arXiv subjects

You Li

Publications and source records attributed to You Li.

At least 37 records · Page 2Linked to original sources

arXiv2026

FoleyDirector: Fine-Grained Temporal Steering for Video-to-Audio Generation via Structured Scripts

Recent Video-to-Audio (V2A) methods have achieved remarkable progress, enabling the synthesis of realistic, high-quality audio. However, they struggle with fine-grained temporal control in multi-event scenarios or when visual cues are insufficient, such as small regions, off-screen sounds, or occluded or partially visible objects. In this paper, we propose FoleyDirector, a framework that, for the first time, enables precise temporal guidance in DiT-based V2A generation while preserving the base model's audio quality and allowing seamless switching between V2A generation and temporally controlled synthesis. FoleyDirector introduces Structured Temporal Scripts (STS), a set of captions corresponding to short temporal segments, to provide richer temporal information. These features are integrated via the Script-Guided Temporal Fusion Module, which employs Temporal Script Attention to fuse STS features coherently. To handle complex multi-event scenarios, we further propose Bi-Frame Sound Synthesis, enabling parallel in-frame and out-of-frame audio generation and improving controllability. To support training and evaluation, we construct the DirectorSound dataset and introduce VGGSoundDirector and DirectorBench. Experiments demonstrate that FoleyDirector substantially enhances temporal controllability while maintaining high audio fidelity, empowering users to act as Foley directors and advancing V2A toward more expressive and controllable generation.

cs.SD↗

arXiv2026

RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details

We introduce region-specific image refinement as a dedicated problem setting: given an input image and a user-specified region (e.g., a scribble mask or a bounding box), the goal is to restore fine-grained details while keeping all non-edited pixels strictly unchanged. Despite rapid progress in image generation, modern models still frequently suffer from local detail collapse (e.g., distorted text, logos, and thin structures). Existing instruction-driven editing models emphasize coarse-grained semantic edits and often either overlook subtle local defects or inadvertently change the background, especially when the region of interest occupies only a small portion of a fixed-resolution input. We present RefineAnything, a multimodal diffusion-based refinement model that supports both reference-based and reference-free refinement. Building on a counter-intuitive observation that crop-and-resize can substantially improve local reconstruction under a fixed VAE input resolution, we propose Focus-and-Refine, a region-focused refinement-and-paste-back strategy that improves refinement effectiveness and efficiency by reallocating the resolution budget to the target region, while a blended-mask paste-back guarantees strict background preservation. We further introduce a boundary-aware Boundary Consistency Loss to reduce seam artifacts and improve paste-back naturalness. To support this new setting, we construct Refine-30K (20K reference-based and 10K reference-free samples) and introduce RefineEval, a benchmark that evaluates both edited-region fidelity and background consistency. On RefineEval, RefineAnything achieves strong improvements over competitive baselines and near-perfect background preservation, establishing a practical solution for high-precision local refinement. Project Page: https://limuloo.github.io/RefineAnything/.

cs.CV↗

arXiv2026

Sustaining high-fidelity quantum logic in neutral-atom circuits via mid-circuit operations

The realization of fault-tolerant quantum computation hinges on the ability to execute deep quantum circuits while maintaining gate fidelities consistently above error-correction thresholds. Although neutral-atom arrays have recently demonstrated high-fidelity two-qubit gates and early-stage logical quantum processors, sustaining such high performance across deep, repetitive circuits remains a formidable challenge due to cumulative motional heating and atom loss. Here we demonstrate a sustainable neutral-atom framework that overcomes these limitations by integrating a suite of hardware-efficient mid-circuit operations. We report a two-qubit controlled logic gate with a raw fidelity of 99.60(1)%, which is further increased to a fidelity of 99.81(1)% via non-destructive erasure detection. Crucially, by implementing in-circuit Raman sideband cooling and qubit re-initialization, we demonstrate that gate fidelities can be maintained at the ~99.8% level across multiple operational rounds without observable degradation. By actively managing the internal and motional entropy of the system mid-stream, our in-situ refreshable architecture provides a critical pathway for executing the repeated syndrome-extraction cycles required for large-scale, continuous quantum error correction.

quant-ph↗

arXiv2025

LLA: Enhancing Security and Privacy for Generative Models with Logic-Locked Accelerators

We introduce LLA, an effective intellectual property (IP) protection scheme for generative AI models. LLA leverages the synergy between hardware and software to defend against various supply chain threats, including model theft, model corruption, and information leakage. On the software side, it embeds key bits into neurons that can trigger outliers to degrade performance and applies invariance transformations to obscure the key values. On the hardware side, it integrates a lightweight locking module into the AI accelerator while maintaining compatibility with various dataflow patterns and toolchains. An accelerator with a pre-stored secret key acts as a license to access the model services provided by the IP owner. The evaluation results show that LLA can withstand a broad range of oracle-guided key optimization attacks, while incurring a minimal computational overhead of less than 0.1% for 7,168 key bits.

cs.CR↗

arXiv2025

Simultaneous Enhancement and Noise Suppression under Complex Illumination Conditions

Under challenging light conditions, captured images often suffer from various degradations, leading to a decline in the performance of vision-based applications. Although numerous methods have been proposed to enhance image quality, they either significantly amplify inherent noise or are only effective under specific illumination conditions. To address these issues, we propose a novel framework for simultaneous enhancement and noise suppression under complex illumination conditions. Firstly, a gradient-domain weighted guided filter (GDWGIF) is employed to accurately estimate illumination and improve image quality. Next, the Retinex model is applied to decompose the captured image into separate illumination and reflection layers. These layers undergo parallel processing, with the illumination layer being corrected to optimize lighting conditions and the reflection layer enhanced to improve image quality. Finally, the dynamic range of the image is optimized through multi-exposure fusion and a linear stretching strategy. The proposed method is evaluated on real-world datasets obtained from practical applications. Experimental results demonstrate that our proposed method achieves better performance compared to state-of-the-art methods in both contrast enhancement and noise suppression.

cs.CV↗

arXiv2025

DreamFoley: Scalable VLMs for High-Fidelity Video-to-Audio Generation

Recent advances in video generation have achieved remarkable improvements in visual content fidelity. However, the absence of synchronized audio severely undermines immersive experience and restricts practical applications of these technologies. To address this challenge, several pioneering works have explored diffusion transformer architectures for generating plausible video-synchronized audio, including Kling-foley, HunyuanVideo-foley and Thinksound. Distinct from existing works, we introduce an autoregressive audio generation architecture (DreamFoley) that harnesses the capabilities of large vision-language models (VLMs) to jointly model sequential interactions among video, audio, and text modalities. Our approach features a dual-visual encoder module that effectively captures both audio-aligned and text-aligned visual features. Additionally, we employ a Residual Vector Quantization audio tokenizer with a delay-pattern generation scheme to balance the trade-off between training efficiency and audio quality. Moreover, we introduce the classifier-free guidance strategy into VLMs to bootstrap generated audio quality. Furthermore, we establish an efficient data production pipeline to scale audio-video-text triple collection. Finally, extensive experiments are conducted to validate the effectiveness of our model, achieving promising performance across popular benchmarks. We hope that the findings in this study provide a strong foundation for future video-to-audio generation research. We also release the previously missing audio-visual textual descriptions from the public benchmark, aiming to facilitate subsequent researchers in conducting more convenient and effective evaluations and comparisons.

cs.SD↗

arXiv2025

Existence and nonexistence of viscosity solutions for a class of degenerate/singular eigenvalue type equations

This paper is devoted to a complete classification on the existence and nonexistence results of viscosity solutions to the general Dirichlet problem for a class of eigenvalue type equations. With the distance function included in the right-hand side, this type of equations can be degenerate and (or) singular near the boundary of uniformly convex domains. One highlight is that all cases related to the exponent of the distance function are investigated. Moreover, when viscosity solutions exist, we derive a series of global estimates based on the distance function. The key ingredients of this paper include adaptions of the Perron method and comparison principle as well as constructions of suitable classical sub-solutions and super-solutions.

math.AP↗

arXiv2025

Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model

The rapid development of Multimodal Large Reasoning Models (MLRMs) has demonstrated broad application potential, yet their safety and reliability remain critical concerns that require systematic exploration. To address this gap, we conduct a comprehensive and systematic safety evaluation of 11 MLRMs across 5 benchmarks and unveil prevalent safety degradation phenomena in most advanced models. Moreover, our analysis reveals distinct safety patterns across different benchmarks: significant safety degradation is observed across jailbreak robustness benchmarks, whereas safety-awareness benchmarks demonstrate less pronounced degradation. In particular, the long thought process in some scenarios even enhances safety performance. Therefore, it is a potential approach to address safety issues in MLRMs by leveraging the intrinsic reasoning capabilities of the model to detect unsafe intent. To operationalize this insight, we construct a multimodal tuning dataset that incorporates a safety-oriented thought process. Experimental results from fine-tuning existing MLRMs with this dataset effectively enhances the safety on both jailbreak robustness and safety-awareness benchmarks. This study provides a new perspective for developing safe MLRMs. Our dataset is available at https://github.com/xinyuelou/Think-in-Safety.

cs.CL↗

arXiv2025

Meta-Reinforcement Learning Optimization for Movable Antenna-aided Full-Duplex CF-DFRC Systems with Carrier Frequency Offset

By enabling spectrum sharing between radar and communication operations, the cell-free dual-functional radar-communication (CF-DFRC) system is a promising candidate to significantly improve spectrum efficiency in future sixth-generation (6G) wireless networks. However, in wideband scenarios, synchronization errors caused by carrier frequency offset (CFO) can severely reduce both communication capacity and sensing accuracy. To address this challenge, this paper integrates movable antennas (MAs) into the CF-DFRC framework, leveraging their spatial flexibility and adaptive beamforming to dynamically mitigate CFO-induced impairments. To fully exploit the advantages of MAs in wideband scenarios with CFO, we aim to maximize the worst-case sum-rate of communication and sensing by jointly optimizing MA positions, {beamforming}, and CFO parameters, subject to transmit power and MA positioning constraints. Due to the non-convex nature of the problem, we propose a robust meta reinforcement learning (MRL)-based two-stage alternating optimization strategy. In the first stage, we employ manifold optimization (MO) with penalty dual decomposition (PDD) to solve the CFO-robust worst-case subproblem. In the second stage, we adopt to jointly optimize {the MA positions and beamforming vectors} in a data-driven manner {for dynamic wireless environments}. Simulation results show that the proposed MRL approach significantly outperforms conventional deep reinforcement learning (DRL) schemes in both communication and sensing performance under CFO impairments. Furthermore, compared to fixed-position antennas (FPAs), the MA-aided CF-DFRC system exhibits

eess.SP↗

arXiv2025

Noise Fusion-based Distillation Learning for Anomaly Detection in Complex Industrial Environments

Anomaly detection and localization in automated industrial manufacturing can significantly enhance production efficiency and product quality. Existing methods are capable of detecting surface defects in pre-defined or controlled imaging environments. However, accurately detecting workpiece defects in complex and unstructured industrial environments with varying views, poses and illumination remains challenging. We propose a novel anomaly detection and localization method specifically designed to handle inputs with perturbative patterns. Our approach introduces a new framework based on a collaborative distillation heterogeneous teacher network (HetNet), an adaptive local-global feature fusion module, and a local multivariate Gaussian noise generation module. HetNet can learn to model the complex feature distribution of normal patterns using limited information about local disruptive changes. We conducted extensive experiments on mainstream benchmarks. HetNet demonstrates superior performance with approximately 10% improvement across all evaluation metrics on MSC-AD under industrial conditions, while achieving state-of-the-art results on other datasets, validating its resilience to environmental fluctuations and its capability to enhance the reliability of industrial anomaly detection systems across diverse scenarios. Tests in real-world environments further confirm that HetNet can be effectively integrated into production lines to achieve robust and real-time anomaly detection. Codes, images and videos are published on the project website at: https://zihuatanejoyu.github.io/HetNet/

cs.RO↗

arXiv2025

MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesis

We introduce the Multi-Instance Generation (MIG) task, which focuses on generating multiple instances within a single image, each accurately placed at predefined positions with attributes such as category, color, and shape, strictly following user specifications. MIG faces three main challenges: avoiding attribute leakage between instances, supporting diverse instance descriptions, and maintaining consistency in iterative generation. To address attribute leakage, we propose the Multi-Instance Generation Controller (MIGC). MIGC generates multiple instances through a divide-and-conquer strategy, breaking down multi-instance shading into single-instance tasks with singular attributes, later integrated. To provide more types of instance descriptions, we developed MIGC++. MIGC++ allows attribute control through text \& images and position control through boxes \& masks. Lastly, we introduced the Consistent-MIG algorithm to enhance the iterative MIG ability of MIGC and MIGC++. This algorithm ensures consistency in unmodified regions during the addition, deletion, or modification of instances, and preserves the identity of instances when their attributes are changed. We introduce the COCO-MIG and Multimodal-MIG benchmarks to evaluate these methods. Extensive experiments on these benchmarks, along with the COCO-Position benchmark and DrawBench, demonstrate that our methods substantially outperform existing techniques, maintaining precise control over aspects including position, attribute, and quantity. Project page: https://github.com/limuloo/MIGC.

cs.CV↗

arXiv2025

HSS-IAD: A Heterogeneous Same-Sort Industrial Anomaly Detection Dataset

Multi-class Unsupervised Anomaly Detection algorithms (MUAD) are receiving increasing attention due to their relatively low deployment costs and improved training efficiency. However, the real-world effectiveness of MUAD methods is questioned due to limitations in current Industrial Anomaly Detection (IAD) datasets. These datasets contain numerous classes that are unlikely to be produced by the same factory and fail to cover multiple structures or appearances. Additionally, the defects do not reflect real-world characteristics. Therefore, we introduce the Heterogeneous Same-Sort Industrial Anomaly Detection (HSS-IAD) dataset, which contains 8,580 images of metallic-like industrial parts and precise anomaly annotations. These parts exhibit variations in structure and appearance, with subtle defects that closely resemble the base materials. We also provide foreground images for synthetic anomaly generation. Finally, we evaluate popular IAD methods on this dataset under multi-class and class-separated settings, demonstrating its potential to bridge the gap between existing datasets and real factory conditions. The dataset is available at https://github.com/Qiqigeww/HSS-IAD-Dataset.

cs.CV↗

arXiv2025

OmniGeo: Towards a Multimodal Large Language Models for Geospatial Artificial Intelligence

The rapid advancement of multimodal large language models (LLMs) has opened new frontiers in artificial intelligence, enabling the integration of diverse large-scale data types such as text, images, and spatial information. In this paper, we explore the potential of multimodal LLMs (MLLM) for geospatial artificial intelligence (GeoAI), a field that leverages spatial data to address challenges in domains including Geospatial Semantics, Health Geography, Urban Geography, Urban Perception, and Remote Sensing. We propose a MLLM (OmniGeo) tailored to geospatial applications, capable of processing and analyzing heterogeneous data sources, including satellite imagery, geospatial metadata, and textual descriptions. By combining the strengths of natural language understanding and spatial reasoning, our model enhances the ability of instruction following and the accuracy of GeoAI systems. Results demonstrate that our model outperforms task-specific models and existing LLMs on diverse geospatial tasks, effectively addressing the multimodality nature while achieving competitive results on the zero-shot geospatial tasks. Our code will be released after publication.

cs.AI↗

arXiv2025

Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models

The recent advancement of Multimodal Large Language Models (MLLMs) has significantly improved their fine-grained perception of single images and general comprehension across multiple images. However, existing MLLMs still face challenges in achieving precise grounding in complex multi-image scenarios. To address this, we first explore a Chain-of-Thought (CoT) framework that integrates single-image grounding with multi-image comprehension. While partially effective, it remains unstable and struggles to capture abstract visual information due to its non-end-to-end nature. Therefore, we introduce Migician, the first multi-image grounding model capable of performing free-form and accurate grounding across multiple images. To support this, we present the MGrounding-630k dataset, which comprises data for several multi-image grounding tasks derived from existing datasets, along with newly generated free-form grounding instruction-following data. Furthermore, we propose MIG-Bench, a comprehensive benchmark specifically designed for evaluating multi-image grounding capabilities. Experimental results demonstrate that our model achieves significantly superior multi-image grounding capabilities, outperforming the best existing MLLMs by 24.94% and even surpassing much larger 70B models. Our code, model, dataset, and benchmark are fully open-sourced at https://migician-vg.github.io/.

cs.CL↗

arXiv2025

A Survey on Large Language Models with Multilingualism: Recent Advances and New Frontiers

The rapid development of Large Language Models (LLMs) demonstrates remarkable multilingual capabilities in natural language processing, attracting global attention in both academia and industry. To mitigate potential discrimination and enhance the overall usability and accessibility for diverse language user groups, it is important for the development of language-fair technology. Despite the breakthroughs of LLMs, the investigation into the multilingual scenario remains insufficient, where a comprehensive survey to summarize recent approaches, developments, limitations, and potential solutions is desirable. To this end, we provide a survey with multiple perspectives on the utilization of LLMs in the multilingual scenario. We first rethink the transitions between previous and current research on pre-trained language models. Then we introduce several perspectives on the multilingualism of LLMs, including training and inference methods, information retrieval, model security, multi-domain with language culture, and usage of datasets. We also discuss the major challenges that arise in these aspects, along with possible solutions. Besides, we highlight future research directions that aim at further enhancing LLMs with multilingualism. The survey aims to help the research community address multilingual problems and provide a comprehensive understanding of the core concepts, key techniques, and latest developments in multilingual natural language processing based on LLMs.

cs.CL↗

arXiv2024

AI-Enabled Rapid Assembly of Thousands of Defect-Free Neutral Atom Arrays with Constant-time-overhead

Assembling increasingly larger-scale defect-free optical tweezer-trapped atom arrays is essential for quantum computation and quantum simulations based on atoms. Here, we propose an AI-enabled, rapid, constant-time-overhead rearrangement protocol, and we experimentally assemble defect-free 2D and 3D atom arrays with up to 2024 atoms with a constant time cost of 60 ms. The AI model calculates the holograms for real-time atom rearrangement. With precise controls over both position and phase, a high-speed spatial light modulator moves all the atoms simultaneously. This protocol can be readily used to generate defect-free arrays of tens of thousands of atoms with current technologies, and become a useful toolbox for quantum error correction.

quant-ph↗

arXiv2024

A Real-time Degeneracy Sensing and Compensation Method for Enhanced LiDAR SLAM

LiDAR is widely used in Simultaneous Localization and Mapping (SLAM) and autonomous driving. The LiDAR odometry is of great importance in multi-sensor fusion. However, in some unstructured environments, the point cloud registration cannot constrain the poses of the LiDAR due to its sparse geometric features, which leads to the degeneracy of multi-sensor fusion accuracy. To address this problem, we propose a novel real-time approach to sense and compensate for the degeneracy of LiDAR. Firstly, this paper introduces the degeneracy factor with clear meaning, which can measure the degeneracy of LiDAR. Then, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering method adaptively perceives the degeneracy with better environmental generalization. Finally, the degeneracy perception results are utilized to fuse LiDAR and IMU, thus effectively resisting degeneracy effects. Experiments on our dataset show the method's high accuracy and robustness and validate our algorithm's adaptability to different environments and LiDAR scanning modalities.

cs.RO↗

arXiv2024

AnySynth: Harnessing the Power of Image Synthetic Data Generation for Generalized Vision-Language Tasks

Diffusion models have recently been employed to generate high-quality images, reducing the need for manual data collection and improving model generalization in tasks such as object detection, instance segmentation, and image perception. However, the synthetic framework is usually designed with meticulous human effort for each task due to various requirements on image layout, content, and annotation formats, restricting the application of synthetic data on more general scenarios. In this paper, we propose AnySynth, a unified framework integrating adaptable, comprehensive, and highly controllable components capable of generating an arbitrary type of synthetic data given diverse requirements. Specifically, the Task-Specific Layout Generation Module is first introduced to produce reasonable layouts for different tasks by leveraging the generation ability of large language models and layout priors of real-world images. A Uni-Controlled Image Generation Module is then developed to create high-quality synthetic images that are controllable and based on the generated layouts. In addition, user specific reference images, and style images can be incorporated into the generation to task requirements. Finally, the Task-Oriented Annotation Module offers precise and detailed annotations for the generated images across different tasks. We have validated our framework's performance across various tasks, including Few-shot Object Detection, Cross-domain Object Detection, Zero-shot Composed Image Retrieval, and Multi-modal Image Perception and Grounding. The specific data synthesized by our framework significantly improves model performance in these tasks, demonstrating the generality and effectiveness of our framework.

cs.CV↗