arXiv subjects

Dong Xu

Publications and source records attributed to Dong Xu.

At least 73 records · Page 4Linked to original sources

arXiv2025

A fast powerful X-ray transient from possible tidal disruption of a white dwarf

Stars captured by black holes (BHs) can be torn apart by strong tidal forces, producing electromagnetic flares. To date, more than 100 tidal disruption events (TDEs) have been observed, each involving invariably normal gaseous stars whose debris falls onto the BH, sustaining the flares over years. White dwarfs (WDs), which are the most prevalent compact stars and a million times denser--and therefore tougher--than gaseous stars, can only be disrupted by intermediate-mass black holes (IMBHs) of 10^2--10^5 solar masses. WD-TDEs are considered to generate more powerful and short-lived flares, but their evidence has been lacking. Here we report observations of a fast and luminous X-ray transient EP250702a detected by Einstein Probe. Its one-day-long X-ray peak as luminous as 10^(47-49) erg/s showed strong recurrent flares with hard spectra extending to several tens of MeV gamma-rays, as detected by Fermi/GBM and Konus-Wind, indicating relativistic jet emission. The jet's X-ray dropped sharply from 3 x 10^49 erg/s to around 10^44 erg/s within 20 days (10 days in the source rest frame). These characteristics are inconsistent with any known transient phenomena other than a jetted-TDE evolving over an unprecedentedly short timescale, indicating the disruption of a WD by an IMBH. At late times, a new soft component progressively dominates the X-ray spectrum, exhibiting an extreme super-Eddington luminosity, which possibly originates from an accretion disc. WD-TDEs open a new window for investigating the elusive IMBHs and their surrounding stellar environments, and they are prime sources of gravitational waves in the band of space-based interferometers.

astro-ph.HE↗

arXiv2025

JWST and HST observations of the host galaxy and supernova, SN 2024aihh in EP240801a at z=1.67

We present James Webb Space Telescope (JWST) and Hubble Space Telescope (HST) observations of the counterpart of EP240801a, at z=1.67, the first fast X-ray transient (FXT) identified as an X-ray flash (XRF) by the Einstein Probe (EP) and Fermi-GBM. Our observations reveal strong photometric and spectroscopic evidence for an associated broad-lined Type Ic supernova (SN) SN 2024aihh, the most distant spectroscopically identified gamma ray-burst (GRB)-SN to date. The SN exhibits similar luminosity and light curve evolution to the proto-type GRB-SN 1998bw with an absolute magnitude of the SN at $\sim$23 days rest-frame of $M_{F140W} \approx$-19 mag. The SN is located in a host galaxy with complex morphology at a large ($\sim$6 kpc) offset in a region of relatively low surface brightness. The region around the SN has a modest star formation rate and is dominated by an intermediate mass-weighted age (1.4$\pm$0.3 Gyr) population, despite the apparent presence of a young, massive broad-lined Type Ic SN progenitor. These observations demonstrate that observations with HST and JWST can greatly extend the redshift range over which the GRB/FXT-SN connection can be studied, including in relatively low luminosity, X-ray rich events. They demonstrate little apparent evolution in the SN properties from local examples despite EP240801a originating from an epoch 10 Gyr ago.

astro-ph.HE↗

arXiv2025

Prot2Token: A Unified Framework for Protein Modeling via Next-Token Prediction

The diverse nature of protein prediction tasks has traditionally necessitated specialized models, hindering the development of broadly applicable and computationally efficient Protein Language Models (PLMs). In this work, we introduce Prot2Token, a unified framework that overcomes these challenges by converting a wide spectrum of protein-related predictions-from sequence-level properties and residue-specific attributes to complex inter-protein interactions-into a standardized next-token prediction format. At its core, Prot2Token employs an autoregressive decoder, conditioned on embeddings from pre-trained protein encoders and guided by learnable task tokens, to perform diverse predictions. This architecture uniquely facilitates multi-task learning, enabling general-purpose decoders to generalize across five distinct categories. We present extensive experimental validation across a variety of benchmarks, demonstrating Prot2Token's predictive power in different types of protein-prediction tasks. In 3D structure prediction, Prot2Token delivers substantial speedups (up to 1000x faster than AlphaFold2 with MSA on the same hardware) while, across other numerous tasks, matching or surpassing specialized methods. Beyond that, we introduce an auxiliary self-supervised decoder pre-training approach to improve spatially sensitive task performance. Prot2Token thus offers a step towards standardizing biological prediction into a generative interface, promising to accelerate biological discovery and the development of novel therapeutics. The code is available at https://github.com/mahdip72/prot2token .

cs.LG↗

arXiv2025

EP241217a: a likely Type II GRB with an achromatic bump at z = 4.59

EP241217a is an X-ray transient detected by the Einstein Probe (EP) lasting for about 100 seconds and without accompanying $γ$-ray detection. The optical spectroscopy reveals the redshift of EP241217a is 4.59. By combining the $γ$-ray upper limit provided by GECAM-C, there is a considerable possibility that EP241217a is a typical Type II gamma-ray burst (GRB), but it is fainter than the detection threshold of any available $γ$-ray monitors (i.e., $E_{γ,{\rm iso}}\lesssim10^{53}$ erg). The X-ray light curve exhibits a plateau lasting for $\sim5\times10^4$ seconds. However, the joint analysis with optical data suggests the presence of an achromatic bump peaking at $\sim3\times10^4$ s after the trigger, indicating the actual duration of the X-ray plateau may be significantly shorter than it appears. To interpret the achromatic bump, we adopt the scenario of a mildly relativistic jet coasting in a wind-like medium and encountering a rapid density enhancement of the circumburst medium, which is likely induced by the the interaction of the progenitor's stellar wind and the interstellar medium. However, this model cannot fully explain observed data, and some issues do exist, e.g., the observed spectrum is harder than the model prediction. Consequently, we conclude that the scenario of a mildly relativistic jet coasting in the wind-like medium cannot explain all observed features of EP241217a. In addition, some alternative models commonly invoked to explain X-ray plateaus are discussed, but there are more or less issues when they are applied to EP241217a. Therefore, further theoretical modeling is encouraged to explore the origin of EP241217a.

astro-ph.HE↗

arXiv2025

EP250207b is not a collapsar fast X-ray transient. Is it due to a compact object merger?

Fast X-ray Transients (FXTs) are short-lived extra-galactic X-ray sources. Recent progress through multi-wavelength follow-up of Einstein Probe discovered FXTs has shown that several are related to collapsars, which can also produce gamma-ray bursts (GRBs). In this paper we investigate the nature of the FXT EP250207b. The VLT/MUSE spectra of a nearby (15.9 kpc in projection) lenticular galaxy reveal no signs of recent star formation. If this galaxy is indeed the host, EP250207b lies at a redshift of z=0.082, implying a peak observed absolute magnitude for the optical counterpart of M_r=-14.5. At the time when supernovae (SNe) would peak, it is substantially fainter than all SN types. These results are inconsistent with a collapsar origin for EP250207b. The properties favour a binary compact object merger driven origin. The X-ray, optical and radio observations are compared with predictions of several types of extra-galactic transients, including afterglow and kilonova models. The data can be fit with a slightly off-axis viewing angle afterglow. However, the late-time (~30 day) optical/NIR counterpart is too bright for the afterglow and also for conventional kilonova models. This could be remedied if that late emission is due to a globular cluster or the core of a (tidally disrupted) dwarf galaxy. If confirmed, this would be the first case where the multi-wavelength properties of an FXT are found to be consistent with a compact object merger origin, increasing the parallels between FXTs and GRBs. We finally discuss if the source could originate in a higher redshift host galaxy.

astro-ph.HE↗

arXiv2025

TCM-Ladder: A Benchmark for Multimodal Question Answering on Traditional Chinese Medicine

Traditional Chinese Medicine (TCM), as an effective alternative medicine, has been receiving increasing attention. In recent years, the rapid development of large language models (LLMs) tailored for TCM has highlighted the urgent need for an objective and comprehensive evaluation framework to assess their performance on real-world tasks. However, existing evaluation datasets are limited in scope and primarily text-based, lacking a unified and standardized multimodal question-answering (QA) benchmark. To address this issue, we introduce TCM-Ladder, the first comprehensive multimodal QA dataset specifically designed for evaluating large TCM language models. The dataset covers multiple core disciplines of TCM, including fundamental theory, diagnostics, herbal formulas, internal medicine, surgery, pharmacognosy, and pediatrics. In addition to textual content, TCM-Ladder incorporates various modalities such as images and videos. The dataset was constructed using a combination of automated and manual filtering processes and comprises over 52,000 questions. These questions include single-choice, multiple-choice, fill-in-the-blank, diagnostic dialogue, and visual comprehension tasks. We trained a reasoning model on TCM-Ladder and conducted comparative experiments against nine state-of-the-art general domain and five leading TCM-specific LLMs to evaluate their performance on the dataset. Moreover, we propose Ladder-Score, an evaluation method specifically designed for TCM question answering that effectively assesses answer quality in terms of terminology usage and semantic expression. To the best of our knowledge, this is the first work to systematically evaluate mainstream general domain and TCM-specific LLMs on a unified multimodal benchmark. The datasets and leaderboard are publicly available at https://tcmladder.com and will be continuously updated.

cs.CL↗

arXiv2025

HOLISMOKES XIX: SN 2025wny at $z=2$, the first strongly lensed superluminous supernova

We present imaging and spectroscopic observations of supernova SN 2025wny, associated with the lens candidate PS1 J0716+3821. Photometric monitoring from the Lulin and Maidanak observatories confirms multiple point-like images, consistent with SN 2025wny being strongly lensed by two foreground galaxies. Optical spectroscopy of the brightest image with the Nordic Optical Telescope and the University of Hawaii 88-inch Telescope allows us to determine the redshift to be z_s = 2.008 +- 0.001, based on narrow absorption lines originating in the interstellar medium of the supernova host galaxy. At this redshift, the spectra of SN 2025wny are consistent with those of superluminous supernovae of Type I. We find a high ejecta temperature and depressed spectral lines compared to other similar objects. We also measure, for the first time, the redshift of the fainter of the two lens galaxies (the "perturber") to be z_p = 0.375 +- 0.001, fully consistent with the DESI spectroscopic redshift of the main deflector at z_d = 0.3754. SN 2025wny thus represents the first confirmed galaxy-scale strongly lensed supernova with time delays likely in the range of days to weeks, as judged from the image separations. This makes SN 2025wny suitable for cosmography, offering a promising new system for independent measurements of the Hubble constant. Following a tradition in the field of strongly-lensed SNe, we give SN 2025wny the nickname SN Winny.

astro-ph.CO↗

arXiv2025

CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward

In this work, we introduce CAD-Coder, a novel framework that reformulates text-to-CAD as the generation of CadQuery scripts - a Python-based, parametric CAD language. This representation enables direct geometric validation, a richer modeling vocabulary, and seamless integration with existing LLMs. To further enhance code validity and geometric fidelity, we propose a two-stage learning pipeline: (1) supervised fine-tuning on paired text-CadQuery data, and (2) reinforcement learning with Group Reward Policy Optimization (GRPO), guided by a CAD-specific reward comprising both a geometric reward (Chamfer Distance) and a format reward. We also introduce a chain-of-thought (CoT) planning process to improve model reasoning, and construct a large-scale, high-quality dataset of 110K text-CadQuery-3D model triplets and 1.5K CoT samples via an automated pipeline. Extensive experiments demonstrate that CAD-Coder enables LLMs to generate diverse, valid, and complex CAD models directly from natural language, advancing the state of the art of text-to-CAD generation and geometric reasoning.

cs.GR↗

arXiv2025

Leveraging Group Relative Policy Optimization to Advance Large Language Models in Traditional Chinese Medicine

Traditional Chinese Medicine (TCM) presents a rich and structurally unique knowledge system that challenges conventional applications of large language models (LLMs). Although previous TCM-specific LLMs have shown progress through supervised fine-tuning, they often face limitations in alignment, data quality, and evaluation consistency. In this study, we introduce Ladder-base, the first TCM-focused LLM trained with Group Relative Policy Optimization (GRPO), a reinforcement learning method that improves reasoning and factual consistency by optimizing response selection based on intra-group comparisons. Ladder-base is built upon the Qwen2.5-7B-Instruct foundation model and trained exclusively on the textual subset of the TCM-Ladder benchmark, using 80 percent of the data for training and the remaining 20 percent split evenly between validation and test sets. Through standardized evaluation, Ladder-base demonstrates superior performance across multiple reasoning metrics when compared to both state-of-the-art general-purpose LLMs such as GPT-4, Gemini 2.5, Claude 3, and Qwen3 and domain-specific TCM models including BenTsao, HuatuoGPT2, and Zhongjing. These findings suggest that GRPO provides an effective and efficient strategy for aligning LLMs with expert-level reasoning in traditional medical domains and supports the development of trustworthy and clinically grounded TCM artificial intelligence systems.

cs.CL↗

arXiv2025

BenCao: An Instruction-Tuned Large Language Model for Traditional Chinese Medicine

Traditional Chinese Medicine (TCM), with a history spanning over two millennia, plays a role in global healthcare. However, applying large language models (LLMs) to TCM remains challenging due to its reliance on holistic reasoning, implicit logic, and multimodal diagnostic cues. Existing TCM-domain LLMs have made progress in text-based understanding but lack multimodal integration, interpretability, and clinical applicability. To address these limitations, we developed BenCao, a ChatGPT-based multimodal assistant for TCM, integrating structured knowledge bases, diagnostic data, and expert feedback refinement. BenCao was trained through natural language instruction tuning rather than parameter retraining, aligning with expert-level reasoning and ethical norms specific to TCM. The system incorporates a comprehensive knowledge base of over 1,000 classical and modern texts, a scenario-based instruction framework for diverse interactions, a chain-of-thought simulation mechanism for interpretable reasoning, and a feedback refinement process involving licensed TCM practitioners. BenCao connects to external APIs for tongue-image classification and multimodal database retrieval, enabling dynamic access to diagnostic resources. In evaluations across single-choice question benchmarks and multimodal classification tasks, BenCao achieved superior accuracy to general-domain and TCM-domain models, particularly in diagnostics, herb recognition, and constitution classification. The model was deployed as an interactive application on the OpenAI GPTs Store, accessed by nearly 1,000 users globally as of October 2025. This study demonstrates the feasibility of developing a TCM-domain LLM through natural language-based instruction tuning and multimodal integration, offering a practical framework for aligning generative AI with traditional medical reasoning and a scalable pathway for real-world deployment.

cs.CL↗

arXiv2025

SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification

Large language models with Mixture-of-Experts (MoE) architectures achieve efficiency and scalability, yet their routing mechanisms introduce safety alignment challenges insufficiently addressed by techniques developed for dense models. In this work, the MoE-specific safety risk of positional vulnerability-that safety-aligned behaviors rely on specific expert modules-is formalized and systematically analyzed. An analytical framework, SAFEx, is presented to robustly identify, characterize, and validate safety-critical experts via a stability-based expert selection procedure, and to decompose them into two functional groups: the Harmful Content Detection Group (HCDG), which specializes in identifying and recognizing harmful content within user inputs, and the Harmful Response Control Group (HRCG), which specializes in controlling and enforcing model behaviors to generate appropriate safety responses. Expert-level interventions are conducted to probe causality and to test mitigation. Targeted masking of SAFEx-selected experts reveals that safety behavior is highly concentrated. On Qwen3-30B-A3B, configured with 48 MoE-FFN layers and 128 experts per layer under top-8 routing (48x128=6,144 experts in total), disabling 12 selected experts reduces the refusal rate by 22%. In addition, lightweight adaptation is performed using LoRA under three configurations-the HRCG, the union of HCDG and HRCG, and all experts-and the resulting updates are composed through negative weight merging targeted at the HRCG, leading to improved refusal under adversarial prompts without full-model retraining. These results establish positional vulnerability as a distinct MoE-specific safety challenge and provide a practical, compute-efficient pathway for expert-level safety interventions within routed architectures.

cs.LG↗

arXiv2025

4DGS-Craft: Consistent and Interactive 4D Gaussian Splatting Editing

Recent advances in 4D Gaussian Splatting (4DGS) editing still face challenges with view, temporal, and non-editing region consistency, as well as with handling complex text instructions. To address these issues, we propose 4DGS-Craft, a consistent and interactive 4DGS editing framework. We first introduce a 4D-aware InstructPix2Pix model to ensure both view and temporal consistency. This model incorporates 4D VGGT geometry features extracted from the initial scene, enabling it to capture underlying 4D geometric structures during editing. We further enhance this model with a multi-view grid module that enforces consistency by iteratively refining multi-view input images while jointly optimizing the underlying 4D scene. Furthermore, we preserve the consistency of non-edited regions through a novel Gaussian selection mechanism, which identifies and optimizes only the Gaussians within the edited regions. Beyond consistency, facilitating user interaction is also crucial for effective 4DGS editing. Therefore, we design an LLM-based module for user intent understanding. This module employs a user instruction template to define atomic editing operations and leverages an LLM for reasoning. As a result, our framework can interpret user intent and decompose complex instructions into a logical sequence of atomic operations, enabling it to handle intricate user commands and further enhance editing performance. Compared to related works, our approach enables more consistent and controllable 4D scene editing. Our code will be made available upon acceptance.

cs.CV↗

arXiv2025

Data-driven modeling of wind farm wake flow based on multi-scale feature recognition

Accurate, efficient prediction of wind flow with wake effects is crucial for wind-farm layout and power forecasting. Existing approaches-physical measurements, numerical simulations, physics-based models, and data-driven models-face trade-offs: the first two are time- and resource-intensive; physics-based models can lack accuracy due to limited physics; data-driven methods leverage abundant, high-quality data and are increasingly popular. We propose a rapid, data-driven wake-flow model inspired by video-frame interpolation and the principle of similarity. Field data are transformed into images; multi-scale feature recognition then identifies, matches, and interpolates wake structures using Scale-Invariant Feature Transform (SIFT) and Dynamic Time Warping (DTW) to generate intermediate flow fields. Six representative mini wind-farm cases validate the approach, spanning variations in turbine spacing, turbine size, combined spacing-size variations, different turbine counts, and wind-direction misalignment. Across cases, the method achieves a mean absolute percentage error (MAPE) of 0.68-2.28%. Because it flexibly computes both 2D and 3D wake fields, the method offers substantial computational-efficiency gains over large-eddy simulation (LES) and Meteodyn WT when 2D accuracy suffices for industrial needs. Accordingly, it provides a practical alternative to measurements, high-fidelity simulations, and simplified physics-based models, enabling efficient expansion of wake-flow databases for wind-farm design and power prediction while balancing speed and accuracy.

physics.flu-dyn↗

arXiv2025

Qianfan-VL: Domain-Enhanced Universal Vision-Language Models

We present Qianfan-VL, a series of multimodal large language models ranging from 3B to 70B parameters, achieving state-of-the-art performance through innovative domain enhancement techniques. Our approach employs multi-stage progressive training and high-precision data synthesis pipelines, which prove to be critical technologies for enhancing domain-specific capabilities while maintaining strong general performance. Qianfan-VL achieves comparable results to leading open-source models on general benchmarks, with state-of-the-art performance on benchmarks such as CCBench, SEEDBench IMG, ScienceQA, and MMStar. The domain enhancement strategy delivers significant advantages in OCR and document understanding, validated on both public benchmarks (OCRBench 873, DocVQA 94.75%) and in-house evaluations. Notably, Qianfan-VL-8B and 70B variants incorporate long chain-of-thought capabilities, demonstrating superior performance on mathematical reasoning (MathVista 78.6%) and logical inference tasks. All models are trained entirely on Baidu's Kunlun P800 chips, validating the capability of large-scale AI infrastructure to train SOTA-level multimodal models with over 90% scaling efficiency on 5000 chips for a single task. This work establishes an effective methodology for developing domain-enhanced multimodal models suitable for diverse enterprise deployment scenarios.

cs.CV↗

arXiv2025

TOM: An Open-Source Tongue Segmentation Method with Multi-Teacher Distillation and Task-Specific Data Augmentation

Tongue imaging serves as a valuable diagnostic tool, particularly in Traditional Chinese Medicine (TCM). The quality of tongue surface segmentation significantly affects the accuracy of tongue image classification and subsequent diagnosis in intelligent tongue diagnosis systems. However, existing research on tongue image segmentation faces notable limitations, and there is a lack of robust and user-friendly segmentation tools. This paper proposes a tongue image segmentation model (TOM) based on multi-teacher knowledge distillation. By incorporating a novel diffusion-based data augmentation method, we enhanced the generalization ability of the segmentation model while reducing its parameter size. Notably, after reducing the parameter count by 96.6% compared to the teacher models, the student model still achieves an impressive segmentation performance of 95.22% mIoU. Furthermore, we packaged and deployed the trained model as both an online and offline segmentation tool (available at https://itongue.cn/), allowing TCM practitioners and researchers to use it without any programming experience. We also present a case study on TCM constitution classification using segmented tongue patches. Experimental results demonstrate that training with tongue patches yields higher classification performance and better interpretability than original tongue images. To our knowledge, this is the first open-source and freely available tongue image segmentation tool.

eess.IV↗

arXiv2025

EP241021a: A catastrophic collapse/merger of compact star binary leading to the formation of a remnant millisecond magnetar?

Observations of fast X-ray transients (FXRTs) with the Einstein Probe have successfully led to the discovery of some unusual extragalactic optical transients. EP241021a is a newly discovered FXRT that was featured by a significant bump around ten days in both optical and X-ray bands. This timescale and the exceptionally high peak bolometric luminosity up to $\sim \rm 10^{44}erg~s^{-1}$ of the optical bump make it somewhat similar to fast blue optical transients, but still distinctive from them by its relatively red color. We then suggest that the multi-wavelength bump of EP241021a could represent an explosion-type transient, while the underlying power-law decaying component of the optical and X-ray emission as well as the total radio emission are produced by a moderately relativistic jet. By fitting the observed multi-wavelength light curves, it is found that the explosion ejecta that produce the thermal optical emission can have a mass of $\sim0.03~M_{\odot}$, an expanding velocity of $\sim0.25~c$, and an optical opacity of $\sim12~\rm cm^2g^{-1}$, which was continuously powered by a rapidly rotating and highly magnetized neutron star (NS; i.e., a magnetar). In addition to heating the explosion ejecta, the magnetar also provided the dominant contribution to the observed X-ray rebrightening through the non-thermal emission of its wind. These properties suggest that the explosion may result from a catastrophic collapse/merger of a compact star system, which led to the formation of a millisecond magnetar, and the possible progenitor could be an accreting white dwarf (WD) or a binary consisting of double WDs, double NSs, or a WD and an NS.

astro-ph.HE↗

arXiv2025

IBEX: Information-Bottleneck-EXplored Coarse-to-Fine Molecular Generation under Limited Data

Three-dimensional generative models increasingly drive structure-based drug discovery, yet it remains constrained by the scarce publicly available protein-ligand complexes. Under such data scarcity, almost all existing pipelines struggle to learn transferable geometric priors and consequently overfit to training-set biases. As such, we present IBEX, an Information-Bottleneck-EXplored coarse-to-fine pipeline to tackle the chronic shortage of protein-ligand complex data in structure-based drug design. Specifically, we use PAC-Bayesian information-bottleneck theory to quantify the information density of each sample. This analysis reveals how different masking strategies affect generalization and indicates that, compared with conventional de novo generation, the constrained Scaffold Hopping task endows the model with greater effective capacity and improved transfer performance. IBEX retains the original TargetDiff architecture and hyperparameters for training to generate molecules compatible with the binding pocket; it then applies an L-BFGS optimization step to finely refine each conformation by optimizing five physics-based terms and adjusting six translational and rotational degrees of freedom in under one second. With only these modifications, IBEX raises the zero-shot docking success rate on CBGBench CrossDocked2020-based from 53% to 64%, improves the mean Vina score from $-7.41 kcal mol^{-1}$ to $-8.07 kcal mol^{-1}$, and achieves the best median Vina energy in 57 of 100 pockets versus 3 for the original TargetDiff. IBEX also increases the QED by 25%, achieves state-of-the-art validity and diversity, and markedly reduces extrapolation error.

cs.LG↗

arXiv2025

3D Gaussian Splatting Data Compression with Mixture of Priors

3D Gaussian Splatting (3DGS) data compression is crucial for enabling efficient storage and transmission in 3D scene modeling. However, its development remains limited due to inadequate entropy models and suboptimal quantization strategies for both lossless and lossy compression scenarios, where existing methods have yet to 1) fully leverage hyperprior information to construct robust conditional entropy models, and 2) apply fine-grained, element-wise quantization strategies for improved compression granularity. In this work, we propose a novel Mixture of Priors (MoP) strategy to simultaneously address these two challenges. Specifically, inspired by the Mixture-of-Experts (MoE) paradigm, our MoP approach processes hyperprior information through multiple lightweight MLPs to generate diverse prior features, which are subsequently integrated into the MoP feature via a gating mechanism. To enhance lossless compression, the resulting MoP feature is utilized as a hyperprior to improve conditional entropy modeling. Meanwhile, for lossy compression, we employ the MoP feature as guidance information in an element-wise quantization procedure, leveraging a prior-guided Coarse-to-Fine Quantization (C2FQ) strategy with a predefined quantization step value. Specifically, we expand the quantization step value into a matrix and adaptively refine it from coarse to fine granularity, guided by the MoP feature, thereby obtaining a quantization step matrix that facilitates element-wise quantization. Extensive experiments demonstrate that our proposed 3DGS data compression framework achieves state-of-the-art performance across multiple benchmarks, including Mip-NeRF360, BungeeNeRF, DeepBlending, and Tank&Temples.

cs.CV↗