arXiv subjects

Bin Li

Publications and source records attributed to Bin Li.

At least 235 records · Page 13Linked to original sources

arXiv2025

ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images

Medical Visual Question Answering (Med-VQA) represents a critical and challenging subtask within the general VQA domain. Despite significant advancements in general VQA, multimodal large language models (MLLMs) still exhibit substantial limitations when handling multi-task VQA scenarios. These limitations manifest through erroneous spatial localization and misinterpretation of medical images, which primarily arise from two fundamental issues: inadequate image-text alignment and insufficient domain-specified knowledge for medical applications. To address these issues, we introduce the Cross-Modal Clinical Knowledge Distiller (ClinKD), an innovative framework designed to enhance image-text alignment and establish more effective medical knowledge transformation mechanisms, which enables MLLMs to perform better even when lacking prior medical knowledge. Our extensive experimental evaluations demonstrate that the ClinKD achieves state-of-the-art performance on several datasets which are challenging for Med-VQA task. The results indicate that our approach not only significantly improves image-text alignment but also effectively enables MLLMs to adapt to the medical knowledge. The source code for ClinKD is available at: https://github.com/overloadedHenry/ClinKD.

cs.CV↗

arXiv2025

UAV-Assisted Integrated Communication and Over-the-Air Computation with Interference Awareness

Over the air computation (AirComp) is a promising technique that addresses big data collection and fast wireless data aggregation. However, in a network where wireless communication and AirComp coexist, mutual interference becomes a critical challenge. In this paper, we propose to employ an unmanned aerial vehicle (UAV) to enable integrated communication and AirComp, where we capitalize on UAV mobility with alleviated interference for performance enhancement. Particularly, we aim to maximize the sum of user transmission rate with the guaranteed AirComp accuracy requirement, where we jointly optimize the transmission strategy, signal normalizing factor, scheduling strategy, and UAV trajectory. We decouple the formulated problem into two layers where the outer layer is for UAV trajectory and scheduling, and the inner layer is for transmission and computation. Then, we solve the inner layer problem through alternating optimization, and the outer layer is solved through soft actor critic based deep reinforcement learning. Simulation results show the convergence of the proposed learning process and also demonstrate the performance superiority of our proposal as compared with the baselines in various situations.

eess.SP↗

arXiv2025

Gradient Purification: Defense Against Poisoning Attack in Decentralized Federated Learning

Decentralized federated learning (DFL) is inherently vulnerable to data poisoning attacks, as malicious clients can transmit manipulated gradients to neighboring clients. Existing defense methods either reject suspicious gradients per iteration or restart DFL aggregation after excluding all malicious clients. They all neglect the potential benefits that may exist within contributions from malicious clients. In this paper, we propose a novel gradient purification defense, termed GPD, to defend against data poisoning attacks in DFL. It aims to separately mitigate the harm in gradients and retain benefits embedded in model weights, thereby enhancing overall model accuracy. For each benign client in GPD, a recording variable is designed to track historically aggregated gradients from one of its neighbors. It allows benign clients to precisely detect malicious neighbors and mitigate all aggregated malicious gradients at once. Upon mitigation, benign clients optimize model weights using purified gradients. This optimization not only retains previously beneficial components from malicious clients but also exploits canonical contributions from benign clients. We analyze the convergence of GPD, as well as its ability to harvest high accuracy. Extensive experiments demonstrate that, GPD is capable of mitigating data poisoning attacks under both iid and non-iid data distributions. It also significantly outperforms state-of-the-art defense methods in terms of model accuracy.

cs.LG↗

arXiv2025

M$^3$-Med: A Benchmark for Multi-lingual, Multi-modal, and Multi-hop Reasoning in Medical Instructional Video Understanding

With the rapid progress of artificial intelligence (AI) in multi-modal understanding, there is increasing potential for video comprehension technologies to support professional domains such as medical education. However, existing benchmarks suffer from two primary limitations: (1) Linguistic Singularity: they are largely confined to English, neglecting the need for multilingual resources; and (2) Shallow Reasoning: their questions are often designed for surface-level information retrieval, failing to properly assess deep multi-modal integration. To address these limitations, we present M3-Med, the first benchmark for Multi-lingual, Multi-modal, and Multi-hop reasoning in Medical instructional video understanding. M3-Med consists of medical questions paired with corresponding video segments, annotated by a team of medical experts. A key innovation of M3-Med is its multi-hop reasoning task, which requires a model to first locate a key entity in the text, then find corresponding visual evidence in the video, and finally synthesize information across both modalities to derive the answer. This design moves beyond simple text matching and poses a substantial challenge to a model's deep cross-modal understanding capabilities. We define two tasks: Temporal Answer Grounding in Single Video (TAGSV) and Temporal Answer Grounding in Video Corpus (TAGVC). We evaluated several state-of-the-art models and Large Language Models (LLMs) on M3-Med. The results reveal a significant performance gap between all models and human experts, especially on the complex multi-hop questions where model performance drops sharply. M3-Med effectively highlights the current limitations of AI models in deep cross-modal reasoning within specialized domains and provides a new direction for future research.

cs.CV↗

arXiv2025

CrowdTrack: A Benchmark for Difficult Multiple Pedestrian Tracking in Real Scenarios

Multi-object tracking is a classic field in computer vision. Among them, pedestrian tracking has extremely high application value and has become the most popular research category. Existing methods mainly use motion or appearance information for tracking, which is often difficult in complex scenarios. For the motion information, mutual occlusions between objects often prevent updating of the motion state; for the appearance information, non-robust results are often obtained due to reasons such as only partial visibility of the object or blurred images. Although learning how to perform tracking in these situations from the annotated data is the simplest solution, the existing MOT dataset fails to satisfy this solution. Existing methods mainly have two drawbacks: relatively simple scene composition and non-realistic scenarios. Although some of the video sequences in existing dataset do not have the above-mentioned drawbacks, the number is far from adequate for research purposes. To this end, we propose a difficult large-scale dataset for multi-pedestrian tracking, shot mainly from the first-person view and all from real-life complex scenarios. We name it ``CrowdTrack'' because there are numerous objects in most of the sequences. Our dataset consists of 33 videos, containing a total of 5,185 trajectories. Each object is annotated with a complete bounding box and a unique object ID. The dataset will provide a platform to facilitate the development of algorithms that remain effective in complex situations. We analyzed the dataset comprehensively and tested multiple SOTA models on our dataset. Besides, we analyzed the performance of the foundation models on our dataset. The dataset and project code is released at: https://github.com/loseevaya/CrowdTrack .

cs.CV↗

arXiv2025

A Glimpse of Satellite Galaxies in the Milky Way with the 2.5-meter Wide Field Survey Telescope (WFST): Bootes III and Draco

We carry out deep imaging of the Milky Way satellite galaxies, Bootes III and Draco, with WFST as one pilot observing program to demonstrate the capability of WFST. Combining catalogs with PS1 DR2 and Gaia DR3, we derive proper motions for candidate member stars in these two satellite galaxies over a 12-year time baseline, yielding uncertainties of ~1.8 mas/yr at 21 mag and ~3.0 mas/yr at 22 mag in the r band. The proper motions derived from bright and faint stars are consistent, indicating no significant variation in proper motion across stellar luminosity as these galaxies undergo tidal interactions with the MW. Meanwhile, we suggest that Bootes III represents the bound remnant of the progenitor galaxy that gave rise to the Styx stream, as evidenced by its elongated density profile and overdensity in both spatial and kinematic space. This is the first paper to use WFST to measure the proper motions of faint stars in Milky Way satellite galaxies. More detailed analyses will be presented in forthcoming papers from the wide field survey (WFS) program.

astro-ph.GA↗

arXiv2025

VesselSAM: Leveraging SAM for Aortic Vessel Segmentation with AtrousLoRA

Medical image segmentation is crucial for clinical diagnosis and treatment planning, especially when dealing with complex anatomical structures such as vessels. However, accurately segmenting vessels remains challenging due to their small size, intricate edge structures, and susceptibility to artifacts and imaging noise. In this work, we propose VesselSAM, an enhanced version of the Segment Anything Model (SAM), specifically tailored for aortic vessel segmentation. VesselSAM incorporates AtrousLoRA, a novel module integrating Atrous Attention and Low-Rank Adaptation (LoRA), to enhance segmentation performance. Atrous Attention enables the model to capture multi-scale contextual information, preserving both fine-grained local details and broader global context. Additionally, LoRA facilitates efficient fine-tuning of the frozen SAM image encoder, reducing the number of trainable parameters and thereby enhancing computational efficiency. We evaluate VesselSAM using two challenging datasets: the Aortic Vessel Tree (AVT) dataset and the Type-B Aortic Dissection (TBAD) dataset. VesselSAM achieves state-of-the-art performance, attaining DSC scores of 93.50\%, 93.25\%, 93.02\%, and 93.26\% across multi-center datasets. Our results demonstrate that VesselSAM delivers high segmentation accuracy while significantly reducing computational overhead compared to existing large-scale models. This development paves the way for enhanced AI-based aortic vessel segmentation in clinical environments. The code and models will be released at https://github.com/Adnan-CAS/AtrousLora.

eess.IV↗

arXiv2025

CoLa: Chinese Character Decomposition with Compositional Latent Components

Humans can decompose Chinese characters into compositional components and recombine them to recognize unseen characters. This reflects two cognitive principles: Compositionality, the idea that complex concepts are built on simpler parts; and Learning-to-learn, the ability to learn strategies for decomposing and recombining components to form new concepts. These principles provide inductive biases that support efficient generalization. They are critical to Chinese character recognition (CCR) in solving the zero-shot problem, which results from the common long-tail distribution of Chinese character datasets. Existing methods have made substantial progress in modeling compositionality via predefined radical or stroke decomposition. However, they often ignore the learning-to-learn capability, limiting their ability to generalize beyond human-defined schemes. Inspired by these principles, we propose a deep latent variable model that learns Compositional Latent components of Chinese characters (CoLa) without relying on human-defined decomposition schemes. Recognition and matching can be performed by comparing compositional latent components in the latent space, enabling zero-shot character recognition. The experiments illustrate that CoLa outperforms previous methods in both character the radical zero-shot CCR. Visualization indicates that the learned components can reflect the structure of characters in an interpretable way. Moreover, despite being trained on historical documents, CoLa can analyze components of oracle bone characters, highlighting its cross-dataset generalization ability.

cs.CV↗

arXiv2025

Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image Detection

Current AIGC detectors often achieve near-perfect accuracy on images produced by the same generator used for training but struggle to generalize to outputs from unseen generators. We trace this failure in part to latent prior bias: detectors learn shortcuts tied to patterns stemming from the initial noise vector rather than learning robust generative artifacts. To address this, we propose On-Manifold Adversarial Training (OMAT): by optimizing the initial latent noise of diffusion models under fixed conditioning, we generate on-manifold adversarial examples that remain on the generator's output manifold-unlike pixel-space attacks, which introduce off-manifold perturbations that the generator itself cannot reproduce and that can obscure the true discriminative artifacts. To test against state-of-the-art generative models, we introduce GenImage++, a test-only benchmark of outputs from advanced generators (Flux.1, SD3) with extended prompts and diverse styles. We apply our adversarial-training paradigm to ResNet50 and CLIP baselines and evaluate across existing AIGC forensic benchmarks and recent challenge datasets. Extensive experiments show that adversarially trained detectors significantly improve cross-generator performance without any network redesign. Our findings on latent-prior bias offer valuable insights for future dataset construction and detector evaluation, guiding the development of more robust and generalizable AIGC forensic methodologies.

cs.CV↗

arXiv2025

ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models

Person re-identification (Re-ID) is a crucial task in computer vision, aiming to recognize individuals across non-overlapping camera views. While recent advanced vision-language models (VLMs) excel in logical reasoning and multi-task generalization, their applications in Re-ID tasks remain limited. They either struggle to perform accurate matching based on identity-relevant features or assist image-dominated branches as auxiliary semantics. In this paper, we propose a novel framework ChatReID, that shifts the focus towards a text-side-dominated retrieval paradigm, enabling flexible and interactive re-identification. To integrate the reasoning abilities of language models into Re-ID pipelines, We first present a large-scale instruction dataset, which contains more than 8 million prompts to promote the model fine-tuning. Next. we introduce a hierarchical progressive tuning strategy, which endows Re-ID ability through three stages of tuning, i.e., from person attribute understanding to fine-grained image retrieval and to multi-modal task reasoning. Extensive experiments across ten popular benchmarks demonstrate that ChatReID outperforms existing methods, achieving state-of-the-art performance in all Re-ID tasks. More experiments demonstrate that ChatReID not only has the ability to recognize fine-grained details but also to integrate them into a coherent reasoning process.

cs.CV↗

arXiv2025

PHT-CAD: Efficient CAD Parametric Primitive Analysis with Progressive Hierarchical Tuning

Computer-Aided Design (CAD) plays a pivotal role in industrial manufacturing, yet 2D Parametric Primitive Analysis (PPA) remains underexplored due to two key challenges: structural constraint reasoning and advanced semantic understanding. To tackle these challenges, we first propose an Efficient Hybrid Parametrization (EHP) for better representing 2D engineering drawings. EHP contains four types of atomic component i.e., point, line, circle, and arc). Additionally, we propose PHT-CAD, a novel 2D PPA framework that harnesses the modality alignment and reasoning capabilities of Vision-Language Models (VLMs) for precise engineering drawing analysis. In PHT-CAD, we introduce four dedicated regression heads to predict corresponding atomic components. To train PHT-CAD, a three-stage training paradigm Progressive Hierarchical Tuning (PHT) is proposed to progressively enhance PHT-CAD's capability to perceive individual primitives, infer structural constraints, and align annotation layers with their corresponding geometric representations. Considering that existing datasets lack complete annotation layers and real-world engineering drawings, we introduce ParaCAD, the first large-scale benchmark that explicitly integrates both the geometric and annotation layers. ParaCAD comprises over 10 million annotated drawings for training and 3,000 real-world industrial drawings with complex topological structures and physical constraints for test. Extensive experiments demonstrate the effectiveness of PHT-CAD and highlight the practical significance of ParaCAD in advancing 2D PPA research.

cs.CV↗

arXiv2025

Zero-Shot Chinese Character Recognition with Hierarchical Multi-Granularity Image-Text Aligning

Chinese Character Recognition (CCR) is a fundamental technology for intelligent document processing. Unlike Latin characters, Chinese characters exhibit unique spatial structures and compositional rules, allowing for the use of fine-grained semantic information in representation. However, existing approaches are usually based on auto-regressive as well as edit distance post-process and typically rely on a single-level character representation. In this paper, we propose a Hierarchical Multi-Granularity Image-Text Aligning (Hi-GITA) framework based on a contrastive paradigm. To leverage the abundant fine-grained semantic information of Chinese characters, we propose multi-granularity encoders on both image and text sides. Specifically, the Image Multi-Granularity Encoder extracts hierarchical image representations from character images, capturing semantic cues from localized strokes to holistic structures. The Text Multi-Granularity Encoder extracts stroke and radical sequence representations at different levels of granularity. To better capture the relationships between strokes and radicals, we introduce Multi-Granularity Fusion Modules on the image and text sides, respectively. Furthermore, to effectively bridge the two modalities, we further introduce a Fine-Grained Decoupled Image-Text Contrastive loss, which aligns image and text representations across multiple granularities. Extensive experiments demonstrate that our proposed Hi-GITA significantly outperforms existing zero-shot CCR methods. For instance, it brings about 20% accuracy improvement in handwritten character and radical zero-shot settings. Code and models will be released soon.

cs.CV↗

arXiv2025

Autoregressive Meta-Actions for Unified Controllable Trajectory Generation

Controllable trajectory generation guided by high-level semantic decisions, termed meta-actions, is crucial for autonomous driving systems. A significant limitation of existing frameworks is their reliance on invariant meta-actions assigned over fixed future time intervals, causing temporal misalignment with the actual behavior trajectories. This misalignment leads to irrelevant associations between the prescribed meta-actions and the resulting trajectories, disrupting task coherence and limiting model performance. To address this challenge, we introduce Autoregressive Meta-Actions, an approach integrated into autoregressive trajectory generation frameworks that provides a unified and precise definition for meta-action-conditioned trajectory prediction. Specifically, We decompose traditional long-interval meta-actions into frame-level meta-actions, enabling a sequential interplay between autoregressive meta-action prediction and meta-action-conditioned trajectory generation. This decomposition ensures strict alignment between each trajectory segment and its corresponding meta-action, achieving a consistent and unified task formulation across the entire trajectory span and significantly reducing complexity. Moreover, we propose a staged pre-training process to decouple the learning of basic motion dynamics from the integration of high-level decision control, which offers flexibility, stability, and modularity. Experimental results validate our framework's effectiveness, demonstrating improved trajectory adaptivity and responsiveness to dynamic decision-making scenarios. We provide the video document and dataset, which are available at https://arma-traj.github.io/.

cs.RO↗

arXiv2025

UDuo: Universal Dual Optimization Framework for Online Matching

Online resource allocation under budget constraints critically depends on proper modeling of user arrival dynamics. Classical approaches employ stochastic user arrival models to derive near-optimal solutions through fractional matching formulations of exposed users for downstream allocation tasks. However, this is no longer a reasonable assumption when the environment changes dynamically. In this work, We propose the Universal Dual optimization framework UDuo, a novel paradigm that fundamentally rethinks online allocation through three key innovations: (i) a temporal user arrival representation vector that explicitly captures distribution shifts in user arrival patterns and resource consumption dynamics, (ii) a resource pacing learner with adaptive allocation policies that generalize to heterogeneous constraint scenarios, and (iii) an online time-series forecasting approach for future user arrival distributions that achieves asymptotically optimal solutions with constraint feasibility guarantees in dynamic environments. Experimental results show that UDuo achieves higher efficiency and faster convergence than the traditional stochastic arrival model in real-world pricing while maintaining rigorous theoretical validity for general online allocation problems.

cs.IR↗

arXiv2025

StyleAR: Customizing Multimodal Autoregressive Model for Style-Aligned Text-to-Image Generation

In the current research landscape, multimodal autoregressive (AR) models have shown exceptional capabilities across various domains, including visual understanding and generation. However, complex tasks such as style-aligned text-to-image generation present significant challenges, particularly in data acquisition. In analogy to instruction-following tuning for image editing of AR models, style-aligned generation requires a reference style image and prompt, resulting in a text-image-to-image triplet where the output shares the style and semantics of the input. However, acquiring large volumes of such triplet data with specific styles is considerably more challenging than obtaining conventional text-to-image data used for training generative models. To address this issue, we propose StyleAR, an innovative approach that combines a specially designed data curation method with our proposed AR models to effectively utilize text-to-image binary data for style-aligned text-to-image generation. Our method synthesizes target stylized data using a reference style image and prompt, but only incorporates the target stylized image as the image modality to create high-quality binary data. To facilitate binary data training, we introduce a CLIP image encoder with a perceiver resampler that translates the image input into style tokens aligned with multimodal tokens in AR models and implement a style-enhanced token technique to prevent content leakage which is a common issue in previous work. Furthermore, we mix raw images drawn from large-scale text-image datasets with stylized images to enhance StyleAR's ability to extract richer stylistic features and ensure style consistency. Extensive qualitative and quantitative experiments demonstrate our superior performance.

cs.CV↗

arXiv2025

Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression

Most existing approaches for image and video compression perform transform coding in the pixel space to reduce redundancy. However, due to the misalignment between the pixel-space distortion and human perception, such schemes often face the difficulties in achieving both high-realism and high-fidelity at ultra-low bitrate. To solve this problem, we propose \textbf{G}enerative \textbf{L}atent \textbf{C}oding (\textbf{GLC}) models for image and video compression, termed GLC-image and GLC-Video. The transform coding of GLC is conducted in the latent space of a generative vector-quantized variational auto-encoder (VQ-VAE). Compared to the pixel-space, such a latent space offers greater sparsity, richer semantics and better alignment with human perception, and show its advantages in achieving high-realism and high-fidelity compression. To further enhance performance, we improve the hyper prior by introducing a spatial categorical hyper module in GLC-image and a spatio-temporal categorical hyper module in GLC-video. Additionally, the code-prediction-based loss function is proposed to enhance the semantic consistency. Experiments demonstrate that our scheme shows high visual quality at ultra-low bitrate for both image and video compression. For image compression, GLC-image achieves an impressive bitrate of less than $0.04$ bpp, achieving the same FID as previous SOTA model MS-ILLM while using $45\%$ fewer bitrate on the CLIC 2020 test set. For video compression, GLC-video achieves 65.3\% bitrate saving over PLVC in terms of DISTS.

eess.IV↗

arXiv2025

First Lasing and Stable Operation of a Direct-Amplification Enabled Harmonic Generation Free-Electron laser

Seeded free-electron lasers (FELs) capable of operating at repetition rates up to the MHz level are in high demand for advanced time-resolved spectroscopies, which require both full longitudinal coherence and high average photon flux in the extreme ultraviolet (EUV) and x-ray regimes. However, conventional external-seed laser systems cannot sustain MHz operation with sufficient hundreds of megawatts peak power requirement due to their limited total power. Here, we report the first lasing and stable operation of a direct-amplification-enabled harmonic generation FEL driven by a weak seed laser with MW-level peak power. Beginning with an ultraviolet seed laser with only 0.75 μJ pulse energy, we demonstrate its direct amplification to over 10 μJ within an 8-meter-long modulator. We observe coherent harmonic generation up to the 12th harmonic of the seed and achieve saturation of the 7th harmonic in the radiator. These results represent a crucial milestone toward the realization of MHz-class, fully coherent EUV and x-ray light sources.

physics.acc-ph↗

arXiv2025

A Quality-Centric Framework for Generic Deepfake Detection

Detecting AI-generated images, particularly deepfakes, has become increasingly crucial, with the primary challenge being the generalization to previously unseen manipulation methods. This paper tackles this issue by leveraging the forgery quality of training data to improve the generalization performance of existing deepfake detectors. Generally, the forgery quality of different deepfakes varies: some have easily recognizable forgery clues, while others are highly realistic. Existing works often train detectors on a mix of deepfakes with varying forgery qualities, potentially leading detectors to short-cut the easy-to-spot artifacts from low-quality forgery samples, thereby hurting generalization performance. To tackle this issue, we propose a novel quality-centric framework for generic deepfake detection, which is composed of a Quality Evaluator, a low-quality data enhancement module, and a learning pacing strategy that explicitly incorporates forgery quality into the training process. Our framework is inspired by curriculum learning, which is designed to gradually enable the detector to learn more challenging deepfake samples, starting with easier samples and progressing to more realistic ones. We employ both static and dynamic assessments to assess the forgery quality, combining their scores to produce a final rating for each training sample. The rating score guides the selection of deepfake samples for training, with higher-rated samples having a higher probability of being chosen. Furthermore, we propose a novel frequency data augmentation method specifically designed for low-quality forgery samples, which helps to reduce obvious forgery traces and improve their overall realism. Extensive experiments demonstrate that our proposed framework can be applied plug-and-play to existing detection models and significantly enhance their generalization performance in detection.

cs.CV↗