arXiv subjects

Zhenyu He

Publications and source records attributed to Zhenyu He.

At least 19 recordsLinked to original sources

arXiv2026

Efficient RGB-T Object Detection via Sparse Cross-Modality Fusion

RGB-T detectors leverage the complementary strengths of visible and thermal infrared modalities, achieving robust performance under challenging conditions. Many of them resort to heavy dual backbones and exhaustive cross-modality fusion across the entire image, leading to impractically high computational costs. We observe that most image regions are smooth backgrounds (e.g., sky, ground) that can be easily handled by lightweight single-modality models. In light of this observation, we propose a sparse fusion mechanism for efficient RGB-T detection: first rapidly scanning the image to identify the proposals and then carefully examining the remaining sparse proposals via feature fusion. We propose a two-stage framework to instantiate this mechanism, which performs detection in two stages: 1) a lightweight and modality-specific detection stage that produces high-recall RoIs, and 2) a fusion-driven examination and refinement stage that filters out the false positives and refines the bounding boxes. This design enables the detector to adaptively allocate more computational resources to the potential foregrounds, improving the efficiency while ensuring detection accuracy. Extensive experiments show that our method achieves competitive performance with substantially fewer parameters and lower cost, while maintaining strong scalability to high-resolution images.

cs.CV↗

arXiv2026

Lossless Anti-Distillation Sampling

Frontier commercial generative models face a growing threat from distillation, whereby a distiller harvests generated responses and trains a competing model of its own at drastically lower cost. Existing defenses either rely on modifying the models outputs, thereby sacrificing response quality for benign users, or on behavioral detection methods, which can be readily circumvented by distributing queries across multiple accounts. In this work, we propose Lossless Anti-Distillation Sampling (LADS), a novel sampling scheme specifically designed to counter multi-account distillation while maintaining a lossless experience for benign users. Concretely, LADS derives the randomness underlying each generation from a private seed determined by the semantic content of the query and the number of times the user has queried the model. By construction, every benign user receives a response independently sampled from the original model at each visit, and thus experiences no distortion. In contrast, for a distiller, different accounts share latent randomness whenever their queries fall in the same semantic bucket. As a result, the harvested data becomes correlated, potentially reducing sample diversity and degrading generalization. Using uniform convergence theory, we show that LADS provably degrades the convergence rate of the distillers generalization gap relative to standard i.i.d. sampling in both unconditional and conditional generation settings. Experiments on image generation, mathematical reasoning, and code generation confirm that LADS substantially degrades the performance of distilled students while preserving exact statistical fidelity for individual users.

cs.LG↗

arXiv2026

Computer-Aided Design Generation by Cascaded Discrete Diffusion Model

Recent deep learning approaches seek to automate CAD creation by representing a model as a sequence of discrete commands and parameters, and then generating them using autoregressive models or continuous diffusion operating in Euclidean embedding space. However, continuous diffusion perturbs representations in a continuous Euclidean domain that does not reflect the inherently discrete and heterogeneous nature of CAD tokens, often producing perturbed representations that map to semantically invalid symbols. To overcome this limitation, we propose a cascaded discrete diffusion framework for CAD generation, which consists of a command diffusion for generating CAD commands and a parameter diffusion conditioned on CAD commands. Unlike isotropic Gaussian perturbation, the forward process of our approach operates directly over categorical token distributions using delicate transition matrices. For commands, we adopt an absorbing-state transition matrix that progressively corrupts tokens to a designated symbol; for parameters, we introduce specific transition matrices tailored to heterogeneous attributes: a Gaussian kernel for coordinate continuity, a scale-invariant kernel for dimensional values, and a prior-preserving kernel for boolean attributes. The reverse process is achieved by two denoising networks: a Transformer-based encoder for command recovery, and a parameter network with extra local self-attention for command-level interaction and cross-attention for conditional injection. Experiments on the DeepCAD dataset show that the proposed approach surpasses existing autoregressive and continuous diffusion models on unconditional generation metrics, while qualitative results validate effective controllability in conditional generation tasks. Source codes will be released.

cs.CV↗

arXiv2026

Drift-Resilient Temporal Priors for Visual Tracking

Temporal information is crucial for visual tracking, but existing multi-frame trackers are vulnerable to model drift caused by naively aggregating noisy historical predictions. In this paper, we introduce DTPTrack, a lightweight and generalizable module designed to be seamlessly integrated into existing trackers to suppress drift. Our framework consists of two core components: (1) a Temporal Reliability Calibrator (TRC) mechanism that learns to assign a per-frame reliability score to historical states, filtering out noise while anchoring on the ground-truth template; and (2) a Temporal Guidance Synthesizer (TGS) module that synthesizes this calibrated history into a compact set of dynamic temporal priors to provide predictive guidance. To demonstrate its versatility, we integrate DTPTrack into three diverse tracking architectures--OSTrack, ODTrack, and LoRAT-and show consistent, significant performance gains across all baselines. Our best-performing model, built upon an extended LoRATv2 backbone, sets a new state-of-the-art on several benchmarks, achieving a 77.5% Success rate on LaSOT and an 80.3% AO on GOT-10k.

cs.CV↗

arXiv2026

Interactive Tracking: A Human-in-the-Loop Paradigm with Memory-Augmented Adaptation

Existing visual trackers mainly operate in a non-interactive, fire-and-forget manner, making them impractical for real-world scenarios that require human-in-the-loop adaptation. To overcome this limitation, we introduce Interactive Tracking, a new paradigm that allows users to guide the tracker at any time using natural language commands. To support research in this direction, we make three main contributions. First, we present InteractTrack, the first large-scale benchmark for interactive tracking, containing 150 videos with dense bounding box annotations and timestamped language instructions. Second, we propose a comprehensive evaluation protocol and evaluate 25 representative trackers, showing that state-of-the-art methods fail in interactive scenarios; strong performance on conventional benchmarks does not transfer. Third, we introduce Interactive Memory-Augmented Tracking (IMAT), a new baseline that employs a dynamic memory mechanism to learn from user feedback and update tracking behavior accordingly. Our benchmark, protocol, and baseline establish a foundation for developing more intelligent, adaptive, and collaborative tracking systems, bridging the gap between automated perception and human guidance. The full benchmark, tracking results, and analysis are available at https://github.com/NorahGreen/InteractTrack.git.

cs.CV↗

arXiv2026

Fusing in 3D: Free-Viewpoint Fusion Rendering with a 3D Infrared-Visible Scene Representation

Infrared-visible image fusion aims to integrate infrared and visible information into a single fused image. Existing 2D fusion methods focus on fusing images from fixed camera viewpoints, neglecting a comprehensive understanding of complex scenarios, which results in the loss of critical information about the scene. To address this limitation, we propose a novel Infrared-Visible Gaussian Fusion (IVGF) framework, which reconstructs scene geometry from multimodal 2D inputs and enables direct rendering of fused images. Specifically, we propose a cross-modal adjustment (CMA) module that modulates the opacity of Gaussians to solve the problem of cross-modal conflicts. Moreover, to preserve the distinctive features from both modalities, we introduce a fusion loss that guides the optimization of CMA, thus ensuring that the fused image retains the critical characteristics of each modality. Comprehensive qualitative and quantitative experiments demonstrate the effectiveness of the proposed method.

cs.CV↗

arXiv2026

Modality-Decoupled RGB-Thermal Object Detector via Query Fusion

The advantage of RGB-Thermal (RGB-T) detection lies in its ability to perform modality fusion and integrate cross-modality complementary information, enabling robust detection under diverse illumination and weather conditions. However, under extreme conditions where one modality exhibits poor quality and disturbs detection, modality separation is necessary to mitigate the impact of noise. To address this problem, we propose a Modality-Decoupled RGB-T detection framework with Query Fusion (MDQF) to balance modality complementation and separation. In this framework, DETR-like detectors are employed as separate branches for the RGB and TIR images, with query fusion interspersed between the two branches in each refinement stage. Herein, query fusion is performed by feeding the high-quality queries from one branch to the other one after query selection and adaptation. This design effectively excludes the degraded modality and corrects the predictions using high-quality queries. Moreover, the decoupled framework allows us to optimize each individual branch with unpaired RGB or TIR images, eliminating the need for paired RGB-T data. Extensive experiments demonstrate that our approach delivers superior performance to existing RGB-T detectors and achieves better modality independence.

cs.CV↗

arXiv2025

FusionFM: All-in-One Multi-Modal Image Fusion with Flow Matching

Current multi-modal image fusion methods typically rely on task-specific models, leading to high training costs and limited scalability. While generative methods provide a unified modeling perspective, they often suffer from slow inference due to the complex sampling trajectories from noise to image. To address this, we formulate image fusion as a direct probabilistic transport from source modalities to the fused image distribution, leveraging the flow matching paradigm to improve sampling efficiency and structural consistency. To mitigate the lack of high-quality fused images for supervision, we collect fusion results from multiple state-of-the-art models as priors, and employ a task-aware selection function to select the most reliable pseudo-labels for each task. We further introduce a Fusion Refiner module that employs a divide-and-conquer strategy to systematically identify, decompose, and enhance degraded components in selected pseudo-labels. For multi-task scenarios, we integrate elastic weight consolidation and experience replay mechanisms to preserve cross-task performance and enhance continual learning ability from both parameter stability and memory retention perspectives. Our approach achieves competitive performance across diverse fusion tasks, while significantly improving sampling efficiency and maintaining a lightweight model design. The code will be available at: https://github.com/Ist-Zhy/FusionFM.

cs.CV↗

arXiv2025

Multi-Channel Amplitude-Phase Asymmetric-Encrypted Janus Acoustic Meta-Holograms

Encrypted optical and acoustic meta-holograms only focus on the encrypted hologram in a single channel, viz. modulating spatial amplitude to project a holographic image. In this research, the unique concept of multi-channel amplitude-phase asymmetric-encrypted Janus acoustic meta-holograms is proposed, demonstrating remarkable capabilities of generating, encrypting, and decrypting both amplitude and phase holographic images on both sides of a metascreen. The flexible and decoupled manipulation mechanism for the amplitude-phase of the bidirectional acoustic waves used in our concept offers multiple possibilities to apply various encryption methods. In this work, our system enables single-input, two-faced four-channel asymmetric encryption, which substantially increase the communication capacity of conventional acoustic holograms, and establish a security framework based on mathematical problem, proving its security. Our work can lead to concrete applications including, but not limited to, multi-channel acoustic field communications and acoustic illusion and cloaking in non-transparent media.

physics.app-ph↗

arXiv2025

New Determination of the $^{14}$C(n, $\gamma$)$^{15}$C Reaction Rate and Its Astrophysical Implications

We present a novel experiment to investigate the spectroscopic factor of the $^{15}$C ground state for the first time using single-neutron $removal$ transfer reactions on $^{15}$C. Two consistent spectroscopic factors were derived from the (p, d) and (d, t) reactions, which were subsequently used to deduce the $^{14}$C(n, $\gamma$)$^{15}$C reaction cross section and the corresponding stellar reaction rate. A typical cross section of (3.89 $\pm$ 0.76) $\mu$b is determined at $E_\mathrm{_{c.m.}}$ = 23.3 keV. At the temperature range of 0.01-4 GK, our new reaction rate is 2.4-3.7 times higher than that of the first direct measurement and 20\%-25\% lower than that of the most recent direct measurement, respectively. Moreover, it is interesting that we can associate a long-standing nuclear structure issue, i.e., the so-called ``quenching'' effect, with this astrophysically relevant reaction. Finally, motivated by astrophysical interests of this reaction decades ago, implications of our new rate on several astrophysical problems are evaluated using state-of-the-art theoretical models. Our calculations demonstrate that the abundances of $^{14}$N and $^{15}$N can be enhanced in the inner regions of asymptotic giant branch (AGB) stars, though with minimal impact on the chemical compositions of the interstellar medium. In the inhomogeneous Big Bang nucleosynthesis, the updated reaction rate can lead to a $\sim 20\%$ variation in the final yields of $^{15}$N in neutron rich regions. For the $r$-process in the core-collapse supernovae, a slight difference of $\sim 0.2\%$ in the final abundances of heavy elements with $A > 90$ can be found by using our new rate.

nucl-ex↗

arXiv2025

Learning A Robust RGB-Thermal Detector for Extreme Modality Imbalance

RGB-Thermal (RGB-T) object detection utilizes thermal infrared (TIR) images to complement RGB data, improving robustness in challenging conditions. Traditional RGB-T detectors assume balanced training data, where both modalities contribute equally. However, in real-world scenarios, modality degradation-due to environmental factors or technical issues-can lead to extreme modality imbalance, causing out-of-distribution (OOD) issues during testing and disrupting model convergence during training. This paper addresses these challenges by proposing a novel base-and-auxiliary detector architecture. We introduce a modality interaction module to adaptively weigh modalities based on their quality and handle imbalanced samples effectively. Additionally, we leverage modality pseudo-degradation to simulate real-world imbalances in training data. The base detector, trained on high-quality pairs, provides a consistency constraint for the auxiliary detector, which receives degraded samples. This framework enhances model robustness, ensuring reliable performance even under severe modality degradation. Experimental results demonstrate the effectiveness of our method in handling extreme modality imbalances~(decreasing the Missing Rate by 55%) and improving performance across various baseline detectors.

cs.CV↗

arXiv2025

An Actinide-boost Star Discovered in the Gaia-Sausage-Enceladus

We report the discovery of an actinide-boost, very metal-poor ($\left[\mathrm{Fe/H} \right]=-2.38$), $r$-process-enhanced ($\left[\mathrm{Eu/Fe} \right]=0.80$) star, LAMOST J0804+5740, within the Gaia-Sausage-Enceladus (GSE). Based on the high-resolution ($R\sim36,000\; and \;60,000$) and high signal-to-noise ratio spectra obtained with the High Dispersion Spectrograph on the Subaru Telescope, the abundances of 48 species are determined. Its $\log\epsilon\rm(\mathrm{Th}/\mathrm{Eu}) = -0.22 $ establishes it as the first confirmed actinide-boost star within the GSE. Comparative analysis of its abundance pattern with theoretical $r$-process models reveals that the magnetorotationally driven jet supernova $r$-process model with $\hat{L}v$ = 0.2 provides the best fit and successfully reproduces the actinide-boost signature. Kinematic analysis of actinide-boost stars reveals that approximately two-thirds of them are classified as $\textit{ex-situ}$ stars, suggesting that actinide-boost stars are more likely to originate from accreted dwarf galaxies. As the first actinide-boost star identified within the GSE, J0804+5740 will provide valuable insights into $r$-process nucleosynthesis in accreted dwarf galaxies like the GSE, especially on the production of the heaviest elements.

astro-ph.SR↗

arXiv2025

Enhancing Auto-regressive Chain-of-Thought through Loop-Aligned Reasoning

Chain-of-Thought (CoT) prompting has emerged as a powerful technique for enhancing language model's reasoning capabilities. However, generating long and correct CoT trajectories is challenging. Recent studies have demonstrated that Looped Transformers possess remarkable length generalization capabilities, but their limited generality and adaptability prevent them from serving as an alternative to auto-regressive solutions. To better leverage the strengths of Looped Transformers, we propose RELAY (REasoning through Loop Alignment iterativelY). Specifically, we align the steps of Chain-of-Thought (CoT) reasoning with loop iterations and apply intermediate supervision during the training of Looped Transformers. This additional iteration-wise supervision not only preserves the Looped Transformer's ability for length generalization but also enables it to predict CoT reasoning steps for unseen data. Therefore, we leverage this Looped Transformer to generate accurate reasoning chains for complex problems that exceed the training length, which will then be used to fine-tune an auto-regressive model. We conduct extensive experiments, and the results demonstrate the effectiveness of our approach, with significant improvements in the performance of the auto-regressive model. Code will be released at https://github.com/qifanyu/RELAY.

cs.CL↗

arXiv2025

ZeroBP: Learning Position-Aware Correspondence for Zero-shot 6D Pose Estimation in Bin-Picking

Bin-picking is a practical and challenging robotic manipulation task, where accurate 6D pose estimation plays a pivotal role. The workpieces in bin-picking are typically textureless and randomly stacked in a bin, which poses a significant challenge to 6D pose estimation. Existing solutions are typically learning-based methods, which require object-specific training. Their efficiency of practical deployment for novel workpieces is highly limited by data collection and model retraining. Zero-shot 6D pose estimation is a potential approach to address the issue of deployment efficiency. Nevertheless, existing zero-shot 6D pose estimation methods are designed to leverage feature matching to establish point-to-point correspondences for pose estimation, which is less effective for workpieces with textureless appearances and ambiguous local regions. In this paper, we propose ZeroBP, a zero-shot pose estimation framework designed specifically for the bin-picking task. ZeroBP learns Position-Aware Correspondence (PAC) between the scene instance and its CAD model, leveraging both local features and global positions to resolve the mismatch issue caused by ambiguous regions with similar shapes and appearances. Extensive experiments on the ROBI dataset demonstrate that ZeroBP outperforms state-of-the-art zero-shot pose estimation methods, achieving an improvement of 9.1% in average recall of correct poses.

cs.CV↗

arXiv2024

Deep learning for nuclear masses in deformed relativistic Hartree-Bogoliubov theory in continuum

Most nuclei are deformed, and these deformations play an important role in various nuclear and astrophysical phenomena. Microscopic nuclear mass models have been developed based on covariant density functional theory to explore exotic nuclear properties. Among these, we adopt mass models based on the relativistic continuum Hartree-Bogoliubov theory (RCHB) with spherical symmetry and the deformed relativistic Hartree-Bogoliubov theory in continuum (DRHBc) with axial symmetry to study the effects of deformation on the abundances produced during the rapid neutron-capture process (r-process). Since the DRHBc mass table has so far been completed only for even-Z nuclei, we first investigate whether a Deep Neural Network (DNN) can be used to extend the DRHBc mass table by focusing on nuclear binding energies. To incorporate information about odd-odd and odd-even isotopes into the DNN, we also use binding energies from AME2020 as a training set, in addition to those from the DRHBc mass table for even-Z nuclei. After generating an improved mass table through the DNN study, we conduct a sensitivity analysis of r-process abundances to deformation or mass variations using the RCHB$^\star$ and DRHBc$^\star$ mass tables (where $\star$ indicates that the mass table is obtained from the DNN study). For the r-process sensitivity study, we consider magnetohydrodynamic jets and collapsar jets. Our findings indicate that r-process abundances are sensitive to nuclear deformation, particularly within the mass range of $A=80-120$.

nucl-th↗

arXiv2024

PRSI: Privacy-Preserving Recommendation Model Based on Vector Splitting and Interactive Protocols

With the development of the internet, recommending interesting products to users has become a highly valuable research topic for businesses. Recommendation systems play a crucial role in addressing this issue. To prevent the leakage of each user's (client's) private data, Federated Recommendation Systems (FedRec) have been proposed and widely used. However, extensive research has shown that FedRec suffers from security issues such as data privacy leakage, and it is challenging to train effective models with FedRec when each client only holds interaction information for a single user. To address these two problems, this paper proposes a new privacy-preserving recommendation system (PRSI), which includes a preprocessing module and two main phases. The preprocessing module employs split vectors and fake interaction items to protect clients' interaction information and recommendation results. The two main phases are: (1) the collection of interaction information and (2) the sending of recommendation results. In the interaction information collection phase, each client uses the preprocessing module and random communication methods (according to the designed interactive protocol) to protect their ID information and IP addresses. In the recommendation results sending phase, the central server uses the preprocessing module and triplets to distribute recommendation results to each client under secure conditions, following the designed interactive protocol. Finally, we conducted multiple sets of experiments to verify the security, accuracy, and communication cost of the proposed method.

cs.CR↗

arXiv2024

MambaVLT: Time-Evolving Multimodal State Space Model for Vision-Language Tracking

The vision-language tracking task aims to perform object tracking based on various modality references. Existing Transformer-based vision-language tracking methods have made remarkable progress by leveraging the global modeling ability of self-attention. However, current approaches still face challenges in effectively exploiting the temporal information and dynamically updating reference features during tracking. Recently, the State Space Model (SSM), known as Mamba, has shown astonishing ability in efficient long-sequence modeling. Particularly, its state space evolving process demonstrates promising capabilities in memorizing multimodal temporal information with linear complexity. Witnessing its success, we propose a Mamba-based vision-language tracking model to exploit its state space evolving ability in temporal space for robust multimodal tracking, dubbed MambaVLT. In particular, our approach mainly integrates a time-evolving hybrid state space block and a selective locality enhancement block, to capture contextual information for multimodal modeling and adaptive reference feature update. Besides, we introduce a modality-selection module that dynamically adjusts the weighting between visual and language references, mitigating potential ambiguities from either reference type. Extensive experimental results show that our method performs favorably against state-of-the-art trackers across diverse benchmarks.

cs.CV↗

arXiv2024

LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentation

Despite the promising performance of current video segmentation models on existing benchmarks, these models still struggle with complex scenes. In this paper, we introduce the 6th Large-scale Video Object Segmentation (LSVOS) challenge in conjunction with ECCV 2024 workshop. This year's challenge includes two tasks: Video Object Segmentation (VOS) and Referring Video Object Segmentation (RVOS). In this year, we replace the classic YouTube-VOS and YouTube-RVOS benchmark with latest datasets MOSE, LVOS, and MeViS to assess VOS under more challenging complex environments. This year's challenge attracted 129 registered teams from more than 20 institutes across over 8 countries. This report include the challenge and dataset introduction, and the methods used by top 7 teams in two tracks. More details can be found in our homepage https://lsvos.github.io/.

cs.CV↗