Kexin Li

Kexin Li, Zongxin Yang, Lei Chen et al.

Audio-visual video segmentation~(AVVS) aims to generate pixel-level maps of sound-producing objects within image frames and ensure the maps faithfully adhere to the given audio, such as identifying and segmenting a singing person in a video. However, existing methods exhibit two limitations: 1) they address video temporal features and audio-visual interactive features separately, disregarding the inherent spatial-temporal dependence of combined audio and video, and 2) they inadequately introduce audio constraints and object-level information during the decoding stage, resulting in segmentation outcomes that fail to comply with audio directives. To tackle these issues, we propose a decoupled audio-video transformer that combines audio and video features from their respective temporal and spatial dimensions, capturing their combined dependence. To optimize memory consumption, we design a block, which, when stacked, enables capturing audio-visual fine-grained combinatorial-dependence in a memory-efficient manner. Additionally, we introduce audio-constrained queries during the decoding phase. These queries contain rich object-level information, ensuring the decoded mask adheres to the sounds. Experimental results confirm our approach's effectiveness, with our framework achieving a new SOTA performance on all three datasets using two backbones. The code is available at \url{https://github.com/aspirinone/CATR.github.io}

Yuxuan Wang, Yijun Liu, Fei Yu et al.

Despite the rapid development of Chinese vision-language models (VLMs), most existing Chinese vision-language (VL) datasets are constructed on Western-centric images from existing English VL datasets. The cultural bias in the images makes these datasets unsuitable for evaluating VLMs in Chinese culture. To remedy this issue, we present a new Chinese Vision- Language Understanding Evaluation (CVLUE) benchmark dataset, where the selection of object categories and images is entirely driven by Chinese native speakers, ensuring that the source images are representative of Chinese culture. The benchmark contains four distinct VL tasks ranging from image-text retrieval to visual question answering, visual grounding and visual dialogue. We present a detailed statistical analysis of CVLUE and provide a baseline performance analysis with several open-source multilingual VLMs on CVLUE and its English counterparts to reveal their performance gap between English and Chinese. Our in-depth category-level analysis reveals a lack of Chinese cultural knowledge in existing VLMs. We also find that fine-tuning on Chinese culture-related VL datasets effectively enhances VLMs' understanding of Chinese culture.

Thomas J McKenna, Ingvill Rasmussen, Sten Ludvigsen et al.

Educational dialogue -- the collaborative exchange of ideas through talk -- is widely recognized as a catalyst for deeper learning and critical thinking in and across contexts. At the same time, artificial intelligence (AI) has rapidly emerged as a powerful force in education, with the potential to address major challenges, personalize learning, and innovate teaching practices. However, these advances come with significant risks: rapid AI development can undermine human agency, exacerbate inequities, and outpace our capacity to guide its use with sound policy. Human learning presupposes cognitive efforts and social interaction (dialogues). In response to this evolving landscape, an international workshop titled "Educational Dialogue: Moving Thinking Forward" convened 19 leading researchers from 11 countries in Cambridge (September 1-3, 2025) to examine the intersection of AI and educational dialogue. This AI-focused strand of the workshop centered on three critical questions: (1) When is AI truly useful in education, and when might it merely replace human effort at the expense of learning? (2) Under what conditions can AI use lead to better dialogic teaching and learning? (3) Does the AI-human partnership risk outpacing and displacing human educational work, and what are the implications? These questions framed two days of presentations and structured dialogue among participants.

Yicheng Rui, Xiao-Wei Duan, Licai Deng et al.

Ground-based time-domain observatories require minute-by-minute, site-scale awareness of cloud cover, yet existing all-sky datasets are short, daylight-biased, or lack astrometric calibration. We present LenghuSky-8, an eight-year (2018-2025) all-sky imaging dataset from a premier astronomical site, comprising 429,620 $512 \times 512$ frames with 81.2% night-time coverage, star-aware cloud masks, background masks, and per-pixel altitude-azimuth (Alt-Az) calibration. For robust cloud segmentation across day, night, and lunar phases, we train a linear probe on DINOv3 local features and obtain 93.3% $\pm$ 1.1% overall accuracy on a balanced, manually labeled set of 1,111 images. Using stellar astrometry, we map each pixel to local alt-az coordinates and measure calibration uncertainties of approximately 0.37 deg at zenith and approximately 1.34 deg at 30 deg altitude, sufficient for integration with telescope schedulers. Beyond segmentation, we introduce a short-horizon nowcasting benchmark over per-pixel three-class logits (sky/cloud/contamination) with four baselines: persistence (copying the last frame), optical flow, ConvLSTM, and VideoGPT. ConvLSTM performs best but yields only limited gains over persistence, underscoring the difficulty of near-term cloud evolution. We release the dataset, calibrations, and an open-source toolkit for loading, evaluation, and scheduler-ready alt-az maps to boost research in segmentation, nowcasting, and autonomous observatory operations.

Jun Li, Kexin Li, Yafeng Zhou et al.

Targeted diagnosis and treatment plans for patients with coronary artery disease vary according to atherosclerotic plaque component. Coronary CT angiography (CCTA) is widely used for artery imaging and determining the stenosis degree. However, the limited spatial resolution and susceptibility to artifacts fail CCTA in obtaining lumen morphological characteristics and plaque composition. It can be settled by invasive optical coherence tomography (OCT) without much trouble for physicians, but bringing higher costs and potential risks to patients. Therefore, it is clinically critical to introduce annotations of plaque tissue and lumen characteristics from OCT to paired CCTA scans, denoted as \textbf{the O2CTA problem} in this paper. We propose a method to handle the O2CTA problem. CCTA scans are first reconstructed into multi-planar reformatted (MPR) images, which agree with OCT images in term of semantic contents. The artery segment in OCT, which is manually labelled, is then spatially aligned with the entire artery in MPR images via the proposed alignment strategy. Finally, a classification model involving a 3D CNN and a Transformer, is learned to extract local features and capture dependence along arteries. Experiments on 55 paired OCT and CCTA we curate demonstrate that it is feasible to classify the CCTA based on the OCT labels, with an accuracy of 86.2%, while the manual readings of OCT and CCTA vary significantly, with a Kappa coefficient of 0.113. We will make our source codes, models, data, and results publicly available to benefit the research community.

Mengkang Hu, Bowei Xia, Yuran Wu et al.

Symbolic world models (e.g., PDDL domains or executable simulators) are central to model-based planning, but training LLMs to generate such world models is limited by the lack of large-scale verifiable supervision. Current approaches rely primarily on static validation methods that fail to catch behavior-level errors arising from interactive execution. In this paper, we propose Agent2World, a tool-augmented multi-agent framework that achieves strong inference-time world-model generation and also serves as a data engine for supervised fine-tuning, by grounding generation in multi-agent feedback. Agent2World follows a three-stage pipeline: (i) A Deep Researcher agent performs knowledge synthesis by web searching to address specification gaps; (ii) A Model Developer agent implements executable world models; And (iii) a specialized Testing Team conducts adaptive unit testing and simulation-based validation. Agent2World demonstrates superior inference-time performance across three benchmarks spanning both Planning Domain Definition Language (PDDL) and executable code representations, achieving consistent state-of-the-art results. Beyond inference, Testing Team serves as an interactive environment for the Model Developer, providing behavior-aware adaptive feedback that yields multi-turn training trajectories. The model fine-tuned on these trajectories substantially improves world-model generation, yielding an average relative gain of 30.95% over the same model before training. Project page: https://agent2world.github.io.

Binhe Yu, Zhen Wang, Kexin Li et al.

Multi-subject customization aims to synthesize multiple user-specified subjects into a coherent image. To address issues such as subjects missing or conflicts, recent works incorporate layout guidance to provide explicit spatial constraints. However, existing methods still struggle to balance three critical objectives: text alignment, subject identity preservation, and layout control, while the reliance on additional training further limits their scalability and efficiency. In this paper, we present AnyMS, a novel training-free framework for layout-guided multi-subject customization. AnyMS leverages three input conditions: text prompt, subject images, and layout constraints, and introduces a bottom-up dual-level attention decoupling mechanism to harmonize their integration during generation. Specifically, global decoupling separates cross-attention between textual and visual conditions to ensure text alignment. Local decoupling confines each subject's attention to its designated area, which prevents subject conflicts and thus guarantees identity preservation and layout control. Moreover, AnyMS employs pre-trained image adapters to extract subject-specific features aligned with the diffusion model, removing the need for subject learning or adapter tuning. Extensive experiments demonstrate that AnyMS achieves state-of-the-art performance, supporting complex compositions and scaling to a larger number of subjects.

Kexin Li, Xiao Hu, Ilya Grishchenko et al.

The availability of high-quality, AI-generated audio raises security challenges such as misinformation campaigns and voice-cloning fraud. A key defense against the misuse of AI-generated audio is by watermarking it, so that it can be easily distinguished from genuine audio. As those seeking to misuse AI-generated audio may thus seek to remove audio watermarks, studying effective watermark removal techniques is critical to being able to objectively evaluate the robustness of audio watermarks against removal. Previous watermark removal schemes either assume impractical knowledge of the watermarks they are designed to remove or are computationally expensive, potentially generating a false sense of confidence in current watermark schemes. We introduce HarmonicAttack, an efficient audio watermark removal method that only requires the basic ability to generate the watermarks from the targeted scheme and nothing else. With this, we are able to train a general watermark removal model that is able to remove the watermarks generated by the targeted scheme from any watermarked audio sample. HarmonicAttack employs a dual-path convolutional autoencoder that operates in both temporal and frequency domains, along with GAN-style training, to separate the watermark from the original audio. When evaluated against state-of-the-art watermark schemes AudioSeal, WavMark, and Silentcipher, HarmonicAttack demonstrates greater watermark removal ability than previous watermark removal methods with near real-time performance. Moreover, while HarmonicAttack requires training, we find that it is able to transfer to out-of-distribution samples with minimal degradation in performance.

Gefan Ye, Lin Li, Kexin Li et al.

Zero-shot compositional action recognition (ZS-CAR) aims to identify unseen verb-object compositions in the videos by exploiting the learned knowledge of verb and object primitives during training. Despite compositional learning's progress in ZS-CAR, two critical challenges persist: 1) Missing compositional structure constraint, leading to spurious correlations between primitives; 2) Neglecting semantic hierarchy constraint, leading to semantic ambiguity and impairing the training process. In this paper, we argue that human-like symbolic reasoning offers a principled solution to these challenges by explicitly modeling compositional and hierarchical structured abstraction. To this end, we propose a logic-driven ZS-CAR framework LogicCAR that integrates dual symbolic constraints: Explicit Compositional Logic and Hierarchical Primitive Logic. Specifically, the former models the restrictions within the compositions, enhancing the compositional reasoning ability of our model. The latter investigates the semantical dependencies among different primitives, empowering the models with fine-to-coarse reasoning capacity. By formalizing these constraints in first-order logic and embedding them into neural network architectures, LogicCAR systematically bridges the gap between symbolic abstraction and existing models. Extensive experiments on the Sth-com dataset demonstrate that our LogicCAR outperforms existing baseline methods, proving the effectiveness of our logic-driven constraints.

Kexin Li, Zongxin Yang, Yi Yang et al.

Audio-visual video segmentation (AVVS) aims to generate pixel-level maps of sound-producing objects that accurately align with the corresponding audio. However, existing methods often face temporal misalignment, where audio cues and segmentation results are not temporally coordinated. Audio provides two critical pieces of information: i) target object-level details and ii) the timing of when objects start and stop producing sounds. Current methods focus more on object-level information but neglect the boundaries of audio semantic changes, leading to temporal misalignment. To address this issue, we propose a Collaborative Hybrid Propagator Framework~(Co-Prop). This framework includes two main steps: Preliminary Audio Boundary Anchoring and Frame-by-Frame Audio-Insert Propagation. To Anchor the audio boundary, we employ retrieval-assist prompts with Qwen large language models to identify control points of audio semantic changes. These control points split the audio into semantically consistent audio portions. After obtaining the control point lists, we propose the Audio Insertion Propagator to process each audio portion using a frame-by-frame audio insertion propagation and matching approach. We curated a compact dataset comprising diverse source conversion cases and devised a metric to assess alignment rates. Compared to traditional simultaneous processing methods, our approach reduces memory requirements and facilitates frame alignment. Experimental results demonstrate the effectiveness of our approach across three datasets and two backbones. Furthermore, our method can be integrated with existing AVVS approaches, offering plug-and-play functionality to enhance their performance.

Kexin Li, Tao Jiang, Zongxin Yang et al.

Interactive Video Object Segmentation (iVOS) is a challenging task that requires real-time human-computer interaction. To improve the user experience, it is important to consider the user's input habits, segmentation quality, running time and memory consumption.However, existing methods compromise user experience with single input mode and slow running speed. Specifically, these methods only allow the user to interact with one single frame, which limits the expression of the user's intent.To overcome these limitations and better align with people's usage habits, we propose a framework that can accept multiple frames simultaneously and explore synergistic interaction across frames (SIAF). Concretely, we designed the Across-Frame Interaction Module that enables users to annotate different objects freely on multiple frames. The AFI module will migrate scribble information among multiple interactive frames and generate multi-frame masks. Additionally, we employ the id-queried mechanism to process multiple objects in batches. Furthermore, for a more efficient propagation and lightweight model, we design a truncated re-propagation strategy to replace the previous multi-round fusion module, which employs an across-round memory that stores important interaction information. Our SwinB-SIAF achieves new state-of-the-art performance on DAVIS 2017 (89.6%, J&F@60). Moreover, our R50-SIAF is more than 3 faster than the state-of-the-art competitor under challenging multi-object scenarios.

Kexin Li, You-wei Wen, Xu Xiao et al.

Robust Principal Component Analysis (RPCA) is a fundamental technique for decomposing data into low-rank and sparse components, which plays a critical role for applications such as image processing and anomaly detection. Traditional RPCA methods commonly use $\ell_1$ norm regularization to enforce sparsity, but this approach can introduce bias and result in suboptimal estimates, particularly in the presence of significant noise or outliers. Non-convex regularization methods have been proposed to mitigate these challenges, but they tend to be complex to optimize and sensitive to initial conditions, leading to potential instability in solutions. To overcome these challenges, in this paper, we propose a novel RPCA model that integrates adaptive weighted least squares (AWLS) and low-rank matrix factorization (LRMF). The model employs a {self-attention-inspired} mechanism in its weight update process, allowing the weight matrix to dynamically adjust and emphasize significant components during each iteration. By employing a weighted F-norm for the sparse component, our method effectively reduces bias while simplifying the computational process compared to traditional $\ell_1$-norm-based methods. We use an alternating minimization algorithm, where each subproblem has an explicit solution, thereby improving computational efficiency. Despite its simplicity, numerical experiments demonstrate that our method outperforms existing non-convex regularization approaches, offering superior performance and stability, as well as enhanced accuracy and robustness in practical applications.

Kexin Li, Guozhen Ding, Ilya Grishchenko et al.

Modern generative diffusion models rely on vast training datasets, often including images with uncertain ownership or usage rights. Radioactive watermarks -- marks that transfer to a model's outputs -- can help detect when such unauthorized data has been used for training. Moreover, aside from being radioactive, an effective watermark for protecting images from unauthorized training also needs to meet other existing requirements, such as imperceptibility, robustness, and multi-bit capacity. To overcome these challenges, we propose HMARK, a novel multi-bit watermarking scheme, which encodes ownership information as secret bits in the semantic-latent space (h-space) for image diffusion models. By leveraging the interpretability and semantic significance of h-space, ensuring that watermark signals correspond to meaningful semantic attributes, the watermarks embedded by HMARK exhibit radioactivity, robustness to distortions, and minimal impact on perceptual quality. Experimental results demonstrate that HMARK achieves 98.57% watermark detection accuracy, 95.07% bit-level recovery accuracy, 100% recall rate, and 1.0 AUC on images produced by the downstream adversarial model finetuned with LoRA on watermarked data across various types of distortions.

Kexin Li, Mandar Chitre

Accurate modeling of time-varying underwater acoustic channels is essential for the design, evaluation, and deployment of reliable underwater communication systems. Conventional physics models require detailed environmental knowledge, while stochastic replay methods are constrained by the limited diversity of measured channels and often fail to generalize to unseen scenarios, reducing their practical applicability. To address these challenges, we propose StableUASim, a pre-trained conditional latent diffusion surrogate model that captures the stochastic dynamics of underwater acoustic communication channels. Leveraging generative modeling, StableUASim produces diverse and statistically realistic channel realizations, while supporting conditional generation from specific measurement samples. Pre-training enables rapid adaptation to new environments using minimal additional data, and the autoencoder latent representation facilitates efficient channel analysis and compression. Experimental results demonstrate that StableUASim accurately reproduces key channel characteristics and communication performance, providing a scalable, data-efficient, and physically consistent surrogate model for both system design and machine learning-driven underwater applications.

Youcan Xu, Zhen Wang, Jiaxin Shi et al.

While recent text-to-video models excel at generating diverse scenes, they struggle with precise motion control, particularly for complex, multi-subject motions. Although methods for single-motion customization have been developed to address this gap, they fail in compositional scenarios due to two primary challenges: motion-appearance entanglement and ineffective multi-motion blending. This paper introduces CoMo, a novel framework for $\textbf{compositional motion customization}$ in text-to-video generation, enabling the synthesis of multiple, distinct motions within a single video. CoMo addresses these issues through a two-phase approach. First, in the single-motion learning phase, a static-dynamic decoupled tuning paradigm disentangles motion from appearance to learn a motion-specific module. Second, in the multi-motion composition phase, a plug-and-play divide-and-merge strategy composes these learned motions without additional training by spatially isolating their influence during the denoising process. To facilitate research in this new domain, we also introduce a new benchmark and a novel evaluation metric designed to assess multi-motion fidelity and blending. Extensive experiments demonstrate that CoMo achieves state-of-the-art performance, significantly advancing the capabilities of controllable video generation. Our project page is at https://como6.github.io/.

Yangyang Xu, Kexin Li, Li Yang et al.

Tensor Robust Principal Component Analysis (TRPCA) is a fundamental technique for decomposing multi-dimensional data into a low-rank tensor and an outlier tensor, yet existing methods relying on sparse outlier assumptions often fail under structured corruptions. In this paper, we propose a self-guided data augmentation approach that employs adaptive weighting to suppress outlier influence, reformulating the original TRPCA problem into a standard Tensor Principal Component Analysis (TPCA) problem. The proposed model involves an optimization-driven weighting scheme that dynamically identifies and downweights outlier contributions during tensor augmentation. We develop an efficient proximal block coordinate descent algorithm with closed-form updates to solve the resulting optimization problem, ensuring computational efficiency. Theoretical convergence is guaranteed through a framework combining block coordinate descent with majorization-minimization principles. Numerical experiments on synthetic and real-world datasets, including face recovery, background subtraction, and hyperspectral denoising, demonstrate that our method effectively handles various corruption patterns. The results show the improvements in both accuracy and computational efficiency compared to state-of-the-art methods.

Kexin Li, Luwei Bai, Xiao Wang et al.

Anderson acceleration is an effective technique for enhancing the efficiency of fixed-point iterations; however, analyzing its convergence in nonsmooth settings presents significant challenges. In this paper, we investigate a class of nonsmooth optimization algorithms characterized by the active manifold identification property. This class includes a diverse array of methods such as the proximal point method, proximal gradient method, proximal linear method, proximal coordinate descent method, Douglas-Rachford splitting (or the alternating direction method of multipliers), and the iteratively reweighted $\ell_1$ method, among others. Under the assumption that the optimization problem possesses an active manifold at a stationary point, we establish a local R-linear convergence rate for the Anderson-accelerated algorithm. Our extensive numerical experiments further highlight the robust performance of the proposed Anderson-accelerated methods.

Kexin Li

Iteratively reweighted L1 (IRL1) algorithm is a common algorithm for solving sparse optimization problems with nonconvex and nonsmooth regularization. The development of its acceleration algorithm, often employing Nesterov acceleration, has sparked significant interest. Nevertheless, the convergence and complexity analysis of these acceleration algorithms consistently poses substantial challenges. Recently, Anderson acceleration has gained prominence owing to its exceptional performance for speeding up fixed-point iteration, with numerous recent studies applying it to gradient-based algorithms. Motivated by the powerful impact of Anderson acceleration, we propose an Anderson-accelerated IRL1 algorithm and establish its local linear convergence rate. We extend this convergence result, typically observed in smooth settings, to a nonsmooth scenario. Importantly, our theoretical results do not depend on the Kurdyka-Lojasiewicz condition, a necessary condition in existing Nesterov acceleration-based algorithms. Furthermore, to ensure global convergence, we introduce a globally convergent Anderson accelerated IRL1 algorithm by incorporating a classical nonmonotone line search condition. Experimental results indicate that our algorithm outperforms existing Nesterov acceleration-based algorithms.