arXiv subjects

Dong Xu

Publications and source records attributed to Dong Xu.

At least 91 records · Page 5Linked to original sources

arXiv2025

GRB 240825A: Early Reverse Shock and Its Physical Implications

Early multiwavelength observations offer crucial insights into the nature of the relativistic jets responsible for gamma-ray bursts and their interaction with the surrounding medium.We present data of GRB 240825A from 17 space- and ground-based telescopes/instruments, covering wavelengths from NIR/optical to X-ray and GeV, and spanning from the prompt emission to the afterglow phase triggered by Swift and Fermi. The early afterglow observations were carried out by SVOM/C-GFT, and spectroscopic observations of the afterglow by GTC, VLT, and TNG determined the redshift of the burst ($z = 0.659$) later.A comprehensive analysis of the prompt emission spectrum observed by Swift-BAT and Fermi-GBM/LAT reveals a rare and significant high-energy cutoff at ~76 MeV. Assuming this cutoff is due to $γγ$ absorption allows us to place an upper limit on the initial Lorentz factor, $Γ_0 < 245$. The optical/NIR and GeV afterglow light curves be described by the standard external shock model, with early-time emission dominated by a reverse shock (RS) and a subsequent transition to forward shock (FS) emission. Our afterglow modelling yields a consistent estimate of the initial Lorentz factor ($Γ_{\rm 0} \sim 234$). Furthermore, the RS-to-FS magnetic field ratio ($\mathcal{R}_B \sim 302$) indicates that the reverse shock region is significantly more magnetized than the FS region. An isotropic-equivalent kinetic energy of $E_{\text{k,iso}} = 5.25 \times 10^{54}$ erg is derived, and the corresponding $γ$-ray radiation efficiency is estimated to be $η_γ$ = 3.1%. On the other hand, the standard afterglow model can not reproduce the X-ray light curve of GRB 240825A, calling for improved models to characterize all multiwavelength data.

astro-ph.HE↗

arXiv2025

Spectral Hardening Reveals Afterglow Emergence in Long-Duration Fast X-ray Transients: A Case Study of GRB 250404A/EP250404a

The prompt emission and afterglow phases of gamma-ray bursts (GRBs) have been extensively studied, yet the transition between these two phases remains inadequately characterized due to limited multiwavelength observational coverage. Among the recent growing samples of fast X-ray transients observed by Einstein Probe (EP), a subgroup of GRBs are captured with long-duration X-ray emission, potentially containing featured evolution from prompt emission to the afterglow phase. In this Letter, we present a detailed analysis of GRB 250404A/EP250404a, a bright fast X-ray transient detected simultaneously by EP and the Fermi Gamma-ray Burst Monitor in X-rays and gamma rays. Its continuous X-ray emission reveals a long-duration tail, accompanied by distinct spectral evolution manifested by the spectral index $α_{\rm X}$ with an initial softening, followed by an evident hardening, eventually reaching a plateau at the value of $\sim$ -2. Early optical and near-infrared observations enable broadband modeling with forward- and reverse-shock components, confirming that the X-ray hardening signals the emergence of the external-shock afterglow. From this spectral hardening we infer that the prompt phase in soft X-rays lasted $\sim300\;\mathrm{s}$, which is more than 3 times longer than the gamma-ray $T_{90}$. This well-tracked soft-hard-flat spectral pattern provides a clear indication of afterglow emergence from the fading prompt emission and offers a practical criterion for identifying a distinct population of GRBs among fast X-ray transients, even when the detection of the gamma-ray counterpart or obvious temporal break is absent.

astro-ph.HE↗

arXiv2025

Individual Content and Motion Dynamics Preserved Pruning for Video Diffusion Models

The high computational cost and slow inference time are major obstacles to deploying Video Diffusion Models (VDMs). To overcome this, we introduce a new Video Diffusion Model Compression approach using individual content and motion dynamics preserved pruning and consistency loss. First, we empirically observe that deeper VDM layers are crucial for maintaining the quality of \textbf{motion dynamics} (\textit{e.g.,} coherence of the entire video), while shallower layers are more focused on \textbf{individual content} (\textit{e.g.,} individual frames). Therefore, we prune redundant blocks from the shallower layers while preserving more of the deeper layers, resulting in a lightweight VDM variant called VDMini. Moreover, we propose an \textbf{Individual Content and Motion Dynamics (ICMD)} Consistency Loss to gain comparable generation performance as larger VDM to VDMini. In particular, we first use the Individual Content Distillation (ICD) Loss to preserve the consistency in the features of each generated frame between the teacher and student models. Next, we introduce a Multi-frame Content Adversarial (MCA) Loss to enhance the motion dynamics across the generated video as a whole. This method significantly accelerates inference time while maintaining high-quality video generation. Extensive experiments demonstrate the effectiveness of our VDMini on two important video generation tasks, Text-to-Video (T2V) and Image-to-Video (I2V), where we respectively achieve an average 2.5 $\times$, 1.4 $\times$, and 1.25 $\times$ speed up for the I2V method SF-V, the T2V method T2V-Turbo-v2, and the T2V method HunyuanVideo, while maintaining the quality of the generated videos on several benchmarks including UCF101, VBench-T2V, and VBench-I2V.

cs.CV↗

arXiv2025

On-Device Diffusion Transformer Policy for Efficient Robot Manipulation

Diffusion Policies have significantly advanced robotic manipulation tasks via imitation learning, but their application on resource-constrained mobile platforms remains challenging due to computational inefficiency and extensive memory footprint. In this paper, we propose LightDP, a novel framework specifically designed to accelerate Diffusion Policies for real-time deployment on mobile devices. LightDP addresses the computational bottleneck through two core strategies: network compression of the denoising modules and reduction of the required sampling steps. We first conduct an extensive computational analysis on existing Diffusion Policy architectures, identifying the denoising network as the primary contributor to latency. To overcome performance degradation typically associated with conventional pruning methods, we introduce a unified pruning and retraining pipeline, optimizing the model's post-pruning recoverability explicitly. Furthermore, we combine pruning techniques with consistency distillation to effectively reduce sampling steps while maintaining action prediction accuracy. Experimental evaluations on the standard datasets, \ie, PushT, Robomimic, CALVIN, and LIBERO, demonstrate that LightDP achieves real-time action prediction on mobile devices with competitive performance, marking an important step toward practical deployment of diffusion-based policies in resource-limited environments. Extensive real-world experiments also show the proposed LightDP can achieve performance comparable to state-of-the-art Diffusion Policies.

cs.RO↗

arXiv2025

The day-long, repeating GRB 250702BDE / EP250702a: A unique extragalactic transient

Gamma-ray bursts (GRBs) are singular outbursts of high-energy radiation with durations typically lasting from milliseconds to minutes and, in extreme cases, a few hours. They are attributed to the catastrophic outcomes of stellar-scale events and, as such, are not expected to recur. Here, we present observations of an exceptional GRB\,250702BDE which triggered the {\em Fermi} gamma-ray burst monitor on three occasions over several hours, and which was detected in soft X-rays by the \textit{Einstein Probe} a day before the $γ$-ray triggers (EP250702a). We present the discovery of an extremely red infrared counterpart of the event with the VLT, as well as radio observations from MeerKAT. Hubble Space Telescope observations pinpoint the source to a non-nuclear location in a host galaxy with complex morphology, implying GRB 250702BDE is an extragalactic event. The multi-wavelength counterpart is well described with standard afterglow models at a relatively low redshift $z \sim 0.2$, but the prompt emission does not readily fit within the expectations for either collapsar or merger-driven GRBs. Indeed, a striking feature of the multiple prompt outbursts is that the third occurs at an integer multiple of the interval between the first two. Although not conclusive, this could be indicative of periodicity in the progenitor system. We discuss several possible scenarios to explain the exceptional properties of the burst, which suggest that either a very unusual collapsar or the tidal disruption of a white dwarf by an intermediate-mass black hole are plausible explanations for this unprecedented GRB.

astro-ph.HE↗

arXiv2025

MODA: A Unified 3D Diffusion Framework for Multi-Task Target-Aware Molecular Generation

Three-dimensional molecular generators based on diffusion models can now reach near-crystallographic accuracy, yet they remain fragmented across tasks. SMILES-only inputs, two-stage pretrain-finetune pipelines, and one-task-one-model practices hinder stereochemical fidelity, task alignment, and zero-shot transfer. We introduce MODA, a diffusion framework that unifies fragment growing, linker design, scaffold hopping, and side-chain decoration with a Bayesian mask scheduler. During training, a contiguous spatial fragment is masked and then denoised in one pass, enabling the model to learn shared geometric and chemical priors across tasks. Multi-task training yields a universal backbone that surpasses six diffusion baselines and three training paradigms on substructure, chemical property, interaction, and geometry. Model-C reduces ligand-protein clashes and substructure divergences while maintaining Lipinski compliance, whereas Model-B preserves similarity but trails in novelty and binding affinity. Zero-shot de novo design and lead-optimisation tests confirm stable negative Vina scores and high improvement rates without force-field refinement. These results demonstrate that a single-stage multi-task diffusion routine can replace two-stage workflows for structure-based molecular design.

q-bio.BM↗

arXiv2025

Model Compression using Progressive Channel Pruning

In this work, we propose a simple but effective channel pruning framework called Progressive Channel Pruning (PCP) to accelerate Convolutional Neural Networks (CNNs). In contrast to the existing channel pruning methods that prune channels only once per layer in a layer-by-layer fashion, our new progressive framework iteratively prunes a small number of channels from several selected layers, which consists of a three-step attempting-selecting-pruning pipeline in each iteration. In the attempting step, we attempt to prune a pre-defined number of channels from one layer by using any existing channel pruning methods and estimate the accuracy drop for this layer based on the labelled samples in the validation set. In the selecting step, based on the estimated accuracy drops for all layers, we propose a greedy strategy to automatically select a set of layers that will lead to less overall accuracy drop after pruning these layers. In the pruning step, we prune a small number of channels from these selected layers. We further extend our PCP framework to prune channels for the deep transfer learning methods like Domain Adversarial Neural Network (DANN), in which we effectively reduce the data distribution mismatch in the channel pruning process by using both labelled samples from the source domain and pseudo-labelled samples from the target domain. Our comprehensive experiments on two benchmark datasets demonstrate that our PCP framework outperforms the existing channel pruning approaches under both supervised learning and transfer learning settings.

cs.CV↗

arXiv2025

Show, Tell and Summarize: Dense Video Captioning Using Visual Cue Aided Sentence Summarization

In this work, we propose a division-and-summarization (DaS) framework for dense video captioning. After partitioning each untrimmed long video as multiple event proposals, where each event proposal consists of a set of short video segments, we extract visual feature (e.g., C3D feature) from each segment and use the existing image/video captioning approach to generate one sentence description for this segment. Considering that the generated sentences contain rich semantic descriptions about the whole event proposal, we formulate the dense video captioning task as a visual cue aided sentence summarization problem and propose a new two stage Long Short Term Memory (LSTM) approach equipped with a new hierarchical attention mechanism to summarize all generated sentences as one descriptive sentence with the aid of visual features. Specifically, the first-stage LSTM network takes all semantic words from the generated sentences and the visual features from all segments within one event proposal as the input, and acts as the encoder to effectively summarize both semantic and visual information related to this event proposal. The second-stage LSTM network takes the output from the first-stage LSTM network and the visual features from all video segments within one event proposal as the input, and acts as the decoder to generate one descriptive sentence for this event proposal. Our comprehensive experiments on the ActivityNet Captions dataset demonstrate the effectiveness of our newly proposed DaS framework for dense video captioning.

cs.CV↗

arXiv2025

Dense Video Captioning using Graph-based Sentence Summarization

Recently, dense video captioning has made attractive progress in detecting and captioning all events in a long untrimmed video. Despite promising results were achieved, most existing methods do not sufficiently explore the scene evolution within an event temporal proposal for captioning, and therefore perform less satisfactorily when the scenes and objects change over a relatively long proposal. To address this problem, we propose a graph-based partition-and-summarization (GPaS) framework for dense video captioning within two stages. For the ``partition" stage, a whole event proposal is split into short video segments for captioning at a finer level. For the ``summarization" stage, the generated sentences carrying rich description information for each segment are summarized into one sentence to describe the whole event. We particularly focus on the ``summarization" stage, and propose a framework that effectively exploits the relationship between semantic words for summarization. We achieve this goal by treating semantic words as nodes in a graph and learning their interactions by coupling Graph Convolutional Network (GCN) and Long Short Term Memory (LSTM), with the aid of visual cues. Two schemes of GCN-LSTM Interaction (GLI) modules are proposed for seamless integration of GCN and LSTM. The effectiveness of our approach is demonstrated via an extensive comparison with the state-of-the-arts methods on the two benchmarks ActivityNet Captions dataset and YouCook II dataset.

cs.CV↗

arXiv2025

Progressive Cross-Stream Cooperation in Spatial and Temporal Domain for Action Localization

Spatio-temporal action localization consists of three levels of tasks: spatial localization, action classification, and temporal localization. In this work, we propose a new progressive cross-stream cooperation (PCSC) framework that improves all three tasks above. The basic idea is to utilize both spatial region (resp., temporal segment proposals) and features from one stream (i.e., the Flow/RGB stream) to help another stream (i.e., the RGB/Flow stream) to iteratively generate better bounding boxes in the spatial domain (resp., temporal segments in the temporal domain). In this way, not only the actions could be more accurately localized both spatially and temporally, but also the action classes could be predicted more precisely. Specifically, we first combine the latest region proposals (for spatial detection) or segment proposals (for temporal localization) from both streams to form a larger set of labelled training samples to help learn better action detection or segment detection models. Second, to learn better representations, we also propose a new message passing approach to pass information from one stream to another stream, which also leads to better action detection and segment detection models. By first using our newly proposed PCSC framework for spatial localization at the frame-level and then applying our temporal PCSC framework for temporal localization at the tube-level, the action localization results are progressively improved at both the frame level and the video level. Comprehensive experiments on two benchmark datasets UCF-101-24 and J-HMDB demonstrate the effectiveness of our newly proposed approaches for spatio-temporal action localization in realistic scenarios.

cs.CV↗

arXiv2025

Self-Paced Collaborative and Adversarial Network for Unsupervised Domain Adaptation

This paper proposes a new unsupervised domain adaptation approach called Collaborative and Adversarial Network (CAN), which uses the domain-collaborative and domain-adversarial learning strategy for training the neural network. The domain-collaborative learning aims to learn domain-specific feature representation to preserve the discriminability for the target domain, while the domain adversarial learning aims to learn domain-invariant feature representation to reduce the domain distribution mismatch between the source and target domains. We show that these two learning strategies can be uniformly formulated as domain classifier learning with positive or negative weights on the losses. We then design a collaborative and adversarial training scheme, which automatically learns domain-specific representations from lower blocks in CNNs through collaborative learning and domain-invariant representations from higher blocks through adversarial learning. Moreover, to further enhance the discriminability in the target domain, we propose Self-Paced CAN (SPCAN), which progressively selects pseudo-labeled target samples for re-training the classifiers. We employ a self-paced learning strategy to select pseudo-labeled target samples in an easy-to-hard fashion. Comprehensive experiments on different benchmark datasets, Office-31, ImageCLEF-DA, and VISDA-2017 for the object recognition task, and UCF101-10 and HMDB51-10 for the video action recognition task, show our newly proposed approaches achieve the state-of-the-art performance, which clearly demonstrates the effectiveness of our proposed approaches for unsupervised domain adaptation.

cs.CV↗

arXiv2025

Progressive Modality Cooperation for Multi-Modality Domain Adaptation

In this work, we propose a new generic multi-modality domain adaptation framework called Progressive Modality Cooperation (PMC) to transfer the knowledge learned from the source domain to the target domain by exploiting multiple modality clues (\eg, RGB and depth) under the multi-modality domain adaptation (MMDA) and the more general multi-modality domain adaptation using privileged information (MMDA-PI) settings. Under the MMDA setting, the samples in both domains have all the modalities. In two newly proposed modules of our PMC, the multiple modalities are cooperated for selecting the reliable pseudo-labeled target samples, which captures the modality-specific information and modality-integrated information, respectively. Under the MMDA-PI setting, some modalities are missing in the target domain. Hence, to better exploit the multi-modality data in the source domain, we further propose the PMC with privileged information (PMC-PI) method by proposing a new multi-modality data generation (MMG) network. MMG generates the missing modalities in the target domain based on the source domain data by considering both domain distribution mismatch and semantics preservation, which are respectively achieved by using adversarial learning and conditioning on weighted pseudo semantics. Extensive experiments on three image datasets and eight video datasets for various multi-modality cross-domain visual recognition tasks under both MMDA and MMDA-PI settings clearly demonstrate the effectiveness of our proposed PMC framework.

cs.CV↗

arXiv2025

Improving Weakly Supervised Temporal Action Localization by Exploiting Multi-resolution Information in Temporal Domain

Weakly supervised temporal action localization is a challenging task as only the video-level annotation is available during the training process. To address this problem, we propose a two-stage approach to fully exploit multi-resolution information in the temporal domain and generate high quality frame-level pseudo labels based on both appearance and motion streams. Specifically, in the first stage, we generate reliable initial frame-level pseudo labels, and in the second stage, we iteratively refine the pseudo labels and use a set of selected frames with highly confident pseudo labels to train neural networks and better predict action class scores at each frame. We fully exploit temporal information at multiple scales to improve temporal action localization performance. Specifically, in order to obtain reliable initial frame-level pseudo labels, in the first stage, we propose an Initial Label Generation (ILG) module, which leverages temporal multi-resolution consistency to generate high quality class activation sequences (CASs), which consist of a number of sequences with each sequence measuring how likely each video frame belongs to one specific action class. In the second stage, we propose a Progressive Temporal Label Refinement (PTLR) framework. In our PTLR framework, two networks called Network-OTS and Network-RTS, which are respectively used to generate CASs for the original temporal scale and the reduced temporal scales, are used as two streams (i.e., the OTS stream and the RTS stream) to refine the pseudo labels in turn. By this way, the multi-resolution information in the temporal domain is exchanged at the pseudo label level, and our work can help improve each stream (i.e., the OTS/RTS stream) by exploiting the refined pseudo labels from another stream (i.e., the RTS/OTS stream).

cs.CV↗

arXiv2025

A Dual-Directional Context-Aware Test-Time Learning for Text Classification

Text classification assigns text to predefined categories. Traditional methods struggle with complex structures and long-range dependencies. Deep learning with recurrent neural networks and Transformer models has improved feature extraction and context awareness. However, these models still trade off interpretability, efficiency and contextual range. We propose the Dynamic Bidirectional Elman Attention Network (DBEAN). DBEAN combines bidirectional temporal modeling and self-attention. It dynamically weights critical input segments and preserves computational efficiency.

cs.CL↗

arXiv2025

Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization

Transformer-based models have achieved remarkable success, but their core components, Transformer layers, are largely heuristics-driven and engineered from the bottom up, calling for a prototypical model with high interpretability and practical competence. To this end, we conceptualize a principled, top-down approach grounded in energy-based interpretation. Specifically, we formalize token dynamics as a joint maximum likelihood estimation on the hypersphere, featuring two properties: semantic alignment in the high-dimensional space and distributional uniformity in the low-dimensional space. By quantifying them with extended Hopfield energy functions, we instantiate this idea as a constrained energy minimization problem, which enables designs of symmetric attention and feedforward modules with RMS normalization. We further present \textit{Hyper-Spherical Energy Transformer} (Hyper-SET), a recurrent-depth alternative to vanilla Transformers naturally emerging from iterative energy optimization on the hypersphere. With shared parameters across layers, Hyper-SET can scale to arbitrary depth with fewer parameters. Theoretically grounded and compact, it achieves competitive or superior performance across diverse tasks, including Sudoku solving, image classification, and masked image modeling. We also design novel variations under the proposed general principle, such as linear attention and gated feedforward layer. Moreover, we showcase its scalability with depth-wise LoRA. Our results highlight Hyper-SET as a step toward interpretable and principled Transformer design.

cs.LG↗

arXiv2025

Intern-GS: Vision Model Guided Sparse-View 3D Gaussian Splatting

Sparse-view scene reconstruction often faces significant challenges due to the constraints imposed by limited observational data. These limitations result in incomplete information, leading to suboptimal reconstructions using existing methodologies. To address this, we present Intern-GS, a novel approach that effectively leverages rich prior knowledge from vision foundation models to enhance the process of sparse-view Gaussian Splatting, thereby enabling high-quality scene reconstruction. Specifically, Intern-GS utilizes vision foundation models to guide both the initialization and the optimization process of 3D Gaussian splatting, effectively addressing the limitations of sparse inputs. In the initialization process, our method employs DUSt3R to generate a dense and non-redundant gaussian point cloud. This approach significantly alleviates the limitations encountered by traditional structure-from-motion (SfM) methods, which often struggle under sparse-view constraints. During the optimization process, vision foundation models predict depth and appearance for unobserved views, refining the 3D Gaussians to compensate for missing information in unseen regions. Extensive experiments demonstrate that Intern-GS achieves state-of-the-art rendering quality across diverse datasets, including both forward-facing and large-scale scenes, such as LLFF, DTU, and Tanks and Temples.

cs.CV↗

arXiv2025

4DGS-CC: A Contextual Coding Framework for 4D Gaussian Splatting Data Compression

Storage is a significant challenge in reconstructing dynamic scenes with 4D Gaussian Splatting (4DGS) data. In this work, we introduce 4DGS-CC, a contextual coding framework that compresses 4DGS data to meet specific storage constraints. Building upon the established deformable 3D Gaussian Splatting (3DGS) method, our approach decomposes 4DGS data into 4D neural voxels and a canonical 3DGS component, which are then compressed using Neural Voxel Contextual Coding (NVCC) and Vector Quantization Contextual Coding (VQCC), respectively. Specifically, we first decompose the 4D neural voxels into distinct quantized features by separating the temporal and spatial dimensions. To losslessly compress each quantized feature, we leverage the previously compressed features from the temporal and spatial dimensions as priors and apply NVCC to generate the spatiotemporal context for contextual coding. Next, we employ a codebook to store spherical harmonics information from canonical 3DGS as quantized vectors, which are then losslessly compressed by using VQCC with the auxiliary learned hyperpriors for contextual coding, thereby reducing redundancy within the codebook. By integrating NVCC and VQCC, our contextual coding framework, 4DGS-CC, enables multi-rate 4DGS data compression tailored to specific storage requirements. Extensive experiments on three 4DGS data compression benchmarks demonstrate that our method achieves an average storage reduction of approximately 12 times while maintaining rendering fidelity compared to our baseline 4DGS approach.

cs.CE↗

arXiv2025

HEMGS: A Hybrid Entropy Model for 3D Gaussian Splatting Data Compression

In this work, we propose a novel compression framework for 3D Gaussian Splatting (3DGS) data. Building on anchor-based 3DGS methodologies, our approach compresses all attributes within each anchor by introducing a novel Hybrid Entropy Model for 3D Gaussian Splatting (HEMGS) to achieve hybrid lossy-lossless compression. It consists of three main components: a variable-rate predictor, a hyperprior network, and an autoregressive network. First, unlike previous methods that adopt multiple models to achieve multi-rate lossy compression, thereby increasing training overhead, our variable-rate predictor enables variable-rate compression with a single model and a hyperparameter $λ$ by producing a learned Quantization Step feature for versatile lossy compression. Second, to improve lossless compression, the hyperprior network captures both scene-agnostic and scene-specific features to generate a prior feature, while the autoregressive network employs an adaptive context selection algorithm with flexible receptive fields to produce a contextual feature. By integrating these two features, HEMGS can accurately estimate the distribution of the current coding element within each attribute, enabling improved entropy coding and reduced storage. We integrate HEMGS into a compression framework, and experimental results on four benchmarks indicate that HEMGS achieves about a 40% average reduction in size while maintaining rendering quality over baseline methods and achieving state-of-the-art compression results.

cs.CV↗