arXiv subjects

Xiaoyu Li

Publications and source records attributed to Xiaoyu Li.

At least 109 records · Page 6Linked to original sources

arXiv2025

IC-Custom: Diverse Image Customization via In-Context Learning

Image customization, a crucial technique for industrial media production, aims to generate content that is consistent with reference images. However, current approaches conventionally separate image customization into position-aware and position-free customization paradigms and lack a universal framework for diverse customization, limiting their applications across various scenarios. To overcome these limitations, we propose IC-Custom, a unified framework that seamlessly integrates position-aware and position-free image customization through in-context learning. IC-Custom concatenates reference images with target images to a polyptych, leveraging DiT's multi-modal attention mechanism for fine-grained token-level interactions. We propose the In-context Multi-Modal Attention (ICMA) mechanism, which employs learnable task-oriented register tokens and boundary-aware positional embeddings to enable the model to effectively handle diverse tasks and distinguish between inputs in polyptych configurations. To address the data gap, we curated a 12K identity-consistent dataset with 8K real-world and 4K high-quality synthetic samples, avoiding the overly glossy, oversaturated look typical of synthetic data. IC-Custom supports various industrial applications, including try-on, image insertion, and creative IP customization. Extensive evaluations on our proposed ProductBench and the publicly available DreamBench demonstrate that IC-Custom significantly outperforms community workflows, closed-source models, and state-of-the-art open-source approaches. IC-Custom achieves about 73\% higher human preference across identity consistency, harmony, and text alignment metrics, while training only 0.4\% of the original model parameters. Project page: https://liyaowei-stu.github.io/project/IC_Custom

cs.CV↗

arXiv2025

ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing

Traditional cartoon and anime production involves keyframing, inbetweening, and colorization stages, which require intensive manual effort. Despite recent advances in AI, existing methods often handle these stages separately, leading to error accumulation and artifacts. For instance, inbetweening approaches struggle with large motions, while colorization methods require dense per-frame sketches. To address this, we introduce ToonComposer, a generative model that unifies inbetweening and colorization into a single post-keyframing stage. ToonComposer employs a sparse sketch injection mechanism to provide precise control using keyframe sketches. Additionally, it uses a cartoon adaptation method with the spatial low-rank adapter to tailor a modern video foundation model to the cartoon domain while keeping its temporal prior intact. Requiring as few as a single sketch and a colored reference frame, ToonComposer excels with sparse inputs, while also supporting multiple sketches at any temporal location for more precise motion control. This dual capability reduces manual workload and improves flexibility, empowering artists in real-world scenarios. To evaluate our model, we further created PKBench, a benchmark featuring human-drawn sketches that simulate real-world use cases. Our evaluation demonstrates that ToonComposer outperforms existing methods in visual quality, motion consistency, and production efficiency, offering a superior and more flexible solution for AI-assisted cartoon production.

cs.CV↗

arXiv2025

Implicit Hypergraph Neural Networks: A Stable Framework for Higher-Order Relational Learning with Provable Guarantees

Many real-world interactions are group-based rather than pairwise such as papers with multiple co-authors and users jointly engaging with items. Hypergraph neural networks have shown great promise at modeling higher-order relations, but their reliance on a fixed number of explicit message-passing layers limits long-range dependency capture and can destabilize training as depth grows. In this work, we introduce Implicit Hypergraph Neural Networks (IHGNN), which bring the implicit equilibrium formulation to hypergraphs: instead of stacking layers, IHGNN computes representations as the solution to a nonlinear fixed-point equation, enabling stable and efficient global propagation across hyperedges without deep architectures. We develop a well-posed training scheme with provable convergence, analyze the oversmoothing conditions and expressivity of the model, and derive a transductive generalization bound on hypergraphs. We further present an implicit-gradient training procedure coupled with a projection-based stabilization strategy. Extensive experiments on citation benchmarks show that IHGNN consistently outperforms strong traditional graph/hypergraph neural network baselines in both accuracy and robustness. Empirically, IHGNN is resilient to random initialization and hyperparameter variation, highlighting its strong generalization and practical value for higher-order relational learning.

cs.LG↗

arXiv2025

EF-VI: Enhancing End-Frame Injection for Video Inbetweening

Video inbetweening aims to synthesize intermediate video sequences conditioned on the given start and end frames. Current state-of-the-art methods primarily extend large-scale pre-trained Image-to-Video Diffusion Models (I2V-DMs) by incorporating the end-frame condition via direct fine-tuning or temporally bidirectional sampling. However, the former results in a weak end-frame constraint, while the latter inevitably disrupts the input representation of video frames, leading to suboptimal performance. To improve the end-frame constraint while avoiding disruption of the input representation, we propose a novel video inbetweening framework specific to recent and more powerful transformer-based I2V-DMs, termed EF-VI. It efficiently strengthens the end-frame constraint by utilizing an enhanced injection. This is based on our proposed well-designed lightweight module, termed EF-Net, which encodes only the end frame and expands it into temporally adaptive frame-wise features injected into the I2V-DM. Extensive experiments demonstrate the superiority of our EF-VI compared with other baselines.

cs.CV↗

arXiv2025

4DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation

Given the high complexity of directly generating high-dimensional data such as 4D, we present 4DVD, a cascaded video diffusion model that generates 4D content in a decoupled manner. Unlike previous multi-view video methods that directly model 3D space and temporal features simultaneously with stacked cross view/temporal attention modules, 4DVD decouples this into two subtasks: coarse multi-view layout generation and structure-aware conditional generation, and effectively unifies them. Specifically, given a monocular video, 4DVD first predicts the dense view content of its layout with superior cross-view and temporal consistency. Based on the produced layout priors, a structure-aware spatio-temporal generation branch is developed, combining these coarse structural priors with the exquisite appearance content of input monocular video to generate final high-quality dense-view videos. Benefit from this, explicit 4D representation~(such as 4D Gaussian) can be optimized accurately, enabling wider practical application. To train 4DVD, we collect a dynamic 3D object dataset, called D-Objaverse, from the Objaverse benchmark and render 16 videos with 21 frames for each object. Extensive experiments demonstrate our state-of-the-art performance on both novel view synthesis and 4D generation. Our project page is https://4dvd.github.io/

cs.CV↗

arXiv2025

Channel-Independent Federated Traffic Prediction

In recent years, traffic prediction has achieved remarkable success and has become an integral component of intelligent transportation systems. However, traffic data is typically distributed among multiple data owners, and privacy constraints prevent the direct utilization of these isolated datasets for traffic prediction. Most existing federated traffic prediction methods focus on designing communication mechanisms that allow models to leverage information from other clients in order to improve prediction accuracy. Unfortunately, such approaches often incur substantial communication overhead, and the resulting transmission delays significantly slow down the training process. As the volume of traffic data continues to grow, this issue becomes increasingly critical, making the resource consumption of current methods unsustainable. To address this challenge, we propose a novel variable relationship modeling paradigm for federated traffic prediction, termed the Channel-Independent Paradigm(CIP). Unlike traditional approaches, CIP eliminates the need for inter-client communication by enabling each node to perform efficient and accurate predictions using only local information. Based on the CIP, we further develop Fed-CI, an efficient federated learning framework, allowing each client to process its own data independently while effectively mitigating the information loss caused by the lack of direct data sharing among clients. Fed-CI significantly reduces communication overhead, accelerates the training process, and achieves state-of-the-art performance while complying with privacy regulations. Extensive experiments on multiple real-world datasets demonstrate that Fed-CI consistently outperforms existing methods across all datasets and federated settings. It achieves improvements of 8%, 14%, and 16% in RMSE, MAE, and MAPE, respectively, while also substantially reducing communication costs.

cs.LG↗

arXiv2025

A Forced-Choice Neural Cognitive Diagnostic Model of Personality Testing

In the smart era, psychometric tests are becoming increasingly important for personnel selection, career development, and mental health assessment. Forced-choice tests are common in personality assessments because they require participants to select from closely related options, lowering the risk of response distortion. This study presents a deep learning-based Forced-Choice Neural Cognitive Diagnostic Model (FCNCD) that overcomes the limitations of traditional models and is applicable to the three most common item block types found in forced-choice tests. To account for the unidimensionality of items in forced-choice tests, we create interpretable participant and item parameters. We model the interactions between participant and item features using multilayer neural networks after mining them using nonlinear mapping. In addition, we use the monotonicity assumption to improve the interpretability of the diagnostic results. The FCNCD's effectiveness is validated by experiments on real-world and simulated datasets that show its accuracy, interpretability, and robustness.

cs.AI↗

arXiv2025

End-to-end multi-channel speaker extraction and binaural speech synthesis

Speech clarity and spatial audio immersion are the two most critical factors in enhancing remote conferencing experiences. Existing methods are often limited: either due to the lack of spatial information when using only one microphone, or because their performance is highly dependent on the accuracy of direction-of-arrival estimation when using microphone array. To overcome this issue, we introduce an end-to-end deep learning framework that has the capacity of mapping multi-channel noisy and reverberant signals to clean and spatialized binaural speech directly. This framework unifies source extraction, noise suppression, and binaural rendering into one network. In this framework, a novel magnitude-weighted interaural level difference loss function is proposed that aims to improve the accuracy of spatial rendering. Extensive evaluations show that our method outperforms established baselines in terms of both speech quality and spatial fidelity.

cs.SD↗

arXiv2025

DYNAMO: Dynamic Neutral Atom Multi-programming Optimizer Towards Quantum Operating Systems

As quantum computing advances towards practical applications, quantum operating systems become inevitable, where multi-programming -- the core functionality of operating systems -- enables concurrent execution of multiple quantum programs to enhance hardware utilization. However, most quantum compilation work focuses solely on single-circuit execution, severely limiting resource efficiency and hindering quantum operating system development. We propose Dynamic Neutral Atom Multi-programming Optimizer (DYNAMO), a method that realizes multi-programming on neutral atom quantum architectures through parallel compilation and intelligent resource allocation across multiple quantum processing units (QPUs). DYNAMO addresses two critical challenges: inefficient and difficult resource partitioning, and complex scheduling conflicts from concurrent program. Our method enables efficient spatial and temporal resource sharing while maintaining circuit correctness and hardware constraints. Experimental evaluation across circuits ranging from 12 to over 1200 gates demonstrates that DYNAMO achieves up to 14.39x compilation speedup while reducing execution stages by an average of 50.47%. Furthermore, DYNAMO successfully distributes workloads across multiple QPUs with balanced resource utilization. By enabling efficient multi-programming capabilities, DYNAMO establishes a critical foundation towards realizing practical quantum operating systems.

quant-ph↗

arXiv2025

Accept More, Reject Less: Reducing up to 19% Unnecessary Desk-Rejections over 11 Years of ICLR Data

The explosive growth of AI research has driven paper submissions at flagship AI conferences to unprecedented levels, necessitating many venues in 2025 (e.g., CVPR, ICCV, KDD, AAAI, IJCAI, WSDM) to enforce strict per-author submission limits and to desk-reject any excess papers by simple ID order. While this policy helps reduce reviewer workload, it may unintentionally discard valuable papers and penalize authors' efforts. In this paper, we ask an essential research question on whether it is possible to follow submission limits while minimizing needless rejections. We first formalize the current desk-rejection policies as an optimization problem, and then develop a practical algorithm based on linear programming relaxation and a rounding scheme. Under extensive evaluation on 11 years of real-world ICLR (International Conference on Learning Representations) data, our method preserves up to $19.23\%$ more papers without violating any author limits. Moreover, our algorithm is highly efficient in practice, with all results on ICLR data computed within at most 53.64 seconds. Our work provides a simple and practical desk-rejection strategy that significantly reduces unnecessary rejections, demonstrating strong potential to improve current CS conference submission policies.

cs.DS↗

arXiv2025

Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Content

Evaluating text-to-vision content hinges on two crucial aspects: visual quality and alignment. While significant progress has been made in developing objective models to assess these dimensions, the performance of such models heavily relies on the scale and quality of human annotations. According to Scaling Law, increasing the number of human-labeled instances follows a predictable pattern that enhances the performance of evaluation models. Therefore, we introduce a comprehensive dataset designed to Evaluate Visual quality and Alignment Level for text-to-vision content (Q-EVAL-100K), featuring the largest collection of human-labeled Mean Opinion Scores (MOS) for the mentioned two aspects. The Q-EVAL-100K dataset encompasses both text-to-image and text-to-video models, with 960K human annotations specifically focused on visual quality and alignment for 100K instances (60K images and 40K videos). Leveraging this dataset with context prompt, we propose Q-Eval-Score, a unified model capable of evaluating both visual quality and alignment with special improvements for handling long-text prompt alignment. Experimental results indicate that the proposed Q-Eval-Score achieves superior performance on both visual quality and alignment, with strong generalization capabilities across other benchmarks. These findings highlight the significant value of the Q-EVAL-100K dataset. Data and codes will be available at https://github.com/zzc-1998/Q-Eval.

cs.CV↗

arXiv2025

Ming-Omni: A Unified Multimodal Model for Perception and Generation

We propose Ming-Omni, a unified multimodal model capable of processing images, text, audio, and video, while demonstrating strong proficiency in both speech and image generation. Ming-Omni employs dedicated encoders to extract tokens from different modalities, which are then processed by Ling, an MoE architecture equipped with newly proposed modality-specific routers. This design enables a single model to efficiently process and fuse multimodal inputs within a unified framework, thereby facilitating diverse tasks without requiring separate models, task-specific fine-tuning, or structural redesign. Importantly, Ming-Omni extends beyond conventional multimodal models by supporting audio and image generation. This is achieved through the integration of an advanced audio decoder for natural-sounding speech and Ming-Lite-Uni for high-quality image generation, which also allow the model to engage in context-aware chatting, perform text-to-speech conversion, and conduct versatile image editing. Our experimental results showcase Ming-Omni offers a powerful solution for unified perception and generation across all modalities. Notably, our proposed Ming-Omni is the first open-source model we are aware of to match GPT-4o in modality support, and we release all code and model weights to encourage further research and development in the community.

cs.AI↗

arXiv2025

Proactive Guidance of Multi-Turn Conversation in Industrial Search

The evolution of Large Language Models (LLMs) has significantly advanced multi-turn conversation systems, emphasizing the need for proactive guidance to enhance users' interactions. However, these systems face challenges in dynamically adapting to shifts in users' goals and maintaining low latency for real-time interactions. In the Baidu Search AI assistant, an industrial-scale multi-turn search system, we propose a novel two-phase framework to provide proactive guidance. The first phase, Goal-adaptive Supervised Fine-Tuning (G-SFT), employs a goal adaptation agent that dynamically adapts to user goal shifts and provides goal-relevant contextual information. G-SFT also incorporates scalable knowledge transfer to distill insights from LLMs into a lightweight model for real-time interaction. The second phase, Click-oriented Reinforcement Learning (C-RL), adopts a generate-rank paradigm, systematically constructs preference pairs from user click signals, and proactively improves click-through rates through more engaging guidance. This dual-phase architecture achieves complementary objectives: G-SFT ensures accurate goal tracking, while C-RL optimizes interaction quality through click signal-driven reinforcement learning. Extensive experiments demonstrate that our framework achieves 86.10% accuracy in offline evaluation (+23.95% over baseline) and 25.28% CTR in online deployment (149.06% relative improvement), while reducing inference latency by 69.55% through scalable knowledge distillation.

cs.CL↗

arXiv2025

Discrepancy Minimization in Input-Sparsity Time

A recent work by [Larsen, SODA 2023] introduced a faster combinatorial alternative to Bansal's SDP algorithm for finding a coloring $x \in \{-1, 1\}^n$ that approximately minimizes the discrepancy $\mathrm{disc}(A, x) := | A x |_{\infty}$ of a real-valued $m \times n$ matrix $A$. Larsen's algorithm runs in $\widetilde{O}(mn^2)$ time compared to Bansal's $\widetilde{O}(mn^{4.5})$-time algorithm, with a slightly weaker logarithmic approximation ratio in terms of the hereditary discrepancy of $A$ [Bansal, FOCS 2010]. We present a combinatorial $\widetilde{O}(\mathrm{nnz}(A) + n^3)$-time algorithm with the same approximation guarantee as Larsen's, optimal for tall matrices where $m = \mathrm{poly}(n)$. Using a more intricate analysis and fast matrix multiplication, we further achieve a runtime of $\widetilde{O}(\mathrm{nnz}(A) + n^{2.53})$, breaking the cubic barrier for square matrices and surpassing the limitations of linear-programming approaches [Eldan and Singh, RS&A 2018]. Our algorithm relies on two key ideas: (i) a new sketching technique for finding a projection matrix with a short $\ell_2$-basis using implicit leverage-score sampling, and (ii) a data structure for efficiently implementing the iterative Edge-Walk partial-coloring algorithm [Lovett and Meka, SICOMP 2015], and using an alternative analysis to enable ''lazy'' batch updates with low-rank corrections. Our results nearly close the computational gap between real-valued and binary matrices, for which input-sparsity time coloring was recently obtained by [Jain, Sah and Sawhney, SODA 2023].

cs.DS↗

arXiv2025

Physics-Aware Compilation for Parallel Quantum Circuit Execution on Neutral Atom Arrays

Neutral atom quantum computers are one of the most promising quantum architectures, offering advantages in scalability, dynamic reconfigurability, and potential for large-scale implementations. These characteristics create unique compilation challenges, especially regarding compilation efficiency while adapting to hardware flexibility. However, existing methods encounter significant performance bottlenecks at scale, hindering practical applications. We propose Physics-Aware Compilation (PAC), a method that improves compilation efficiency while preserving the inherent flexibility of neutral atom systems. PAC introduces physics-aware hardware plane partitioning that strategically allocates hardware resources based on physical device characteristics like AOD and SLM trap properties and qubit mobility constraints. Additionally, it implements parallel quantum circuit division with an improved Kernighan-Lin algorithm that enables simultaneous execution across independent regions while maintaining circuit fidelity. Our experimental evaluation compares PAC with state-of-the-art methods across increasingly larger array sizes ranging from 16x16 to 64x64 qubits. Results demonstrate that PAC achieves up to 78.5x speedup on 16x16 arrays while maintaining comparable circuit quality. PAC's compilation efficiency advantage increases with system scale, demonstrating scalability for practical quantum applications on larger arrays. PAC explores a viable path for practical applications of neutral atom quantum computers by effectively addressing the tension between compilation efficiency and hardware flexibility.

quant-ph↗

arXiv2025

Audio Turing Test: Benchmarking the Human-likeness of Large Language Model-based Text-to-Speech Systems in Chinese

Recent advances in large language models (LLMs) have significantly improved text-to-speech (TTS) systems, enhancing control over speech style, naturalness, and emotional expression, which brings TTS Systems closer to human-level performance. Although the Mean Opinion Score (MOS) remains the standard for TTS System evaluation, it suffers from subjectivity, environmental inconsistencies, and limited interpretability. Existing evaluation datasets also lack a multi-dimensional design, often neglecting factors such as speaking styles, context diversity, and trap utterances, which is particularly evident in Chinese TTS evaluation. To address these challenges, we introduce the Audio Turing Test (ATT), a multi-dimensional Chinese corpus dataset ATT-Corpus paired with a simple, Turing-Test-inspired evaluation protocol. Instead of relying on complex MOS scales or direct model comparisons, ATT asks evaluators to judge whether a voice sounds human. This simplification reduces rating bias and improves evaluation robustness. To further support rapid model development, we also finetune Qwen2-Audio-Instruct with human judgment data as Auto-ATT for automatic evaluation. Experimental results show that ATT effectively differentiates models across specific capability dimensions using its multi-dimensional design. Auto-ATT also demonstrates strong alignment with human evaluations, confirming its value as a fast and reliable assessment tool. The white-box ATT-Corpus and Auto-ATT can be found in ATT Hugging Face Collection (https://huggingface.co/collections/meituan/audio-turing-test-682446320368164faeaf38a4).

cs.SD↗

arXiv2025

HAQA: A Hardware-Guided and Fidelity-Aware Strategy for Efficient Qubit Mapping Optimization

Quantum algorithms rely on quantum computers for implementation, but the physical connectivity constraints of modern quantum processors impede the efficient realization of quantum algorithms. Qubit mapping, a critical technology for practical quantum computing applications, directly determines the execution efficiency and feasibility of algorithms on superconducting quantum processors. Existing mapping methods overlook intractable quantum hardware fidelity characteristics, reducing circuit execution quality. They also exhibit prolonged solving times or even failure to complete when handling large-scale quantum architectures, compromising efficiency. To address these challenges, we propose a novel qubit mapping method HAQA. HAQA first introduces a community-based iterative region identification strategy leveraging hardware connection topology, achieving effective dimensionality reduction of mapping space. This strategy avoids global search procedures, with complexity analysis demonstrating quadratic polynomial-level acceleration. Furthermore, HAQA implements a hardware-characteristic-based region evaluation mechanism, enabling quantitative selection of mapping regions based on fidelity metrics. This approach effectively integrates hardware fidelity information into the mapping process, enabling fidelity-aware qubit allocation. Experimental results demonstrate that HAQA significantly improves solving speed and fidelity while ensuring solution quality. When applied to state-of-the-art quantum mapping techniques Qsynth-v2 and TB-OLSQ2, HAQA achieves acceleration ratios of 632.76 and 286.87 respectively, while improving fidelity by up to 52.69% and 238.28%

quant-ph↗

arXiv2025

Traffic Flow Data Completion and Anomaly Diagnosis via Sparse and Low-Rank Tensor Optimization

Spatiotemporal traffic time series, such as traffic speed data, collected from sensing systems are often incomplete, with considerable corruption and large amounts of missing values. A vast amount of data conceals implicit data structures, which poses significant challenges for data recovery issues, such as mining the potential spatio-temporal correlations of data and identifying abnormal data. In this paper, we propose a Tucker decomposition-based sparse low-rank high-order tensor optimization model (TSLTO) for data imputation and anomaly diagnosis. We decompose the traffic tensor data into low-rank and sparse tensors, and establish a sparse low-rank high-order tensor optimization model based on Tucker decomposition. By utilizing tools of non-smooth analysis for tensor functions, we explore the optimality conditions of the proposed tensor optimization model and design an ADMM optimization algorithm for solving the model. Finally, numerical experiments are conducted on both synthetic data and a real-world dataset: the urban traffic speed dataset of Guangzhou. Numerical comparisons with several representative existing algorithms demonstrate that our proposed approach achieves higher accuracy and efficiency in traffic flow data recovery and anomaly diagnosis tasks.

math.OC↗