arXiv subjects

Xiaoteng Zhang

Publications and source records attributed to Xiaoteng Zhang.

11 recordsLinked to original sources

arXiv2026

FeedbackTrack: Visual-Cortex-Inspired Cross-Frame Feedback for Transformer Tracking

Visual object tracking requires effective temporal integration, yet most Transformer trackers still rely on predominantly feed-forward feature extraction. Existing temporal mechanisms typically update templates, prompts, queries, or prediction states, while intermediate representations are rarely reused to modulate corresponding processing stages. We propose \textbf{FeedbackTrack}, a visual-cortex-inspired framework that introduces sparse, group-level layer-aligned cross-frame feedback into pretrained Transformer trackers. Previous-frame intermediate states are detached, cached, and returned to corresponding Transformer groups in the current frame through two lightweight pathways: Query Feedback for token-level query modulation and Gate Feedback for context-dependent feature modulation. FeedbackTrack preserves the original tracking pipeline with only a fixed-size one-frame cache. Across SPMTrack and ARTrackV2, FeedbackTrack consistently improves five backbone configurations on LaSOT and GOT-10k, achieving 83.4 AO and 79.1 AUC with SPMTrack-G while adding less than 1\% parameters. Controlled comparisons show that cross-frame feedback outperforms same-frame modulation by 1.8--3.2 AO points, demonstrating that the gains mainly come from recurrent historical information. Further analysis reveals a non-uniform depth-dependent organization of learned feedback strengths, highlighting the effectiveness of recurrent feedback for Transformer tracking.

cs.CV↗

arXiv2026

A third-order multi-moment cell-centered Lagrangian scheme for hydrodynamics with an accurate 2D nodal solver

This paper presents a novel high-order cell-centered Lagrangian scheme for 2D compressible hydrodynamics by bridging the multi-moment constrained finite volume method (MCV) [16, 51, 52] with a nodal Riemann solver. This scheme (denoted by LMCV) not only maintains high-order accuracy as MCV but also inherits the conservation and robust properties of the nodal Riemann solver. On the one hand, the MCV employs and evolves both the point-values (PV) at cell vertexes and the volume-integrated averages (VIA) on computational mesh, which ensures the rigorous numerical conservation and establishes an adequate foundation for the computation of Lagrangian fluxes with high accuracy. On the other hand, we developed a 2D Riemann solver based on EUCCLHYD [24], it takes fully advantage of numerical formulations from high-order scheme and accomplishes the compatibility between the mesh movement and numerical fluxes. The main new features of the solver are the introduction of a new set of jump and balance conditions. The jump condition provides a high-accurate formulation linking the surface pressure of each cell to its nodal velocity, while the balance condition ensures nodal conservation and stabilizes the velocity field without losing accuracy. More intriguing is that our nodal solver can be regarded as a natural high-order extension of the HLLC and the HLLC-2D [41] solvers. The comparison between these solvers better demonstrates our innovative approach in addressing the difficulties encountered in constructing 2D high-order Lagrangian schemes. A variety of numerical experiments are carried out to illustrate the accuracy and robustness of the algorithm.

math.NA↗

arXiv2026

Graph-GRPO: Stabilizing Multi-Agent Topology Learning via Group Relative Policy Optimization

Optimizing communication topology is fundamental to the efficiency and effectiveness of Large Language Model (LLM)-based Multi-Agent Systems (MAS). While recent approaches utilize reinforcement learning to dynamically construct task-specific graphs, they typically rely on single-sample policy gradients with absolute rewards (e.g., binary correctness). This paradigm suffers from severe gradient variance and the credit assignment problem: simple queries yield non-informative positive rewards for suboptimal structures, while difficult queries often result in failures that provide no learning signal. To address these challenges, we propose Graph-GRPO, a novel topology optimization framework that integrates Group Relative Policy Optimization. Instead of evaluating a single topology in isolation, Graph-GRPO samples a group of diverse communication graphs for each query and computes the advantage of specific edges based on their relative performance within the group. By normalizing rewards across the sampled group, our method effectively mitigates the noise derived from task difficulty variance and enables fine-grained credit assignment. Extensive experiments on reasoning and code generation benchmarks demonstrate that Graph-GRPO significantly outperforms state-of-the-art baselines, achieving superior training stability and identifying critical communication pathways previously obscured by reward noise.

cs.CL↗

arXiv2026

Intelligent Pathological Diagnosis of Gestational Trophoblastic Diseases via Visual-Language Deep Learning Model

The pathological diagnosis of gestational trophoblastic disease(GTD) takes a long time, relies heavily on the experience of pathologists, and the consistency of initial diagnosis is low, which seriously threatens maternal health and reproductive outcomes. We developed an expert model for GTD pathological diagnosis, named GTDoctor. GTDoctor can perform pixel-based lesion segmentation on pathological slides, and output diagnostic conclusions and personalized pathological analysis results. We developed a software system, GTDiagnosis, based on this technology and conducted clinical trials. The retrospective results demonstrated that GTDiagnosis achieved a mean precision of over 0.91 for lesion detection in pathological slides (n=679 slides). In prospective studies, pathologists using GTDiagnosis attained a Positive Predictive Value of 95.59% (n=68 patients). The tool reduced average diagnostic time from 56 to 16 seconds per case (n=285 patients). GTDoctor and GTDiagnosis offer a novel solution for GTD pathological diagnosis, enhancing diagnostic performance and efficiency while maintaining clinical interpretability.

cs.CV↗

arXiv2025

Shared DIFF Transformer

DIFF Transformer improves attention allocation by enhancing focus on relevant context while suppressing noise. It introduces a differential attention mechanism that calculates the difference between two independently generated attention distributions, effectively reducing noise and promoting sparse attention patterns. However, the independent signal generation in DIFF Transformer results in parameter redundancy and suboptimal utilization of information. In this work, we propose Shared DIFF Transformer, which draws on the idea of a differential amplifier by introducing a shared base matrix to model global patterns and incorporating low-rank updates to enhance task-specific flexibility. This design significantly reduces parameter redundancy, improves efficiency, and retains strong noise suppression capabilities. Experimental results show that, compared to DIFF Transformer, our method achieves better performance in tasks such as long-sequence modeling, key information retrieval, and in-context learning. Our work provides a novel and efficient approach to optimizing differential attention mechanisms and advancing robust Transformer architectures.

cs.LG↗

arXiv2025

The Role of Excitatory Parvalbumin-positive Neurons in the Tectofugal Pathway of Pigeon (Columba livia) Hierarchical Visual Processing

The visual systems of birds and mammals exhibit remarkable organizational similarities: the dorsal ventricular ridge (DVR) demonstrates a columnar microcircuitry that parallels the cortical architecture observed in mammals. However, the specific neuronal subtypes involved and their functional roles in pigeon hierarchical visual processing remain unclear. This study investigates the role of excitatory parvalbumin (PV+) neurons within the Ento-MVL (entoallium-mesopallium venterolaterale) circuit of pigeons underlying hierarchical moving target recognition. Electrophysiological recordings and immunofluorescence staining reveal that excitatory PV+ neurons originating from the entopallial internal (Ei) predominantly modulate MVL responses to varying visual stimuli. Using a heterochronous-speed recurrent neural network (HS-RNN) model, we further validated these dynamics, replicating the rapid adaptation of the Ento-MVL circuit to moving visual targets. The findings suggest that the fast-spiking and excitatory properties of PV+ neurons enable rapid processing of motion-related information within the Ento-MVL circuit. Our results elucidate the functional role of excitatory PV+ neurons in hierarchical information processing under the columnar organization of the visual DVR and underscore the convergent neural processing strategies shared by avian and mammalian visual systems.

q-bio.NC↗

arXiv2025

DINT Transformer

DIFF Transformer addresses the issue of irrelevant context interference by introducing a differential attention mechanism that enhances the robustness of local attention. However, it has two critical limitations: the lack of global context modeling, which is essential for identifying globally significant tokens, and numerical instability due to the absence of strict row normalization in the attention matrix. To overcome these challenges, we propose DINT Transformer, which extends DIFF Transformer by incorporating a differential-integral mechanism. By computing global importance scores and integrating them into the attention matrix, DINT Transformer improves its ability to capture global dependencies. Moreover, the unified parameter design enforces row-normalized attention matrices, improving numerical stability. Experimental results demonstrate that DINT Transformer excels in accuracy and robustness across various practical applications, such as long-context language modeling and key information retrieval. These results position DINT Transformer as a highly effective and promising architecture.

cs.CL↗

arXiv2024

RetCompletion:High-Speed Inference Image Completion with Retentive Network

Time cost is a major challenge in achieving high-quality pluralistic image completion. Recently, the Retentive Network (RetNet) in natural language processing offers a novel approach to this problem with its low-cost inference capabilities. Inspired by this, we apply RetNet to the pluralistic image completion task in computer vision. We present RetCompletion, a two-stage framework. In the first stage, we introduce Bi-RetNet, a bidirectional sequence information fusion model that integrates contextual information from images. During inference, we employ a unidirectional pixel-wise update strategy to restore consistent image structures, achieving both high reconstruction quality and fast inference speed. In the second stage, we use a CNN for low-resolution upsampling to enhance texture details. Experiments on ImageNet and CelebA-HQ demonstrate that our inference speed is 10$\times$ faster than ICT and 15$\times$ faster than RePaint. The proposed RetCompletion significantly improves inference speed and delivers strong performance.

cs.CV↗

arXiv2024

TSOM: Small Object Motion Detection Neural Network Inspired by Avian Visual Circuit

Detecting small moving objects in complex backgrounds from an overhead perspective is a highly challenging task for machine vision systems. As an inspiration from nature, the avian visual system is capable of processing motion information in various complex aerial scenes, and its Retina-OT-Rt visual circuit is highly sensitive to capturing the motion information of small objects from high altitudes. However, more needs to be done on small object motion detection algorithms based on the avian visual system. In this paper, we conducted mathematical modeling based on extensive studies of the biological mechanisms of the Retina-OT-Rt visual circuit. Based on this, we proposed a novel tectum small object motion detection neural network (TSOM). The neural network includes the retina, SGC dendritic, SGC Soma, and Rt layers, each layer corresponding to neurons in the visual pathway. The Retina layer is responsible for accurately projecting input content, the SGC dendritic layer perceives and encodes spatial-temporal information, the SGC Soma layer computes complex motion information and extracts small objects, and the Rt layer integrates and decodes motion information from multiple directions to determine the position of small objects. Extensive experiments on pigeon neurophysiological experiments and image sequence data showed that the TSOM is biologically interpretable and effective in extracting reliable small object motion features from complex high-altitude backgrounds.

cs.CV↗

arXiv2023

HVDetFusion: A Simple and Robust Camera-Radar Fusion Framework

In the field of autonomous driving, 3D object detection is a very important perception module. Although the current SOTA algorithm combines Camera and Lidar sensors, limited by the high price of Lidar, the current mainstream landing schemes are pure Camera sensors or Camera+Radar sensors. In this study, we propose a new detection algorithm called HVDetFusion, which is a multi-modal detection algorithm that not only supports pure camera data as input for detection, but also can perform fusion input of radar data and camera data. The camera stream does not depend on the input of Radar data, thus addressing the downside of previous methods. In the pure camera stream, we modify the framework of Bevdet4D for better perception and more efficient inference, and this stream has the whole 3D detection output. Further, to incorporate the benefits of Radar signals, we use the prior information of different object positions to filter the false positive information of the original radar data, according to the positioning information and radial velocity information recorded by the radar sensors to supplement and fuse the BEV features generated by the original camera data, and the effect is further improved in the process of fusion training. Finally, HVDetFusion achieves the new state-of-the-art 67.4\% NDS on the challenging nuScenes test set among all camera-radar 3D object detectors. The code is available at https://github.com/HVXLab/HVDetFusion

cs.CV↗

arXiv2018

Qiniu Submission to ActivityNet Challenge 2018

In this paper, we introduce our submissions for the tasks of trimmed activity recognition (Kinetics) and trimmed event recognition (Moments in Time) for Activitynet Challenge 2018. In the two tasks, non-local neural networks and temporal segment networks are implemented as our base models. Multi-modal cues such as RGB image, optical flow and acoustic signal have also been used in our method. We also propose new non-local-based models for further improvement on the recognition accuracy. The final submissions after ensembling the models achieve 83.5% top-1 accuracy and 96.8% top-5 accuracy on the Kinetics validation set, 35.81% top-1 accuracy and 62.59% top-5 accuracy on the MIT validation set.

cs.CV↗