arXiv subjects

Zhipeng Zhang

Publications and source records attributed to Zhipeng Zhang.

At least 91 records · Page 5Linked to original sources

arXiv2025

MambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object Detection

We present the first work demonstrating that a pure Mamba block can achieve efficient Dense Global Fusion, meanwhile guaranteeing top performance for camera-LiDAR multi-modal 3D object detection. Our motivation stems from the observation that existing fusion strategies are constrained by their inability to simultaneously achieve efficiency, long-range modeling, and retaining complete scene information. Inspired by recent advances in state-space models (SSMs) and linear attention, we leverage their linear complexity and long-range modeling capabilities to address these challenges. However, this is non-trivial since our experiments reveal that simply adopting efficient linear-complexity methods does not necessarily yield improvements and may even degrade performance. We attribute this degradation to the loss of height information during multi-modal alignment, leading to deviations in sequence order. To resolve this, we propose height-fidelity LiDAR encoding that preserves precise height information through voxel compression in continuous space, thereby enhancing camera-LiDAR alignment. Subsequently, we introduce the Hybrid Mamba Block, which leverages the enriched height-informed features to conduct local and global contextual learning. By integrating these components, our method achieves state-of-the-art performance with the top-tire NDS score of 75.0 on the nuScenes validation benchmark, even surpassing methods that utilize high-resolution inputs. Meanwhile, our method maintains efficiency, achieving faster inference speed than most recent state-of-the-art methods.

cs.CV↗

arXiv2025

MSF: Efficient Diffusion Model Via Multi-Scale Latent Factorize

While diffusion-based generative models have made significant strides in visual content creation, conventional approaches face computational challenges, especially for high-resolution images, as they denoise the entire image from noisy inputs. This contrasts with signal processing techniques, such as Fourier and wavelet analyses, which often employ hierarchical decompositions. Inspired by such principles, particularly the idea of signal separation, we introduce a diffusion framework leveraging multi-scale latent factorization. Our framework uniquely decomposes the denoising target, typically latent features from a pretrained Variational Autoencoder, into a low-frequency base signal capturing core structural information and a high-frequency residual signal that contributes finer, high-frequency details like textures. This decomposition into base and residual components directly informs our two-stage image generation process, which first produces the low-resolution base, followed by the generation of the high-resolution residual. Our proposed architecture facilitates reduced sampling steps during the residual learning stage, owing to the inherent ease of modeling residual information, which confers advantages over conventional full-resolution generation techniques. This specific approach of decomposing the signal into a base and a residual, conceptually akin to how wavelet analysis can separate different frequency bands, yields a more streamlined and intuitive design distinct from generic hierarchical models. Our method, \name\ (Multi-Scale Factorization), demonstrates its effectiveness by achieving FID scores of 2.08 ($256\times256$) and 2.47 ($512\times512$) on class-conditional ImageNet benchmarks, outperforming the DiT baseline (2.27 and 3.04 respectively) while also delivering a $4\times$ speed-up with the same number of sampling steps.

cs.CV↗

arXiv2025

EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models

Vision-Language-Action (VLA) models, particularly diffusion-based architectures, demonstrate transformative potential for embodied intelligence but are severely hampered by high computational and memory demands stemming from extensive inherent and inference-time redundancies. While existing acceleration efforts often target isolated inefficiencies, such piecemeal solutions typically fail to holistically address the varied computational and memory bottlenecks across the entire VLA pipeline, thereby limiting practical deployability. We introduce EfficientVLA, a structured and training-free inference acceleration framework that systematically eliminates these barriers by cohesively exploiting multifaceted redundancies. EfficientVLA synergistically integrates three targeted strategies: (1) pruning of functionally inconsequential layers from the language module, guided by an analysis of inter-layer redundancies; (2) optimizing the visual processing pathway through a task-aware strategy that selects a compact, diverse set of visual tokens, balancing task-criticality with informational coverage; and (3) alleviating temporal computational redundancy within the iterative diffusion-based action head by strategically caching and reusing key intermediate features. We apply our method to a standard VLA model CogACT, yielding a 1.93X inference speedup and reduces FLOPs to 28.9%, with only a 0.6% success rate drop in the SIMPLER benchmark.

cs.CV↗

arXiv2025

Underwater Camouflaged Object Tracking Meets Vision-Language SAM2

Over the past decade, significant progress has been made in visual object tracking, largely due to the availability of large-scale datasets. However, these datasets have primarily focused on open-air scenarios and have largely overlooked underwater animal tracking-especially the complex challenges posed by camouflaged marine animals. To bridge this gap, we take a step forward by proposing the first large-scale multi-modal underwater camouflaged object tracking dataset, namely UW-COT220. Based on the proposed dataset, this work first comprehensively evaluates current advanced visual object tracking methods, including SAM- and SAM2-based trackers, in challenging underwater environments, \eg, coral reefs. Our findings highlight the improvements of SAM2 over SAM, demonstrating its enhanced ability to handle the complexities of underwater camouflaged objects. Furthermore, we propose a novel vision-language tracking framework called VL-SAM2, based on the video foundation model SAM2. Extensive experimental results demonstrate that the proposed VL-SAM2 achieves state-of-the-art performance across underwater and open-air object tracking datasets. The dataset and codes are available at~{\color{magenta}{https://github.com/983632847/Awesome-Multimodal-Object-Tracking}}.

cs.CV↗

arXiv2025

More diverse more adaptive: Comprehensive Multi-task Learning for Improved LLM Domain Adaptation in E-commerce

In recent years, Large Language Models (LLMs) have been widely applied across various domains due to their powerful domain adaptation capabilities. Previous studies have suggested that diverse, multi-modal data can enhance LLMs' domain adaptation performance. However, this hypothesis remains insufficiently validated in the e-commerce sector. To address this gap, we propose a comprehensive e-commerce multi-task framework and design empirical experiments to examine the impact of diverse data and tasks on LLMs from two perspectives: "capability comprehensiveness" and "task comprehensiveness." Specifically, we observe significant improvements in LLM performance by progressively introducing tasks related to new major capability areas and by continuously adding subtasks within different major capability domains. Furthermore, we observe that increasing model capacity amplifies the benefits of diversity, suggesting a synergistic relationship between model capacity and data diversity. Finally, we validate the best-performing model from our empirical experiments in the KDD Cup 2024, achieving a rank 5 in Task 1. This outcome demonstrates the significance of our research for advancing LLMs in the e-commerce domain.

cs.CL↗

arXiv2025

Active Learning from Scene Embeddings for End-to-End Autonomous Driving

In the field of autonomous driving, end-to-end deep learning models show great potential by learning driving decisions directly from sensor data. However, training these models requires large amounts of labeled data, which is time-consuming and expensive. Considering that the real-world driving data exhibits a long-tailed distribution where simple scenarios constitute a majority part of the data, we are thus inspired to identify the most challenging scenarios within it. Subsequently, we can efficiently improve the performance of the model by training with the selected data of the highest value. Prior research has focused on the selection of valuable data by empirically designed strategies. However, manually designed methods suffer from being less generalizable to new data distributions. Observing that the BEV (Bird's Eye View) features in end-to-end models contain all the information required to represent the scenario, we propose an active learning framework that relies on these vectorized scene-level features, called SEAD. The framework selects initial data based on driving-environmental information and incremental data based on BEV features. Experiments show that we only need 30\% of the nuScenes training data to achieve performance close to what can be achieved with the full dataset. The source code will be released.

cs.CV↗

arXiv2025

OmniSTVG: Toward Spatio-Temporal Omni-Object Video Grounding

In this paper, we propose spatio-temporal omni-object video grounding, dubbed OmniSTVG, a new STVG task that aims at localizing spatially and temporally all targets mentioned in the textual query from videos. Compared to classic STVG locating only a single target, OmniSTVG enables localization of not only an arbitrary number of text-referred targets but also their interacting counterparts in the query from the video, making it more flexible and practical in real scenarios for comprehensive understanding. In order to facilitate exploration of OmniSTVG, we introduce BOSTVG, a large-scale benchmark dedicated to OmniSTVG. Specifically, our BOSTVG consists of 10,018 videos with 10.2M frames and covers a wide selection of 287 classes from diverse scenarios. Each sequence in BOSTVG, paired with a free-form textual query, encompasses a varying number of targets ranging from 1 to 10. To ensure high quality, each video is manually annotated with meticulous inspection and refinement. To our best knowledge, BOSTVG is to date the first and the largest benchmark for OmniSTVG. To encourage future research, we introduce a simple yet effective approach, named OmniTube, which, drawing inspiration from Transformer-based STVG methods, is specially designed for OmniSTVG and demonstrates promising results. By releasing BOSTVG, we hope to go beyond classic STVG by locating every object appearing in the query for more comprehensive understanding, opening up a new direction for STVG. Our benchmark, model, and results will be released at https://github.com/JellyYao3000/OmniSTVG.

cs.CV↗

arXiv2025

Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization

Representing 3D scenes from multiview images is a core challenge in computer vision and graphics, which requires both precise rendering and accurate reconstruction. Recently, 3D Gaussian Splatting (3DGS) has garnered significant attention for its high-quality rendering and fast inference speed. Yet, due to the unstructured and irregular nature of Gaussian point clouds, ensuring accurate geometry reconstruction remains difficult. Existing methods primarily focus on geometry regularization, with common approaches including primitive-based and dual-model frameworks. However, the former suffers from inherent conflicts between rendering and reconstruction, while the latter is computationally and storage-intensive. To address these challenges, we propose CarGS, a unified model leveraging Contribution-adaptive regularization to achieve simultaneous, high-quality rendering and surface reconstruction. The essence of our framework is learning adaptive contribution for Gaussian primitives by squeezing the knowledge from geometry regularization into a compact MLP. Additionally, we introduce a geometry-guided densification strategy with clues from both normals and Signed Distance Fields (SDF) to improve the capability of capturing high-frequency details. Our design improves the mutual learning of the two tasks, meanwhile its unified structure does not require separate models as in dual-model based approaches, guaranteeing efficiency. Extensive experiments demonstrate the ability to achieve state-of-the-art (SOTA) results in both rendering fidelity and reconstruction accuracy while maintaining real-time speed and minimal storage size.

cs.CV↗

arXiv2025

The chemisorption thermodynamics of O$_2$ and H$_2$O on AFM UO$_2$ surfaces unraveled by DFT+U-D3 study

Unraveling the adsorption mechanism and thermodynamics of O$_2$ and H$_2$O on uranium dioxide surfaces is critical for the nuclear fuel storage and uranium corrosion. Based on the first-principles DFT+U-D3 calculations, we carefully test the effect of antiferromagnetic order arrangements on the thermodynamic stability of UO$_2$ surfaces and propose the 1k AFM surface computational model. The chemisorption states of O$_2$ and H$_2$O on UO$_2$ (111) surface, suggested by previous experiments, are accurately calculated for the first time. The adsorption properties of O$_2$ and H$_2$O on UO$_2$(111) and (110) surfaces are discussed in detail to reveal the different interaction mechanisms. Combined with ab initio atomistic thermodynamics method, we systematically calculate the chemisorption phase diagram and isotherm of O$_2$ and H$_2$O on UO$_2$ surfaces. Due to the different intermolecular interactions, the monolayer and multilayer adsorption models are identified for O$_2$ and H$_2$O, respectively. This study has comprehensively revealed the different adsorption mechanisms of O$_2$ and H$_2$O on UO$_2$ surfaces, bridging the electronic structure calculations to the interpretation of experimental results and providing a solid foundation for future theoretical studies of uranium corrosion mechanism in humid air.

cond-mat.mtrl-sci↗

arXiv2024

Contourlet Refinement Gate Framework for Thermal Spectrum Distribution Regularized Infrared Image Super-Resolution

Image super-resolution (SR) is a classical yet still active low-level vision problem that aims to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts, serving as a key technique for image enhancement. Current approaches to address SR tasks, such as transformer-based and diffusion-based methods, are either dedicated to extracting RGB image features or assuming similar degradation patterns, neglecting the inherent modal disparities between infrared and visible images. When directly applied to infrared image SR tasks, these methods inevitably distort the infrared spectral distribution, compromising the machine perception in downstream tasks. In this work, we emphasize the infrared spectral distribution fidelity and propose a Contourlet refinement gate framework to restore infrared modal-specific features while preserving spectral distribution fidelity. Our approach captures high-pass subbands from multi-scale and multi-directional infrared spectral decomposition to recover infrared-degraded information through a gate architecture. The proposed Spectral Fidelity Loss regularizes the spectral frequency distribution during reconstruction, which ensures the preservation of both high- and low-frequency components and maintains the fidelity of infrared-specific features. We propose a two-stage prompt-learning optimization to guide the model in learning infrared HR characteristics from LR degradation. Extensive experiments demonstrate that our approach outperforms existing image SR models in both visual and perceptual tasks while notably enhancing machine perception in downstream tasks. Our code is available at https://github.com/hey-it-s-me/CoRPLE.

cs.CV↗

arXiv2024

Piecewise constant tuning gain based singularity-free MRAC with application to aircraft control systems

This paper introduces an innovative singularity-free output feedback model reference adaptive control (MRAC) method applicable to a wide range of continuous-time linear time-invariant (LTI) systems with general relative degrees. Unlike existing solutions such as Nussbaum and multiple-model-based methods, which manage unknown high-frequency gains through persistent switching and repeated parameter estimation, the proposed method circumvents these issues without prior knowledge of the high-frequency gain or additional design conditions. The key innovation of this method lies in transforming the estimation error equation into a linear regression form via a modified MRAC law with a piecewise constant tuning gain developed in this work. This represents a significant departure from existing MRAC systems, where the estimation error equation is typically in a bilinear regression form. The linear regression form facilitates the direct estimation of all unknown parameters, thereby simplifying the adaptive control process. The proposed method preserves closed-loop stability and ensures asymptotic output tracking, overcoming some of the limitations associated with existing methods like Nussbaum and multiple-model based methods. The practical efficacy of the developed MRAC method is demonstrated through detailed simulation results within an aircraft control system scenario.

eess.SY↗

arXiv2024

Layout optimization and Performance of Large Array of imaging atmospheric Cherenkov Telescope (LACT)

Large Array of imaging atmospheric Cherenkov Telescope (LACT) is an array of 32 Cherenkov telescopes with 6-meter diameter mirrors to be constructed at the LHAASO site. In this work, we present a study on the layout optimization and performance analysis of LACT. We investigate two observation modes: large zenith angle observations for ultra-high energy events and small zenith angle observations for lower energy thresholds. For large zenith angles (60°), simulations show that an 8-telescope subarray can achieve an effective area of $3 ~\rm km^2$ and excellent angular resolution. For small zenith angles, we optimize the layout of 4-telescope cells and the full 32-telescope array. The threshold of the full array is about $200~\rm GeV$, which is particularly crucial for studying transient phenomena, including gamma-ray bursts (GRBs) and active galactic nuclei (AGNs). This study provides important guidance for the final LACT layout design and performance estimates under different observational conditions, demonstrating LACT's potential for deep observations of ultra-high energy \gray sources and morphological studies of PeVatrons, as well as time-domain \gray astronomy.

astro-ph.HE↗

arXiv2024

Prospects for joint reconstruction of imaging air Cherenkov Telescope array and extensive air shower array

In this paper we proposed a joint reconstruction of \gray events using both extensive air array (EAS) and Imaging air Cherenkov Telescope array (IACT). We considered eight Cherenkov telescopes to be built on the LHAASO (Large High Altitude Air Shower Observatory) site and investigate the improvement in differential sensitivity when combining the information from both IACT and Moun detectors of LHAASO-KM2A. We found that due to the higher cosmic ray background rejection power and higher gamma ray retention ratio provided by muon detectors of LHAASO, such a joint reconstruction can significantly improve the sensitivity of IACTs, especially for extended sources and long exposure time. In this article, we have shown the performance of an eight-telescopes mini array, and our results indicate that above $10~\rm TeV$, the sensitivity can be improved by muon detector from $25\% - 60\%$ in different energy ranges.

astro-ph.HE↗

arXiv2024

Temporal Correlation Meets Embedding: Towards a 2nd Generation of JDE-based Real-Time Multi-Object Tracking

Joint Detection and Embedding (JDE) trackers have demonstrated excellent performance in Multi-Object Tracking (MOT) tasks by incorporating the extraction of appearance features as auxiliary tasks through embedding Re-Identification task (ReID) into the detector, achieving a balance between inference speed and tracking performance. However, solving the competition between the detector and the feature extractor has always been a challenge. Meanwhile, the issue of directly embedding the ReID task into MOT has remained unresolved. The lack of high discriminability in appearance features results in their limited utility. In this paper, a new learning approach using cross-correlation to capture temporal information of objects is proposed. The feature extraction network is no longer trained solely on appearance features from each frame but learns richer motion features by utilizing feature heatmaps from consecutive frames, which addresses the challenge of inter-class feature similarity. Furthermore, our learning approach is applied to a more lightweight feature extraction network, and treat the feature matching scores as strong cues rather than auxiliary cues, with an appropriate weight calculation to reflect the compatibility between our obtained features and the MOT task. Our tracker, named TCBTrack, achieves state-of-the-art performance on multiple public benchmarks, i.e., MOT17, MOT20, and DanceTrack datasets. Specifically, on the DanceTrack test set, we achieve 56.8 HOTA, 58.1 IDF1 and 92.5 MOTA, making it the best online tracker capable of achieving real-time performance. Comparative evaluations with other trackers prove that our tracker achieves the best balance between speed, robustness and accuracy. Code is available at https://github.com/yfzhang1214/TCBTrack.

cs.CV↗

arXiv2024

Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance

Motivated by the Parameter-Efficient Fine-Tuning (PEFT) in large language models, we propose LoRAT, a method that unveils the power of large ViT model for tracking within laboratory-level resources. The essence of our work lies in adapting LoRA, a technique that fine-tunes a small subset of model parameters without adding inference latency, to the domain of visual tracking. However, unique challenges and potential domain gaps make this transfer not as easy as the first intuition. Firstly, a transformer-based tracker constructs unshared position embedding for template and search image. This poses a challenge for the transfer of LoRA, usually requiring consistency in the design when applied to the pre-trained backbone, to downstream tasks. Secondly, the inductive bias inherent in convolutional heads diminishes the effectiveness of parameter-efficient fine-tuning in tracking models. To overcome these limitations, we first decouple the position embeddings in transformer-based trackers into shared spatial ones and independent type ones. The shared embeddings, which describe the absolute coordinates of multi-resolution images (namely, the template and search images), are inherited from the pre-trained backbones. In contrast, the independent embeddings indicate the sources of each token and are learned from scratch. Furthermore, we design an anchor-free head solely based on MLP to adapt PETR, enabling better performance with less computational overhead. With our design, 1) it becomes practical to train trackers with the ViT-g backbone on GPUs with only memory of 25.8GB (batch size of 16); 2) we reduce the training time of the L-224 variant from 35.0 to 10.8 GPU hours; 3) we improve the LaSOT SUC score from 0.703 to 0.742 with the L-224 variant; 4) we fast the inference speed of the L-224 variant from 52 to 119 FPS. Code and models are available at https://github.com/LitingLin/LoRAT.

cs.CV↗

arXiv2024

Image Fusion via Vision-Language Model

Image fusion integrates essential information from multiple images into a single composite, enhancing structures, textures, and refining imperfections. Existing methods predominantly focus on pixel-level and semantic visual features for recognition, but often overlook the deeper text-level semantic information beyond vision. Therefore, we introduce a novel fusion paradigm named image Fusion via vIsion-Language Model (FILM), for the first time, utilizing explicit textual information from source images to guide the fusion process. Specifically, FILM generates semantic prompts from images and inputs them into ChatGPT for comprehensive textual descriptions. These descriptions are fused within the textual domain and guide the visual information fusion, enhancing feature extraction and contextual understanding, directed by textual semantic information via cross-attention. FILM has shown promising results in four image fusion tasks: infrared-visible, medical, multi-exposure, and multi-focus image fusion. We also propose a vision-language dataset containing ChatGPT-generated paragraph descriptions for the eight image fusion datasets across four fusion tasks, facilitating future research in vision-language model-based image fusion. Code and dataset are available at https://github.com/Zhaozixiang1228/IF-FILM.

cs.CV↗

arXiv2024

Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache

Large Language Models (LLMs) demonstrate substantial potential across a diverse array of domains via request serving. However, as trends continue to push for expanding context sizes, the autoregressive nature of LLMs results in highly dynamic behavior of the attention layers, showcasing significant differences in computational characteristics and memory requirements from the non-attention layers. This presents substantial challenges for resource management and performance optimization in service systems. Existing static model parallelism and resource allocation strategies fall short when dealing with this dynamicity. To address the issue, we propose Infinite-LLM, a novel LLM serving system designed to effectively handle dynamic context lengths. Infinite-LLM disaggregates attention layers from an LLM's inference process, facilitating flexible and independent resource scheduling that optimizes computational performance and enhances memory utilization jointly. By leveraging a pooled GPU memory strategy across a cluster, Infinite-LLM not only significantly boosts system throughput but also supports extensive context lengths. Evaluated on a dataset with context lengths ranging from a few to 2000K tokens across a cluster with 32 A100 GPUs, Infinite-LLM demonstrates throughput improvement of 1.35-3.4x compared to state-of-the-art methods, enabling efficient and elastic LLM deployment.

cs.DC↗

arXiv2024

Cyclic Refiner: Object-Aware Temporal Representation Learning for Multi-View 3D Detection and Tracking

We propose a unified object-aware temporal learning framework for multi-view 3D detection and tracking tasks. Having observed that the efficacy of the temporal fusion strategy in recent multi-view perception methods may be weakened by distractors and background clutters in historical frames, we propose a cyclic learning mechanism to improve the robustness of multi-view representation learning. The essence is constructing a backward bridge to propagate information from model predictions (e.g., object locations and sizes) to image and BEV features, which forms a circle with regular inference. After backward refinement, the responses of target-irrelevant regions in historical frames would be suppressed, decreasing the risk of polluting future frames and improving the object awareness ability of temporal fusion. We further tailor an object-aware association strategy for tracking based on the cyclic learning model. The cyclic learning model not only provides refined features, but also delivers finer clues (e.g., scale level) for tracklet association. The proposed cycle learning method and association module together contribute a novel and unified multi-task framework. Experiments on nuScenes show that the proposed model achieves consistent performance gains over baselines of different designs (i.e., dense query-based BEVFormer, sparse query-based SparseBEV and LSS-based BEVDet4D) on both detection and tracking evaluation.

cs.CV↗