Zhichao Sun

Hao Wu, Haoran Lou, Xinyue Li et al.

We present FireRed-OCR, a systematic framework to specialize general VLMs into high-performance OCR models. Large Vision-Language Models (VLMs) have demonstrated impressive general capabilities but frequently suffer from ``structural hallucination'' when processing complex documents, limiting their utility in industrial OCR applications. In this paper, we introduce FireRed-OCR, a novel framework designed to transform general-purpose VLMs (based on Qwen3-VL) into pixel-precise structural document parsing experts. To address the scarcity of high-quality structured data, we construct a ``Geometry + Semantics'' Data Factory. Unlike traditional random sampling, our pipeline leverages geometric feature clustering and multi-dimensional tagging to synthesize and curate a highly balanced dataset, effectively handling long-tail layouts and rare document types. Furthermore, we propose a Three-Stage Progressive Training strategy that guides the model from pixel-level perception to logical structure generation. This curriculum includes: (1) Multi-task Pre-alignment to ground the model's understanding of document structure; (2) Specialized SFT for standardizing full-image Markdown output; and (3) Format-Constrained Group Relative Policy Optimization (GRPO), which utilizes reinforcement learning to enforce strict syntactic validity and structural integrity (e.g., table closure, formula syntax). Extensive evaluations on OmniDocBench v1.5 demonstrate that FireRed-OCR achieves state-of-the-art performance with an overall score of 92.94\%, significantly outperforming strong baselines such as DeepSeek-OCR 2 and OCRVerse across text, formula, table, and reading order metrics. We open-source our code and model weights to facilitate the ``General VLM to Specialized Structural Expert'' paradigm.

Zhichao Sun, Yidong Ma, Gang Liu et al.

Large Vision-Language Models (LVLMs) achieve impressive performance across multiple tasks. A significant challenge, however, is their prohibitive inference cost when processing high-resolution visual inputs. While visual token pruning has emerged as a promising solution, existing methods that primarily focus on semantic relevance often discard tokens that are crucial for spatial reasoning. We address this gap through a novel insight into \emph{how LVLMs process spatial reasoning}. Specifically, we reveal that LVLMs implicitly establish visual coordinate systems through Rotary Position Embeddings (RoPE), where specific token positions serve as \textbf{implicit visual coordinates} (IVC tokens) that are essential for spatial reasoning. Based on this insight, we propose \textbf{IVC-Prune}, a training-free, prompt-aware pruning strategy that retains both IVC tokens and semantically relevant foreground tokens. IVC tokens are identified by theoretically analyzing the mathematical properties of RoPE, targeting positions at which its rotation matrices approximate identity matrix or the $90^\circ$ rotation matrix. Foreground tokens are identified through a robust two-stage process: semantic seed discovery followed by contextual refinement via value-vector similarity. Extensive evaluations across four representative LVLMs and twenty diverse benchmarks show that IVC-Prune reduces visual tokens by approximately 50\% while maintaining $\geq$ 99\% of the original performance and even achieving improvements on several benchmarks. Source codes are available at https://github.com/FireRedTeam/IVC-Prune.

Zhichao Sun, Hailiang Zhao, Kingsum Chow

Cloud-Native microservice architectures have become prevalent owing to their inherent flexibility and scalability properties. To satisfy service quality guarantees, cloud providers must implement efficient proactive autoscaling algorithms. However, effective proactive scaling critically depends on accurately estimating end-to-end latency under given resource quotas, which remains highly challenging. Existing methods struggle with the multi-hierarchical nature and dynamic operational contexts of microservice systems. They primarily employ single-scale modeling that fails to capture inherent organizational structures and lacks adaptability to varying workload types. To address these limitations, we propose MSGAF, a Multi-Scale Graph Adaptive Fusion framework with Scene-Aware Learning for microservice latency estimation. Our approach constructs hierarchical graph representations through learnable aggregation-based coarsening, capturing system behaviors across microscopic, mesoscopic, and macroscopic levels. The framework comprises three components: a system state encoding module transforming heterogeneous monitoring data into unified representations, a multi-scale graph adaptive fusion module leveraging graph attention networks for hierarchical feature extraction, and a scene-aware learning module employing specialized expert networks with dynamic weight allocation for context-specific estimation. Additionally, we design and implement a comprehensive non-intrusive monitoring system for real-time data collection. Extensive experiments on benchmark microservice applications demonstrate that MSGAF significantly outperforms state-of-the-art methods across diverse operational scenarios, providing substantial improvements for cloud-native performance optimization.

Xiaoran Fan, Zhichao Sun, Tao Ji et al.

As vision-language models (VLMs) tackle increasingly complex and multimodal tasks, the rapid growth of Key-Value (KV) cache imposes significant memory and computational bottlenecks during inference. While Multi-Head Latent Attention (MLA) offers an effective means to compress the KV cache and accelerate inference, adapting existing VLMs to the MLA architecture without costly pretraining remains largely unexplored. In this work, we present MHA2MLA-VLM, a parameter-efficient and multimodal-aware framework for converting off-the-shelf VLMs to MLA. Our approach features two core techniques: (1) a modality-adaptive partial-RoPE strategy that supports both traditional and multimodal settings by selectively masking nonessential dimensions, and (2) a modality-decoupled low-rank approximation method that independently compresses the visual and textual KV spaces. Furthermore, we introduce parameter-efficient fine-tuning to minimize adaptation cost and demonstrate that minimizing output activation error, rather than parameter distance, substantially reduces performance loss. Extensive experiments on three representative VLMs show that MHA2MLA-VLM restores original model performance with minimal supervised data, significantly reduces KV cache footprint, and integrates seamlessly with KV quantization.

Zhichao Sun, Yuliang Gu, Yepeng Liu et al.

Anomaly detection in chest X-rays is a critical task. Most methods mainly model the distribution of normal images, and then regard significant deviation from normal distribution as anomaly. Recently, CLIP-based methods, pre-trained on a large number of medical images, have shown impressive performance on zero/few-shot downstream tasks. In this paper, we aim to explore the potential of CLIP-based methods for anomaly detection in chest X-rays. Considering the discrepancy between the CLIP pre-training data and the task-specific data, we propose a position-guided prompt learning method. Specifically, inspired by the fact that experts diagnose chest X-rays by carefully examining distinct lung regions, we propose learnable position-guided text and image prompts to adapt the task data to the frozen pre-trained CLIP-based model. To enhance the model's discriminative capability, we propose a novel structure-preserving anomaly synthesis method within chest x-rays during the training process. Extensive experiments on three datasets demonstrate that our proposed method outperforms some state-of-the-art methods. The code of our implementation is available at https://github.com/sunzc-sunny/PPAD.

Zhichao Sun, Yepeng Liu, Huachao Zhu et al.

Drones have become prevalent robotic platforms with diverse applications, showing significant potential in Embodied Artificial Intelligence (Embodied AI). Referring Expression Comprehension (REC) enables drones to locate objects based on natural language expressions, a crucial capability for Embodied AI. Despite advances in REC for ground-level scenes, aerial views introduce unique challenges including varying viewpoints, occlusions and scale variations. To address this gap, we introduce RefDrone, a REC benchmark for drone scenes. RefDrone reveals three key challenges in REC: 1) multi-scale and small-scale target detection; 2) multi-target and no-target samples; 3) complex environment with rich contextual expressions. To efficiently construct this dataset, we develop RDAgent (referring drone annotation framework with multi-agent system), a semi-automated annotation tool for REC tasks. RDAgent ensures high-quality contextual expressions and reduces annotation cost. Furthermore, we propose Number GroundingDINO (NGDINO), a novel method designed to handle multi-target and no-target cases. NGDINO explicitly learns and utilizes the number of objects referred to in the expression. Comprehensive experiments with state-of-the-art REC methods demonstrate that NGDINO achieves superior performance on both the proposed RefDrone and the existing gRefCOCO datasets. The dataset and code are be publicly at https://github.com/sunzc-sunny/refdrone.

Yepeng Liu, Zhichao Sun, Baosheng Yu et al.

Many keypoint detection and description methods have been proposed for image matching or registration. While these methods demonstrate promising performance for single-modality image matching, they often struggle with multimodal data because the descriptors trained on single-modality data tend to lack robustness against the non-linear variations present in multimodal data. Extending such methods to multimodal image matching often requires well-aligned multimodal data to learn modality-invariant descriptors. However, acquiring such data is often costly and impractical in many real-world scenarios. To address this challenge, we propose a modality-invariant feature learning network (MIFNet) to compute modality-invariant features for keypoint descriptions in multimodal image matching using only single-modality training data. Specifically, we propose a novel latent feature aggregation module and a cumulative hybrid aggregation module to enhance the base keypoint descriptors trained on single-modality data by leveraging pre-trained features from Stable Diffusion models. %, our approach generates robust and invariant features across diverse and unknown modalities. We validate our method with recent keypoint detection and description methods in three multimodal retinal image datasets (CF-FA, CF-OCT, EMA-OCTA) and two remote sensing datasets (Optical-SAR and Optical-NIR). Extensive experiments demonstrate that the proposed MIFNet is able to learn modality-invariant feature for multimodal image matching without accessing the targeted modality and has good zero-shot generalization ability. The code will be released at https://github.com/lyp-deeplearning/MIFNet.

Yuliang Gu, Yepeng Liu, Zhichao Sun et al.

Annotating 3D medical images demands expert knowledge and is time-consuming. As a result, semi-supervised learning (SSL) approaches have gained significant interest in 3D medical image segmentation. The significant size differences among various organs in the human body lead to imbalanced class distribution, which is a major challenge in the real-world application of these SSL approaches. To address this issue, we develop a novel Shape Transformation driven by Active Contour (STAC), that enlarges smaller organs to alleviate imbalanced class distribution across different organs. Inspired by curve evolution theory in active contour methods, STAC employs a signed distance function (SDF) as the level set function, to implicitly represent the shape of organs, and deforms voxels in the direction of the steepest descent of SDF (i.e., the normal vector). To ensure that the voxels far from expansion organs remain unchanged, we design an SDF-based weight function to control the degree of deformation for each voxel. We then use STAC as a data-augmentation process during the training stage. Experimental results on two benchmark datasets demonstrate that the proposed method significantly outperforms some state-of-the-art methods. Source code is publicly available at https://github.com/GuGuLL123/STAC.

Junan Lin, Zhichao Sun, Enjie Cao et al.

Skeletal Action recognition from an egocentric view is important for applications such as interfaces in AR/VR glasses and human-robot interaction, where the device has limited resources. Most of the existing skeletal action recognition approaches use 3D coordinates of hand joints and 8-corner rectangular bounding boxes of objects as inputs, but they do not capture how the hands and objects interact with each other within the spatial context. In this paper, we present a new framework called Contact-aware Skeletal Action Recognition (CaSAR). It uses novel representations of hand-object interaction that encompass spatial information: 1) contact points where the hand joints meet the objects, 2) distant points where the hand joints are far away from the object and nearly not involved in the current action. Our framework is able to learn how the hands touch or stay away from the objects for each frame of the action sequence, and use this information to predict the action class. We demonstrate that our approach achieves the state-of-the-art accuracy of 91.3% and 98.4% on two public datasets, H2O and FPHA, respectively.

Zhichao Sun, Huazhang Hu, Yidong Ma et al.

With the exponential growth of data, traditional object detection methods are increasingly struggling to handle vast vocabulary object detection tasks effectively. We analyze two key limitations of classification-based detectors: positive gradient dilution, where rare positive categories receive insufficient learning signals, and hard negative gradient dilution, where discriminative gradients are overwhelmed by numerous easy negatives. To address these challenges, we propose CQ-DINO, a category query-based object detection framework that reformulates classification as a contrastive task between object queries and learnable category queries. Our method introduces image-guided query selection, which reduces the negative space by adaptively retrieving top-K relevant categories per image via cross-attention, thereby rebalancing gradient distributions and facilitating implicit hard example mining. Furthermore, CQ-DINO flexibly integrates explicit hierarchical category relationships in structured datasets (e.g., V3Det) or learns implicit category correlations via self-attention in generic datasets (e.g., COCO). Experiments demonstrate that CQ-DINO achieves superior performance on the challenging V3Det benchmark (surpassing previous methods by 2.1% AP) while maintaining competitiveness in COCO. Our work provides a scalable solution for real-world detection systems requiring wide category coverage. The code is publicly at https://github.com/FireRedTeam/CQ-DINO.

Zerui Zhang, Zhichao Sun, Zelong Liu et al.

Medical anomaly detection is a critical research area aimed at recognizing abnormal images to aid in diagnosis.Most existing methods adopt synthetic anomalies and image restoration on normal samples to detect anomaly. The unlabeled data consisting of both normal and abnormal data is not well explored. We introduce a novel Spatial-aware Attention Generative Adversarial Network (SAGAN) for one-class semi-supervised generation of health images.Our core insight is the utilization of position encoding and attention to accurately focus on restoring abnormal regions and preserving normal regions. To fully utilize the unlabelled data, SAGAN relaxes the cyclic consistency requirement of the existing unpaired image-to-image conversion methods, and generates high-quality health images corresponding to unlabeled data, guided by the reconstruction of normal images and restoration of pseudo-anomaly images.Subsequently, the discrepancy between the generated healthy image and the original image is utilized as an anomaly score.Extensive experiments on three medical datasets demonstrate that the proposed SAGAN outperforms the state-of-the-art methods.

Yuda Zou, Xin Xiao, Peilin Zhou et al.

Object counting typically uses 2D point annotations. The complexity of object shapes and the subjectivity of annotators may lead to annotation inconsistency, potentially confusing counting model training. Some sophisticated noise-resistance counting methods have been proposed to alleviate this issue. Differently, we aim to directly refine the initial point annotations before training counting models. For that, we propose the Shifted Autoencoders (SAE), which enhances annotation consistency. Specifically, SAE applies random shifts to initial point annotations and employs a UNet to restore them to their original positions. Similar to MAE reconstruction, the trained SAE captures general position knowledge and ignores specific manual offset noise. This allows to restore the initial point annotations to more general and thus consistent positions. Extensive experiments show that using such refined consistent annotations to train some advanced (including noise-resistance) object counting models steadily/significantly boosts their performances. Remarkably, the proposed SAE helps to set new records on nine datasets. We will make codes and refined point annotations available.

Zelong Liu, Yuliang Gu, Zhichao Sun et al.

Crack detection is an important task in computer vision. Despite impressive in-dataset performance, deep learning-based methods still struggle in generalizing to unseen domains. The thin structure property of cracks is usually overlooked by previous methods. In this work, we introduce CrackCue, a novel method for robust crack detection based on coarse-to-fine crack cue generation. The core concept lies on leveraging the thin structure property to generate a robust crack cue, guiding the crack detection. Specifically, we first employ a simple max-pooling and upsampling operation on the crack image. This results in a coarse crack-free background, based on which a fine crack-free background can be obtained via a reconstruction network. The difference between the original image and fine crack-free background provides a fine crack cue. This fine cue embeds robust crack prior information which is unaffected by complex backgrounds, shadow, and varied lighting. As a plug-and-play method, we incorporate the proposed CrackCue into three advanced crack detection networks. Extensive experimental results demonstrate that the proposed CrackCue significantly improves the generalization ability and robustness of the baseline methods. The source code will be publicly available.

Xiaoran Fan, Zhichao Sun, Yangfan Gao et al.

Speech-language models (SLMs) offer a promising path toward unifying speech and text understanding and generation. However, challenges remain in achieving effective cross-modal alignment and high-quality speech generation. In this work, we systematically investigate the role of speech tokenizer designs in LLM-centric SLMs, augmented by speech heads and speaker modeling. We compare coupled, semi-decoupled, and fully decoupled speech tokenizers under a fair SLM framework and find that decoupled tokenization significantly improves alignment and synthesis quality. To address the information density mismatch between speech and text, we introduce multi-token prediction (MTP) into SLMs, enabling each hidden state to decode multiple speech tokens. This leads to up to 12$\times$ faster decoding and a substantial drop in word error rate (from 6.07 to 3.01). Furthermore, we propose a speaker-aware generation paradigm and introduce RoleTriviaQA, a large-scale role-playing knowledge QA benchmark with diverse speaker identities. Experiments demonstrate that our methods enhance both knowledge understanding and speaker consistency.

Yuliang Gu, Zhichao Sun, Tian Chen et al.

Semi-supervised image segmentation has attracted great attention recently. The key is how to leverage unlabeled images in the training process. Most methods maintain consistent predictions of the unlabeled images under variations (e.g., adding noise/perturbations, or creating alternative versions) in the image and/or model level. In most image-level variation, medical images often have prior structure information, which has not been well explored. In this paper, we propose novel dual structure-aware image filterings (DSAIF) as the image-level variations for semi-supervised medical image segmentation. Motivated by connected filtering that simplifies image via filtering in structure-aware tree-based image representation, we resort to the dual contrast invariant Max-tree and Min-tree representation. Specifically, we propose a novel connected filtering that removes topologically equivalent nodes (i.e. connected components) having no siblings in the Max/Min-tree. This results in two filtered images preserving topologically critical structure. Applying the proposed DSAIF to mutually supervised networks decreases the consensus of their erroneous predictions on unlabeled images. This helps to alleviate the confirmation bias issue of overfitting to noisy pseudo labels of unlabeled images, and thus effectively improves the segmentation performance. Extensive experimental results on three benchmark datasets demonstrate that the proposed method significantly/consistently outperforms some state-of-the-art methods. The source codes will be publicly available.

Zhichao Sun, Junjie Wu, Gary G. Yen et al.

Unmanned aerial vehicle (UAV) can provide superior flexibility and cost-efficiency for modern radar imaging systems, which is an ideal platform for advanced remote sensing applications using synthetic aperture radar (SAR) technology. In this paper, an energy-efficient passive UAV radar imaging system using illuminators of opportunity is first proposed and investigated. Equipped with a SAR receiver, the UAV platform passively reuses the backscattered signal of the target scene from an external illuminator, such as SAR satellite, GNSS or ground-based stationary commercial illuminators, and achieves bi-static SAR imaging and data communication. The system can provide instant accessibility to the radar image of the interested targets with enhanced platform concealment, which is an essential tool for stealth observation and scene monitoring. The mission concept and system block diagram are first presented with justifications on the advantages of the system. Then, a set of mission performance evaluators is established to quantitatively assess the capability of the system in a comprehensive manner, including UAV navigation, passive SAR imaging and communication. Finally, the validity of the proposed performance evaluators are verified by numerical simulations.