arXiv subjects

Yun Zhang

Publications and source records attributed to Yun Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2025

Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning

Table reasoning, encompassing tasks such as table question answering, fact verification, and text-to-SQL, requires precise understanding of structured tabular data, coupled with numerical computation and code manipulation for effective inference. Supervised fine-tuning (SFT) approaches have achieved notable success but often struggle with generalization and robustness due to biases inherent in imitative learning. We introduce Reasoning-Table, the first application of reinforcement learning (RL) to table reasoning, achieving state-of-the-art performance. Through rigorous data preprocessing, reward design, and tailored training strategies, our method leverages simple rule-based outcome rewards to outperform SFT across multiple benchmarks. Unified training across diverse tasks enables Reasoning-Table to emerge as a robust table reasoning large language model, surpassing larger proprietary models like Claude-3.7-Sonnet by 4.0% on table reasoning benchmarks. The approach also achieves excellent performance on text-to-SQL tasks, reaching 68.3% performance on the BIRD dev dataset with a 7B model. Further experiments demonstrate that Reasoning-Table enhances the model's generalization capabilities and robustness.

cs.CL↗

arXiv2025

StabStitch++: Unsupervised Online Video Stitching with Spatiotemporal Bidirectional Warps

We retarget video stitching to an emerging issue, named warping shake, which unveils the temporal content shakes induced by sequentially unsmooth warps when extending image stitching to video stitching. Even if the input videos are stable, the stitched video can inevitably cause undesired warping shakes and affect the visual experience. To address this issue, we propose StabStitch++, a novel video stitching framework to realize spatial stitching and temporal stabilization with unsupervised learning simultaneously. First, different from existing learning-based image stitching solutions that typically warp one image to align with another, we suppose a virtual midplane between original image planes and project them onto it. Concretely, we design a differentiable bidirectional decomposition module to disentangle the homography transformation and incorporate it into our spatial warp, evenly spreading alignment burdens and projective distortions across two views. Then, inspired by camera paths in video stabilization, we derive the mathematical expression of stitching trajectories in video stitching by elaborately integrating spatial and temporal warps. Finally, a warp smoothing model is presented to produce stable stitched videos with a hybrid loss to simultaneously encourage content alignment, trajectory smoothness, and online collaboration. Compared with StabStitch that sacrifices alignment for stabilization, StabStitch++ makes no compromise and optimizes both of them simultaneously, especially in the online mode. To establish an evaluation benchmark and train the learning framework, we build a video stitching dataset with a rich diversity in camera motions and scenes. Experiments exhibit that StabStitch++ surpasses current solutions in stitching performance, robustness, and efficiency, offering compelling advancements in this field by building a real-time online video stitching system.

cs.CV↗

arXiv2025

NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results

This paper provides a review of the NTIRE 2025 challenge on real-world face restoration, highlighting the proposed solutions and the resulting outcomes. The challenge focuses on generating natural, realistic outputs while maintaining identity consistency. Its goal is to advance state-of-the-art solutions for perceptual quality and realism, without imposing constraints on computational resources or training data. The track of the challenge evaluates performance using a weighted image quality assessment (IQA) score and employs the AdaFace model as an identity checker. The competition attracted 141 registrants, with 13 teams submitting valid models, and ultimately, 10 teams achieved a valid score in the final ranking. This collaborative effort advances the performance of real-world face restoration while offering an in-depth overview of the latest trends in the field.

cs.CV↗

arXiv2025

InSPE: Rapid Evaluation of Heterogeneous Multi-Modal Infrastructure Sensor Placement

Infrastructure sensing is vital for traffic monitoring at safety hotspots (e.g., intersections) and serves as the backbone of cooperative perception in autonomous driving. While vehicle sensing has been extensively studied, infrastructure sensing has received little attention, especially given the unique challenges of diverse intersection geometries, complex occlusions, varying traffic conditions, and ambient environments like lighting and weather. To address these issues and ensure cost-effective sensor placement, we propose Heterogeneous Multi-Modal Infrastructure Sensor Placement Evaluation (InSPE), a perception surrogate metric set that rapidly assesses perception effectiveness across diverse infrastructure and environmental scenarios with combinations of multi-modal sensors. InSPE systematically evaluates perception capabilities by integrating three carefully designed metrics, i.e., sensor coverage, perception occlusion, and information gain. To support large-scale evaluation, we develop a data generation tool within the CARLA simulator and also introduce Infra-Set, a dataset covering diverse intersection types and environmental conditions. Benchmarking experiments with state-of-the-art perception algorithms demonstrate that InSPE enables efficient and scalable sensor placement analysis, providing a robust solution for optimizing intelligent intersection infrastructure.

cs.RO↗

arXiv2025

Multiscale Feature Importance-based Bit Allocation for End-to-End Feature Coding for Machines

Feature Coding for Machines (FCM) aims to compress intermediate features effectively for remote intelligent analytics, which is crucial for future intelligent visual applications. In this paper, we propose a Multiscale Feature Importance-based Bit Allocation (MFIBA) for end-to-end FCM. First, we find that the importance of features for machine vision tasks varies with the scales, object size, and image instances. Based on this finding, we propose a Multiscale Feature Importance Prediction (MFIP) module to predict the importance weight for each scale of features. Secondly, we propose a task loss-rate model to establish the relationship between the task accuracy losses of using compressed features and the bitrate of encoding these features. Finally, we develop a MFIBA for end-to-end FCM, which is able to assign coding bits of multiscale features more reasonably based on their importance. Experimental results demonstrate that when combined with a retained Efficient Learned Image Compression (ELIC), the proposed MFIBA achieves an average of 38.202% bitrate savings in object detection compared to the anchor ELIC. Moreover, the proposed MFIBA achieves an average of 17.212% and 36.492% feature bitrate savings for instance segmentation and keypoint detection, respectively. When the proposed MFIBA is applied to the LIC-TCM, it achieves an average of 18.103%, 19.866% and 19.597% bit rate savings on three machine vision tasks, respectively, which validates the proposed MFIBA has good generalizability and adaptability to different machine vision tasks and FCM base codecs.

cs.CV↗

arXiv2025

V2X-ReaLO: An Open Online Framework and Dataset for Cooperative Perception in Reality

Cooperative perception enabled by Vehicle-to-Everything (V2X) communication holds significant promise for enhancing the perception capabilities of autonomous vehicles, allowing them to overcome occlusions and extend their field of view. However, existing research predominantly relies on simulated environments or static datasets, leaving the feasibility and effectiveness of V2X cooperative perception especially for intermediate fusion in real-world scenarios largely unexplored. In this work, we introduce V2X-ReaLO, an open online cooperative perception framework deployed on real vehicles and smart infrastructure that integrates early, late, and intermediate fusion methods within a unified pipeline and provides the first practical demonstration of online intermediate fusion's feasibility and performance under genuine real-world conditions. Additionally, we present an open benchmark dataset specifically designed to assess the performance of online cooperative perception systems. This new dataset extends V2X-Real dataset to dynamic, synchronized ROS bags and provides 25,028 test frames with 6,850 annotated key frames in challenging urban scenarios. By enabling real-time assessments of perception accuracy and communication lantency under dynamic conditions, V2X-ReaLO sets a new benchmark for advancing and optimizing cooperative perception systems in real-world applications. The codes and datasets will be released to further advance the field.

cs.CV↗

arXiv2025

The excenters of bicentric polygons are concyclic

We show that the centers of the excircles of a bicentric polygon $B$ are concyclic on a circle $E$. The center of the circumscribed circle $K$ of $B$ is the midpoint of the center of $E$ and the center of the inscribed circle $C$ of $B$. The radius of $E$ is given by a simple formula in terms of the radii of $C$ and $K$ and the distance between their centers.

math.MG↗

arXiv2025

CBQ: Cross-Block Quantization for Large Language Models

Post-training quantization (PTQ) has played a key role in compressing large language models (LLMs) with ultra-low costs. However, existing PTQ methods only focus on handling the outliers within one layer or one block, which ignores the dependency of blocks and leads to severe performance degradation in low-bit settings. In this paper, we propose CBQ, a cross-block reconstruction-based PTQ method for LLMs. CBQ employs a cross-block dependency using a homologous reconstruction scheme, establishing long-range dependencies across multiple blocks to minimize error accumulation. Furthermore, CBQ incorporates a coarse-to-fine preprocessing (CFP) strategy for suppressing weight and activation outliers, coupled with an adaptive LoRA-Rounding technique for precise weight quantization. These innovations enable CBQ to not only handle extreme outliers effectively but also improve overall quantization accuracy. Extensive experiments show that CBQ achieves superior low-bit quantization (W4A4, W4A8, W2A16) and outperforms existing state-of-the-art methods across various LLMs and datasets. Notably, CBQ quantizes the 4-bit LLAMA1-65B model within only 4.3 hours on a single GPU, achieving a commendable tradeoff between performance and quantization efficiency.

cs.LG↗

arXiv2025

Deep-JGAC: End-to-End Deep Joint Geometry and Attribute Compression for Dense Colored Point Clouds

Colored point cloud becomes a fundamental representation in the realm of 3D vision. Effective Point Cloud Compression (PCC) is urgently needed due to huge amount of data. In this paper, we propose an end-to-end Deep Joint Geometry and Attribute point cloud Compression (Deep-JGAC) framework for dense colored point clouds, which exploits the correlation between the geometry and attribute for high compression efficiency. Firstly, we propose a flexible Deep-JGAC framework, where the geometry and attribute sub-encoders are compatible to either learning or non-learning based geometry and attribute encoders. Secondly, we propose an attribute-assisted deep geometry encoder that enhances the geometry latent representation with the help of attribute, where the geometry decoding remains unchanged. Moreover, Attribute Information Fusion Module (AIFM) is proposed to fuse attribute information in geometry coding. Thirdly, to solve the mismatch between the point cloud geometry and attribute caused by the geometry compression distortion, we present an optimized re-colorization module to attach the attribute to the geometrically distorted point cloud for attribute coding. It enhances the colorization and lowers the computational complexity. Extensive experimental results demonstrate that in terms of the geometry quality metric D1-PSNR, the proposed Deep-JGAC achieves an average of 82.96%, 36.46%, 41.72%, and 31.16% bit-rate reductions as compared to the state-of-the-art G-PCC, V-PCC, GRASP, and PCGCv2, respectively. In terms of perceptual joint quality metric MS-GraphSIM, the proposed Deep-JGAC achieves an average of 48.72%, 14.67%, and 57.14% bit-rate reductions compared to the G-PCC, V-PCC, and IT-DL-PCC, respectively. The encoding/decoding time costs are also reduced by 94.29%/24.70%, and 96.75%/91.02% on average as compared with the V-PCC and IT-DL-PCC.

cs.MM↗

arXiv2025

No-Reference Image Quality Assessment with Global-Local Progressive Integration and Semantic-Aligned Quality Transfer

Accurate measurement of image quality without reference signals remains a fundamental challenge in low-level visual perception applications. In this paper, we propose a global-local progressive integration model that addresses this challenge through three key contributions: 1) We develop a dual-measurement framework that combines vision Transformer (ViT)-based global feature extractor and convolutional neural networks (CNNs)-based local feature extractor to comprehensively capture and quantify image distortion characteristics at different granularities. 2) We propose a progressive feature integration scheme that utilizes multi-scale kernel configurations to align global and local features, and progressively aggregates them via an interactive stack of channel-wise self-attention and spatial interaction modules for multi-grained quality-aware representations. 3) We introduce a semantic-aligned quality transfer method that extends the training data by automatically labeling the quality scores of diverse image content with subjective opinion scores. Experimental results demonstrate that our model yields 5.04% and 5.40% improvements in Spearman's rank-order correlation coefficient (SROCC) for cross-authentic and cross-synthetic dataset generalization tests, respectively. Furthermore, the proposed semantic-aligned quality transfer further yields 2.26% and 13.23% performance gains in evaluations on single-synthetic and cross-synthetic datasets.

cs.CV↗

arXiv2025

An alternating approach for reconstructing the initial value and source term in a time-fractional diffusion-wave equation

This paper is dedicated to addressing the simultaneous inversion problem involving the initial value and space-dependent source term in a time-fractional diffusion-wave equation. Firstly, we establish the uniqueness of the inverse problem by leveraging the asymptotic expansion of Mittag-Leffler functions. Subsequently, we decompose the inverse problem into two subproblems and introduce an alternating iteration reconstruction method, complemented by a regularization strategy. Additionally, a comprehensive convergence analysis for this method is provided. To solve the inverse problem numerically, we introduce two semidiscrete schemes based on standard Galerkin method and lumped mass method, respectively. Furthermore, we establish error estimates that are associated with the noise level, iteration step, regularization parameter, and spatial discretization parameter. Finally, we present several numerical experiments in both one-dimensional and two-dimensional cases to validate the theoretical results and demonstrate the effectiveness of our proposed method.

math.NA↗

arXiv2025

The Dynamical State of the Didymos System Before and After the DART Impact

NASA's Double Asteroid Redirection Test (DART) spacecraft impacted Dimorphos, the natural satellite of (65803) Didymos, on 2022 September 26, as a first successful test of kinetic impactor technology for deflecting a potentially hazardous object in space. The experiment resulted in a small change to the dynamical state of the Didymos system consistent with expectations and Level 1 mission requirements. In the pre-encounter paper Richardson (2022), predictions were put forward regarding the pre- and post-impact dynamical state of the Didymos system. Here we assess these predictions, update preliminary findings published after the impact, report on new findings related to dynamics, and provide implications for ESA's Hera mission to Didymos, scheduled for launch in 2024 with arrival in late December 2026. Pre-encounter predictions tested to date are largely in line with observations, despite the unexpected, flattened appearance of Didymos compared to the radar model and the apparent pre-impact oblate shape of Dimorphos (with implications for the origin of the system that remain under investigation). New findings include that Dimorphos likely became prolate due to the impact and may have entered a tumbling rotation state. A possible detection of a post-impact transient secular decrease in the binary orbital period suggests possible dynamical coupling with persistent ejecta. Timescales for damping of any tumbling and clearing of any debris are uncertain. The largest uncertainty in the momentum transfer enhancement factor of the DART impact remains the mass of Dimorphos, which will be resolved by the Hera mission.

astro-ph.EP↗

arXiv2024

AgentAlign: Misalignment-Adapted Multi-Agent Perception for Resilient Inter-Agent Sensor Correlations

Cooperative perception has attracted wide attention given its capability to leverage shared information across connected automated vehicles (CAVs) and smart infrastructures to address sensing occlusion and range limitation issues. However, existing research overlooks the fragile multi-sensor correlations in multi-agent settings, as the heterogeneous agent sensor measurements are highly susceptible to environmental factors, leading to weakened inter-agent sensor interactions. The varying operational conditions and other real-world factors inevitably introduce multifactorial noise and consequentially lead to multi-sensor misalignment, making the deployment of multi-agent multi-modality perception particularly challenging in the real world. In this paper, we propose AgentAlign, a real-world heterogeneous agent cross-modality feature alignment framework, to effectively address these multi-modality misalignment issues. Our method introduces a cross-modality feature alignment space (CFAS) and heterogeneous agent feature alignment (HAFA) mechanism to harmonize multi-modality features across various agents dynamically. Additionally, we present a novel V2XSet-noise dataset that simulates realistic sensor imperfections under diverse environmental conditions, facilitating a systematic evaluation of our approach's robustness. Extensive experiments on the V2X-Real and V2XSet-Noise benchmarks demonstrate that our framework achieves state-of-the-art performance, underscoring its potential for real-world applications in cooperative autonomous driving. The controllable V2XSet-Noise dataset and generation pipeline will be released in the future.

cs.CV↗

arXiv2024

DT-JRD: Deep Transformer based Just Recognizable Difference Prediction Model for Video Coding for Machines

Just Recognizable Difference (JRD) represents the minimum visual difference that is detectable by machine vision, which can be exploited to promote machine vision oriented visual signal processing. In this paper, we propose a Deep Transformer based JRD (DT-JRD) prediction model for Video Coding for Machines (VCM), where the accurately predicted JRD can be used reduce the coding bit rate while maintaining the accuracy of machine tasks. Firstly, we model the JRD prediction as a multi-class classification and propose a DT-JRD prediction model that integrates an improved embedding, a content and distortion feature extraction, a multi-class classification and a novel learning strategy. Secondly, inspired by the perception property that machine vision exhibits a similar response to distortions near JRD, we propose an asymptotic JRD loss by using Gaussian Distribution-based Soft Labels (GDSL), which significantly extends the number of training labels and relaxes classification boundaries. Finally, we propose a DT-JRD based VCM to reduce the coding bits while maintaining the accuracy of object detection. Extensive experimental results demonstrate that the mean absolute error of the predicted JRD by the DT-JRD is 5.574, outperforming the state-of-the-art JRD prediction model by 13.1%. Coding experiments shows that comparing with the VVC, the DT-JRD based VCM achieves an average of 29.58% bit rate reduction while maintaining the object detection accuracy.

eess.IV↗

arXiv2024

LFIC-DRASC: Deep Light Field Image Compression Using Disentangled Representation and Asymmetrical Strip Convolution

Light-Field (LF) image is emerging 4D data of light rays that is capable of realistically presenting spatial and angular information of 3D scene. However, the large data volume of LF images becomes the most challenging issue in real-time processing, transmission, and storage. In this paper, we propose an end-to-end deep LF Image Compression method Using Disentangled Representation and Asymmetrical Strip Convolution (LFIC-DRASC) to improve coding efficiency. Firstly, we formulate the LF image compression problem as learning a disentangled LF representation network and an image encoding-decoding network. Secondly, we propose two novel feature extractors that leverage the structural prior of LF data by integrating features across different dimensions. Meanwhile, disentangled LF representation network is proposed to enhance the LF feature disentangling and decoupling. Thirdly, we propose the LFIC-DRASC for LF image compression, where two Asymmetrical Strip Convolution (ASC) operators, i.e. horizontal and vertical, are proposed to capture long-range correlation in LF feature space. These two ASC operators can be combined with the square convolution to further decouple LF features, which enhances the model ability in representing intricate spatial relationships. Experimental results demonstrate that the proposed LFIC-DRASC achieves an average of 20.5\% bit rate reductions comparing with the state-of-the-art methods.

eess.IV↗

arXiv2024

TSC-PCAC: Voxel Transformer and Sparse Convolution Based Point Cloud Attribute Compression for 3D Broadcasting

Point cloud has been the mainstream representation for advanced 3D applications, such as virtual reality and augmented reality. However, the massive data amounts of point clouds is one of the most challenging issues for transmission and storage. In this paper, we propose an end-to-end voxel Transformer and Sparse Convolution based Point Cloud Attribute Compression (TSC-PCAC) for 3D broadcasting. Firstly, we present a framework of the TSC-PCAC, which include Transformer and Sparse Convolutional Module (TSCM) based variational autoencoder and channel context module. Secondly, we propose a two-stage TSCM, where the first stage focuses on modeling local dependencies and feature representations of the point clouds, and the second stage captures global features through spatial and channel pooling encompassing larger receptive fields. This module effectively extracts global and local interpoint relevance to reduce informational redundancy. Thirdly, we design a TSCM based channel context module to exploit interchannel correlations, which improves the predicted probability distribution of quantized latent representations and thus reduces the bitrate. Experimental results indicate that the proposed TSC-PCAC method achieves an average of 38.53%, 21.30%, and 11.19% Bjontegaard Delta bitrate reductions compared to the Sparse-PCAC, NF-PCAC, and G-PCC v23 methods, respectively. The encoding/decoding time costs are reduced up to 97.68%/98.78% on average compared to the Sparse-PCAC. The source code and the trained models of the TSC-PCAC are available at https://github.com/igizuxo/TSC-PCAC.

cs.MM↗

arXiv2024

Multi-Granularity Semantic Revision for Large Language Model Distillation

Knowledge distillation plays a key role in compressing the Large Language Models (LLMs), which boosts a small-size student model under large teacher models' guidance. However, existing LLM distillation methods overly rely on student-generated outputs, which may introduce generation errors and misguide the distillation process. Moreover, the distillation loss functions introduced in previous art struggle to align the most informative part due to the complex distribution of LLMs' outputs. To address these problems, we propose a multi-granularity semantic revision method for LLM distillation. At the sequence level, we propose a sequence correction and re-generation (SCRG) strategy. SCRG first calculates the semantic cognitive difference between the teacher and student to detect the error token, then corrects it with the teacher-generated one, and re-generates the sequence to reduce generation errors and enhance generation diversity. At the token level, we design a distribution adaptive clipping Kullback-Leibler (DAC-KL) loss as the distillation objective function. DAC-KL loss exploits a learnable sub-network to adaptively extract semantically dense areas from the teacher's output, avoiding the interference of redundant information in the distillation process. Finally, at the span level, we leverage the span priors of a sequence to compute the probability correlations within spans, and constrain the teacher and student's probability correlations to be consistent, further enhancing the transfer of semantic information. Extensive experiments across different model families with parameters ranging from 0.1B to 13B demonstrate the superiority of our method compared to existing methods.

cs.CL↗

arXiv2024

Eliminating Warping Shakes for Unsupervised Online Video Stitching

In this paper, we retarget video stitching to an emerging issue, named warping shake, when extending image stitching to video stitching. It unveils the temporal instability of warped content in non-overlapping regions, despite image stitching having endeavored to preserve the natural structures. Therefore, in most cases, even if the input videos to be stitched are stable, the stitched video will inevitably cause undesired warping shakes and affect the visual experience. To eliminate the shakes, we propose StabStitch to simultaneously realize video stitching and video stabilization in a unified unsupervised learning framework. Starting from the camera paths in video stabilization, we first derive the expression of stitching trajectories in video stitching by elaborately integrating spatial and temporal warps. Then a warp smoothing model is presented to optimize them with a comprehensive consideration regarding content alignment, trajectory smoothness, spatial consistency, and online collaboration. To establish an evaluation benchmark and train the learning framework, we build a video stitching dataset with a rich diversity in camera motions and scenes. Compared with existing stitching solutions, StabStitch exhibits significant superiority in scene robustness and inference speed in addition to stitching and stabilization performance, contributing to a robust and real-time online video stitching system. The code and dataset are available at https://github.com/nie-lang/StabStitch.

cs.CV↗