing sparsity, enabling flexible trade-offs among performance, model size, and inference latency in memory- or time-constrained scenarios. Moreover, we systematically address the challenges of scaling reinforcement learning to unified foundation models, thereby guaranteeing efficient and stable post-training under ultra-sparse MoE architectures and diverse multimodal settings. Extensive experiments demonstrate that ERNIE 5.0 achieves strong and balanced performance across multiple modalities. To the best of our knowledge, among publicly disclosed models, ERNIE 5.0 represents the first production-scale realization of a trillion-parameter unified autoregressive model that supports both multimodal understanding and generation. To facilitate further research, we present detailed visualizations of modality-agnostic expert routing in the unified model, alongside comprehensive empirical analysis of elastic training, aiming to offer profound insights to the community.

Kai Huang, Houdong Liang, Chongchong Yao et al.

Visual Graph Query Interfaces (VQIs) empower non-programmers to query graph data by constructing visual queries intuitively. Devising efficient technologies in Graph Query Engines (GQEs) for interactive search and exploration has also been studied for years. However, these two vibrant scientific fields are traditionally independent of each other, causing a vast barrier for users who wish to explore the full-stack operations of graph querying. In this demonstration, we propose a novel VQI system built upon Neo4j called VisualNeo that facilities an efficient subgraph query in large graph databases. VisualNeo inherits several advanced features from recent advanced VQIs, which include the data-driven gui design and canned pattern generation. Additionally, it embodies a database manager module in order that users can connect to generic Neo4j databases. It performs query processing through the Neo4j driver and provides an aesthetic query result exploration.

Bowen Zhang, Xi Zhao, He Wang et al.

Single-view point cloud completion aims to recover the full geometry of an object based on only limited observation, which is extremely hard due to the data sparsity and occlusion. The core challenge is to generate plausible geometries to fill the unobserved part of the object based on a partial scan, which is under-constrained and suffers from a huge solution space. Inspired by the classic shadow volume technique in computer graphics, we propose a new method to reduce the solution space effectively. Our method considers the camera a light source that casts rays toward the object. Such light rays build a reasonably constrained but sufficiently expressive basis for completion. The completion process is then formulated as a point displacement optimization problem. Points are initialized at the partial scan and then moved to their goal locations with two types of movements for each point: directional movements along the light rays and constrained local movement for shape refinement. We design neural networks to predict the ideal point movements to get the completion results. We demonstrate that our method is accurate, robust, and generalizable through exhaustive evaluation and comparison. Moreover, it outperforms state-of-the-art methods qualitatively and quantitatively on MVP datasets.

Haoyu Tang, Ye Liu, Xi Zhao et al.

Recent advances in machine learning, particularly in Natural Language Processing (NLP), have produced powerful models trained on vast datasets. However, these models risk leaking sensitive information, raising privacy concerns. In response, regulatory measures such as the European Union's General Data Protection Regulation (GDPR) have driven increasing interest in Machine Unlearning techniques, which enable models to selectively forget specific data entries. Early unlearning approaches primarily relied on pre-processing methods, while more recent research has shifted towards training-based solutions. Despite their effectiveness, a key limitation persists: most methods require access to original training data, which is often unavailable. Additionally, directly applying unlearning techniques bears the cost of undermining the model's expressive capabilities. To address these challenges, we introduce the Iterative Contrastive Unlearning (ICU) framework, which consists of three core components: A Knowledge Unlearning Induction module designed to target specific knowledge for removal using an unlearning loss; A Contrastive Learning Enhancement module to preserve the model's expressive capabilities against the pure unlearning goal; And an Iterative Unlearning Refinement module that dynamically adjusts the unlearning process through ongoing evaluation and updates. Experimental results demonstrate the efficacy of our ICU method in unlearning sensitive information while maintaining the model's overall performance, offering a promising solution for privacy-conscious machine learning applications.

Rujiao Long, Yang Li, Xingyao Zhang et al.

Exploration capacity shapes both inference-time performance and reinforcement learning (RL) training for large (vision-) language models, as stochastic sampling often yields redundant reasoning paths with little high-level diversity. This paper proposes Reasoning Palette, a novel latent-modulation framework that endows the model with a stochastic latent variable for strategic contextualization, guiding its internal planning prior to token generation. This latent context is inferred from the mean-pooled embedding of a question-answer pair via a variational autoencoder (VAE), where each sampled latent potentially encodes a distinct reasoning context. During inference, a sampled latent is decoded into learnable token prefixes and prepended to the input prompt, modulating the model's internal reasoning trajectory. In this way, the model performs internal sampling over reasoning strategies prior to output generation, which shapes the style and structure of the entire response sequence. A brief supervised fine-tuning (SFT) warm-up phase allows the model to adapt to this latent conditioning. Within RL optimization, Reasoning Palette facilitates structured exploration by enabling on-demand injection for diverse reasoning modes, significantly enhancing exploration efficiency and sustained learning capability. Experiments across multiple reasoning benchmarks demonstrate that our method enables interpretable and controllable control over the (vision-) language model's strategic behavior, thereby achieving consistent performance gains over standard RL methods.

Yao Tian, Zhoujin Tian, Xi Zhao et al.

In multi-vector retrieval, both queries and data are represented as sets of high-dimensional vectors, enabling finer-grained semantic matching and improving retrieval quality over single-vector approaches. However, its practical adoption is held back by the lack of effective indexing algorithms. Existing work, attempting to reuse standard single-vector indexes, often fails to preserve multi-vector semantics or remains slow. In this work, we present GEM, a native indexing framework for multi-vector representations. The core idea is to construct a proximity graph directly over vector sets, preserving their fine-grained semantics while enabling efficient navigation. First, GEM designs a set-level clustering scheme. It associates each vector set with only its most informative clusters, effectively reducing redundancy without hurting semantic coverage. Then, it builds local proximity graphs within clusters and bridges them into a globally navigable structure. To handle the non-metric nature of multi-vector similarity, GEM decouples the graph construction metric from the final relevance score and injects semantic shortcuts to guide efficient navigation toward relevant regions. At query time, GEM launches beam search from multiple entry points and prunes paths early using cluster cues. To further enhance efficiency, a quantized distance estimation technique is used for both indexing and search. Across in-domain, out-of-domain, and multi-modal benchmarks, GEM achieves up to 16x speedup over state-of-the-art methods while matching or improving accuracy.

Yunfei Feng, Xi Zhao, Cheng Zhang et al.

Mobile agents can autonomously complete user-assigned tasks through GUI interactions. However, existing mainstream evaluation benchmarks, such as AndroidWorld, operate by connecting to a system-level Android emulator and provide evaluation signals based on the state of system resources. In real-world mobile-agent scenarios, however, many third-party applications do not expose system-level APIs to determine whether a task has succeeded, leading to a mismatch between benchmarks and real-world usage and making it difficult to evaluate model performance accurately. To address these issues, we propose MobiFlow, an evaluation framework built on tasks drawn from arbitrary third-party applications. Using an efficient graph-construction algorithm based on multi-trajectory fusion, MobiFlow can effectively compress the state space, support dynamic interaction, and better align with real-world third-party application scenarios. MobiFlow covers 20 widely used third-party applications and comprises 240 diverse real-world tasks, with enriched evaluation metrics. Compared with AndroidWorld, MobiFlow's evaluation results show higher alignment with human assessments and can guide the training of future GUI-based models under real workloads.

Bowen Dang, Xi Zhao, Bowen Zhang et al.

We propose a new method to reconstruct the 3D human body from RGB-D images with occlusions. The foremost challenge is the incompleteness of the RGB-D data due to occlusions between the body and the environment, leading to implausible reconstructions that suffer from severe human-scene penetration. To reconstruct a semantically and physically plausible human body, we propose to reduce the solution space based on scene information and prior knowledge. Our key idea is to constrain the solution space of the human body by considering the occluded body parts and visible body parts separately: modeling all plausible poses where the occluded body parts do not penetrate the scene, and constraining the visible body parts using depth data. Specifically, the first component is realized by a neural network that estimates the candidate region named the "free zone", a region carved out of the open space within which it is safe to search for poses of the invisible body parts without concern for penetration. The second component constrains the visible body parts using the "truncated shadow volume" of the scanned body point cloud. Furthermore, we propose to use a volume matching strategy, which yields better performance than surface matching, to match the human body with the confined region. We conducted experiments on the PROX dataset, and the results demonstrate that our method produces more accurate and plausible results compared with other methods.

Bowen Zhang, Tianyu Yang, Yu Li et al.

3D generation has witnessed significant advancements, yet efficiently producing high-quality 3D assets from a single image remains challenging. In this paper, we present a triplane autoencoder, which encodes 3D models into a compact triplane latent space to effectively compress both the 3D geometry and texture information. Within the autoencoder framework, we introduce a 3D-aware cross-attention mechanism, which utilizes low-resolution latent representations to query features from a high-resolution 3D feature volume, thereby enhancing the representation capacity of the latent space. Subsequently, we train a diffusion model on this refined latent space. In contrast to solely relying on image embedding for 3D generation, our proposed method advocates for the simultaneous utilization of both image embedding and shape embedding as conditions. Specifically, the shape embedding is estimated via a diffusion prior model conditioned on the image embedding. Through comprehensive experiments, we demonstrate that our method outperforms state-of-the-art algorithms, achieving superior performance while requiring less training data and time. Our approach enables the generation of high-quality 3D assets in merely 7 seconds on a single A100 GPU.

Cheng Zhang, Erhu Feng, Xi Zhao et al.

With the rapid advancement of Vision-Language Models (VLMs), GUI-based mobile agents have emerged as a key development direction for intelligent mobile systems. However, existing agent models continue to face significant challenges in real-world task execution, particularly in terms of accuracy and efficiency. To address these limitations, we propose MobiAgent, a comprehensive mobile agent system comprising three core components: the MobiMind-series agent models, the AgentRR acceleration framework, and the MobiFlow benchmarking suite. Furthermore, recognizing that the capabilities of current mobile agents are still limited by the availability of high-quality data, we have developed an AI-assisted agile data collection pipeline that significantly reduces the cost of manual annotation. Compared to both general-purpose LLMs and specialized GUI agent models, MobiAgent achieves state-of-the-art performance in real-world mobile scenarios.

Youwen Yuan, Xi Zhao

Reconstructing translucent objects from multi-view images is a difficult problem. Previously, researchers have used differentiable path tracing and the neural implicit field, which require relatively large computational costs. Recently, many works have achieved good reconstruction results for opaque objects based on a 3DGS pipeline with much higher efficiency. However, such methods have difficulty dealing with translucent objects, because they do not consider the optical properties of translucent objects. In this paper, we propose a novel 3DGS-based pipeline (GTSR) to reconstruct the surface geometry of translucent objects. GTSR combines two sets of Gaussians, surface and interior Gaussians, which are used to model the surface and scattering color when lights pass translucent objects. To render the appearance of translucent objects, we introduce a method that uses the Fresnel term to blend two sets of Gaussians. Furthermore, to improve the reconstructed details of non-contour areas, we introduce the Disney BSDF model with deferred rendering to enhance constraints of the normal and depth. Experimental results demonstrate that our method outperforms baseline reconstruction methods on the NeuralTO Syn dataset while showing great real-time rendering performance. We also extend the dataset with new translucent objects of varying material properties and demonstrate our method can adapt to different translucent materials.

Zibin Liu, Cheng Zhang, Xi Zhao et al.

Large Language Model (LLM) agents are increasingly deployed to automate complex workflows in mobile and desktop environments. However, current model-centric agent architectures struggle to self-evolve post-deployment: improving personalization, capability, and efficiency typically requires continuous model retraining/fine-tuning, which incurs prohibitive computational overheads and suffers from an inherent trade-off between model accuracy and inference efficiency. To enable iterative self-evolution without model retraining, we propose MOBIMEM, a memory-centric agent system. MOBIMEM first introduces three specialized memory primitives to decouple agent evolution from model weights: (1) Profile Memory uses a lightweight distance-graph (DisGraph) structure to align with user preferences, resolving the accuracy-latency trade-off in user profile retrieval; (2) Experience Memory employs multi-level templates to instantiate execution logic for new tasks, ensuring capability generalization; and (3) Action Memory records fine-grained interaction sequences, reducing the reliance on expensive model inference. Building upon this memory architecture, MOBIMEM further integrates a suite of OS-inspired services to orchestrate execution: a scheduler that coordinates parallel sub-task execution and memory operations; an agent record-and-replay (AgentRR) mechanism that enables safe and efficient action reuse; and a context-aware exception handling that ensures graceful recovery from user interruptions and runtime errors. Evaluation on AndroidWorld and top-50 apps shows that MOBIMEM achieves 83.1% profile alignment with 23.83 ms retrieval time (280x faster than GraphRAG baselines), improves task success rates by up to 50.3%, and reduces end-to-end latency by up to 9x on mobile devices.

Tianqianjin Lin, Xi Zhao, Xingyao Zhang et al.

Reinforcement learning (RL) can refine the reasoning abilities of large language models (LLMs), but critically depends on a key prerequisite: the LLM can already generate high-utility reasoning paths with non-negligible probability. For tasks beyond the LLM's current competence, such reasoning path can be hard to sample, and learning risks reinforcing familiar but suboptimal reasoning. We are motivated by the insight from cognitive science that Why is this the answer is often an easier question than What is the answer, as it avoids the heavy cognitive load of open-ended exploration, opting instead for explanatory reconstruction-systematically retracing the reasoning that links a question to its answer. We show that LLMs can similarly leverage answers to derive high-quality reasoning paths. We formalize this phenomenon and prove that conditioning on answer provably increases the expected utility of sampled reasoning paths, thereby transforming intractable problems into learnable ones. Building on this insight, we introduce RAVR (Reference-Answer-guided Variational Reasoning), an end-to-end framework that uses answer-conditioned reasoning as a variational surrogate for question-only reasoning. Experiments in both general and math domains demonstrate consistent improvements over strong baselines. We further analyze the reasoning behavior and find that RAVR reduces hesitation, strengthens conclusion consolidation, and promotes problem-specific strategies in reasoning.

Xiaokang Wei, Bowen Zhang, Xianghui Yang et al.

Generating high-quality physically based rendering (PBR) materials is important to achieve realistic rendering in the downstream tasks, yet it remains challenging due to the intertwined effects of materials and lighting. While existing methods have made breakthroughs by incorporating material decomposition in the 3D generation pipeline, they tend to bake highlights into albedo and ignore spatially varying properties of metallicity and roughness. In this work, we present PBR3DGen, a two-stage mesh generation method with high-quality PBR materials that integrates the novel multi-view PBR material estimation model and a 3D PBR mesh reconstruction model. Specifically, PBR3DGen leverages vision language models (VLM) to guide multi-view diffusion, precisely capturing the spatial distribution and inherent attributes of reflective-metalness material. Additionally, we incorporate view-dependent illumination-aware conditions as pixel-aware priors to enhance spatially varying material properties. Furthermore, our reconstruction model reconstructs high-quality mesh with PBR materials. Experimental results demonstrate that PBR3DGen significantly outperforms existing methods, achieving new state-of-the-art results for PBR estimation and mesh generation. More results and visualization can be found on our project page: https://pbr3dgen1218.github.io/.

Bowen Dang, Xi Zhao

This paper presents a novel method for generating diverse 3D human poses in scenes with semantic control. Existing methods heavily rely on the human-scene interaction dataset, resulting in a limited diversity of the generated human poses. To overcome this challenge, we propose to decouple the pose and interaction generation process. Our approach consists of three stages: pose generation, contact generation, and putting human into the scene. We train a pose generator on the human dataset to learn rich pose prior, and a contact generator on the human-scene interaction dataset to learn human-scene contact prior. Finally, the placing module puts the human body into the scene in a suitable and natural manner. The experimental results on the PROX dataset demonstrate that our method produces more physically plausible interactions and exhibits more diverse human poses. Furthermore, experiments on the MP3D-R dataset further validates the generalization ability of our method.

Feixiang He, Yuanhang Xiang, Xi Zhao et al.

Crowd simulation is a central topic in several fields including graphics. To achieve high-fidelity simulations, data has been increasingly relied upon for analysis and simulation guidance. However, the information in real-world data is often noisy, mixed and unstructured, making it difficult for effective analysis, therefore has not been fully utilized. With the fast-growing volume of crowd data, such a bottleneck needs to be addressed. In this paper, we propose a new framework which comprehensively tackles this problem. It centers at an unsupervised method for analysis. The method takes as input raw and noisy data with highly mixed multi-dimensional (space, time and dynamics) information, and automatically structure it by learning the correlations among these dimensions. The dimensions together with their correlations fully describe the scene semantics which consists of recurring activity patterns in a scene, manifested as space flows with temporal and dynamics profiles. The effectiveness and robustness of the analysis have been tested on datasets with great variations in volume, duration, environment and crowd dynamics. Based on the analysis, new methods for data visualization, simulation evaluation and simulation guidance are also proposed. Together, our framework establishes a highly automated pipeline from raw data to crowd analysis, comparison and simulation guidance. Extensive experiments and evaluations have been conducted to show the flexibility, versatility and intuitiveness of our framework.

Zhihao Shen, Wan Du, Xi Zhao et al.

Retrieving similar trajectories from a large trajectory dataset is important for a variety of applications, like transportation planning and mobility analysis. Unlike previous works based on fine-grained GPS trajectories, this paper investigates the feasibility of identifying similar trajectories from cellular data observed by mobile infrastructure, which provide more comprehensive coverage. To handle the large localization errors and low sample rates of cellular data, we develop a holistic system, cellSim, which seamlessly integrates map matching and similar trajectory search. A set of map matching techniques are proposed to transform cell tower sequences into moving trajectories on a road map by considering the unique features of cellular data, like the dynamic density of cell towers and bidirectional roads. To further improve the accuracy of similarity search, map matching outputs M trajectory candidates of different confidence, and a new similarity measure scheme is developed to process the map matching results. Meanwhile, M is dynamically adapted to maintain a low false positive rate of the similarity search, and two pruning schemes are proposed to minimize the computation overhead. Extensive experiments on a large-scale dataset and real-world trajectories of 1701 km reveal that cellSim provides high accuracy (precision 62.4% and recall of 89.8%).

Xi Zhao, Yong Ding, Quanyu Zhao

In this paper a new multi-candidate electronic voting scheme is constructed with unlimited participants. The main idea is to express a ballot to allow voting for up to k out of the m candidates and unlimited participants. The purpose of vote is to select more than one winner among $m$ candidates. Our result is complementary to the result by Sun peiyong$'$ s scheme, in the sense, their scheme is not amenable for large-scale electronic voting due to flaw of ballot structure. In our scheme the vote is split and hidden, and tallying is made for $G\ddot{o}del$ encoding in decimal base without any trusted third party, and the result does not rely on any traditional cryptography or computational intractable assumption. Thus the proposed scheme not only solves the problem of ballot structure, but also achieves the security including perfect ballot secrecy, receipt-free, robustness, fairness and dispute-freeness.

Wuming Zhang, Xi Zhao, Jean-Marie Morvan et al.

2D face analysis techniques, such as face landmarking, face recognition and face verification, are reasonably dependent on illumination conditions which are usually uncontrolled and unpredictable in the real world. An illumination robust preprocessing method thus remains a significant challenge in reliable face analysis. In this paper we propose a novel approach for improving lighting normalization through building the underlying reflectance model which characterizes interactions between skin surface, lighting source and camera sensor, and elaborates the formation of face color appearance. Specifically, the proposed illumination processing pipeline enables the generation of Chromaticity Intrinsic Image (CII) in a log chromaticity space which is robust to illumination variations. Moreover, as an advantage over most prevailing methods, a photo-realistic color face image is subsequently reconstructed which eliminates a wide variety of shadows whilst retaining the color information and identity details. Experimental results under different scenarios and using various face databases show the effectiveness of the proposed approach to deal with lighting variations, including both soft and hard shadows, in face recognition.