arXiv subjects

Jing Wang

Publications and source records attributed to Jing Wang.

At least 91 records · Page 5Linked to original sources

arXiv2026

Astra: a generalizable report generation foundation model for 3D computed tomography

Interpreting computed tomography (CT) requires review of hundreds of volumetric slices and remains time-intensive and expertise-dependent. Automated CT report generation offers a promising route to improving clinical efficiency, yet the field still lacks a generalizable CT report generation foundation model that supports multi-region reporting and remains robust across external real-world cohorts. Intrinsic inconsistencies in reporting style and diagnostic terminology across cohorts make naive joint training difficult. Here we present Astra, a generalizable CT report generation foundation model developed on 90,678 thoracoabdominal CT-report pairs collected from five sites worldwide (CTRgDB), comprising 353,671 abnormalities spanning eight organ systems. By harmonizing report style and further refining diagnostic consistency via reinforcement learning, Astra achieves style-consistent and diagnostically accurate report generation across diverse anatomical regions and institutions. Evaluated on CTRgDB and six external cohorts, Astra achieves state-of-the-art performance with a 38.4% average improvement in fine-grained diagnostic metrics (P<0.001). Deployed at external clinical sites without any site-specific fine-tuning, Astra accelerated chest report drafting by 29.6% and improved abdominal report completeness by 11.3% among junior and mid-level radiologists (P<0.001). Furthermore, Astra demonstrates broad utility as a foundation for CT AI development, improving downstream diagnostic performance and scaling vision-language pretrain through high-quality report synthesis. Overall, Astra serves as a broadly accessible clinical assistant and a pivotal infrastructure for the next generation of AI-powered healthcare. The code for Astra is publicly available at https://github.com/zh-Wang-Med/Astra.

cs.CV↗

arXiv2026

SpeedyGS: Content-Aware 3D Gaussian Splatting Compression via Two-Stage Optimization

Recent progress in compressing large-scale 3D Gaussian Splatting (3DGS) data has substantially reduced storage footprint, network transmission bandwidth, and memory traffic to GPU caches before rendering. Yet decoding with advanced 3DGS codecs still takes seconds, making them unsuitable for interactive applications. To systematically address this challenge, we propose SpeedyGS, a Content-Aware 3DGS Compressor that separately optimizes the structural formation and statistical coding. First, in structural formation, we jointly optimize adaptive quantization and pruning under a unified rate-distortion objective, where the rate term is replaced by a lightweight rate proxy that estimates entropy coding cost of the next stage, thereby efficiently regulating Gaussian density and precision to yield a compact scene representation. Then, in the statistical coding phase, Gaussian geometry is converted into sparse octree tokens and subsequently undergoes multi-stage coding, while Gaussian attributes are serialized into a 1D token stream for entropy coding via a complexity-controllable local autoregressive model. SpeedyGS achieves a favorable balance among optimization efficiency, compression performance, decoding latency, and rendering speed. Compared to vanilla 3DGS, SpeedyGS achieves up to 160$\times$ model size reduction with negligible quality degradation across common datasets. Compared to state-of-the-art compression methods, it also offers significantly faster decoding and accelerates optimization by 9$\times$ on consumer-grade hardware. To further reduce decoding overhead, the statistical coding stage also supports channel-wise, fixed-length coding for Gaussian as a simpler alternative, enabling SpeedyGS to better adapt to the underlying application and reduce decoding latency to nearly zero.

eess.SP↗

arXiv2026

Cheaper is Better: A Discount-Aware Network for Conversion Rate Prediction in E-commerce Recommendation System

Post-click conversion rate (CVR) is a crucial element in online recommendation systems, which addresses significant challenges such as data sparsity (DS), sample selection bias (SSB), and delayed feedback. However, the impact of item discount rate-a key factor influencing both pricing and user purchasing behavior, has received limited attention. In this paper, we introduce the Discount-Aware Network (DANet) to model the relationship between item discount rates and CVR. DANet comprises three main components: 1) a time-frequency transformation module that utilizes Fourier transform to derive the frequency spectrum and capture the long-term discount rate trends of items; 2) a distribution de-bias module designed to mitigate the biases in user-specific discount rates caused by various purchase combinations and promotional activities, as well as periodic deviations linked to different promotion periods on e-commerce platforms; and 3) a supervised regression auxiliary task that establishes the explicit item discount labels to enhance the model's performance in terms of value accuracy, facilitating an effective representation of item discount rates. Experimental results on real datasets demonstrate the superiority of DANet, with offline AUC improving by 1.61%, and online A/B test also shows that DANet achieves impressive gains of 3.63% on pCVR and 2.23% on GMV. DANet has been successfully deployed on Alibaba Tmall APP. The code is available at https://github.com/tangrc/DANet.

cs.IR↗

arXiv2026

Learning to Forget: Satiation-Aware Long-Sequence Transducers for Mitigating Post-Purchase Redundancy

Sequential recommendation models predominantly interpret user interactions as positive signals for preference accumulation. However, in e-commerce scenarios, a purchase action often signifies the termination of a specific intent ("Interest Exit") rather than its continuation. Existing models overlook this distinction, suffering from Action-Intent Asymmetry, which leads to severe post-purchase redundancy. In this paper, we propose the Satiation-Aware Mechanism (SAM), an end-to-end framework designed to explicitly model the lifecycle of user interests. SAM incorporates three key components: (1) A Dual-path Cross-Attention architecture that retroactively suppresses historical clicks associated with a fulfilled intent while simultaneously retrieving personalized replenishment rhythms from long-term purchase history; (2) An Adaptive Satiation Gating Unit (ASGU) that generates a time-sensitive soft mask to inhibit satisfied interests immediately after purchase and gradually "re-awaken" them as the predicted repurchase cycle approaches; and (3) A self-supervised Time-to-Next-Purchase (TTNP) auxiliary task to learn latent product lifecycles without manual annotation. Extensive offline experiments on industrial datasets and online A/B testing demonstrate that SAM significantly reduces the Post-Purchase Repeat Rate (PPRR) by over 60%.

cs.IR↗

arXiv2026

MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control

While recent generative models produce high-fidelity videos, they struggle with the complex narrative control required for coherent multi-shot audio-visual generation. Existing methods suffer from temporal misalignment, limited controllability, and incomplete scripting. In this paper, we propose MAVIN, the first framework for multi-shot audio-visual generation with customized narrative control. To resolve temporal misalignment, we propose boundary-aware attention, which leverages hierarchical captions and boundary-aware token routing to render audio-visual elements within their respective temporal boundaries. To improve the controllability for multi-subject scenarios, we propose ID-aware propagation, utilizing identity embeddings and an identity-aware mask to bind specific identities to consistent visual appearances and vocal timbres. To provide comprehensive audio-visual narratives, we present a multi-agent scripting pipeline to transform free-form user inputs into hierarchical captions. Furthermore, we construct MAVINSet, a multi-shot audio-visual dataset for robust training and evaluation. Extensive experiments demonstrate that MAVIN achieves state-of-the-art performance, opening up a new avenue for integrating generative models into professional filmmaking workflows.

cs.CV↗

arXiv2026

Vortex-Number-Controlled Josephson Diode Polarity in Corbino Junctions

We demonstrate that the polarity of the Josephson diode effect in Corbino Josephson junctions can be deterministically controlled by the Josephson-vortex number, which arises as a generic consequence of structured spatial inhomogeneity. By solving the continuum Andreev spectral problem, we identify a mechanism in which the vortex number selectively filters specific spatial Fourier harmonics of the local inhomogeneity. This harmonic selection reshapes the amplitudes and relative phases of higher-order Josephson current harmonics, ultimately reversing the critical-current asymmetry. Numerical simulations of both an effective one-dimensional edge model and full two-dimensional lattice models confirm the robustness of this mechanism. Crucially, our results show that a vortex-parity-dependent reversal of diode polarity is not an exclusive signature of Majorana physics, but can emerge generically from geometric and structural inhomogeneities in Corbino junctions.

cond-mat.supr-con↗

arXiv2026

SAIL: Perceptual Quality-Aware Rate Control for Cloud Gaming

Cloud gaming streams cloud-rendered frames under strict motion-to-photon latency, yet its at-scale viability is increasingly constrained by bandwidth cost: in our study of the T cloud gaming platform, bandwidth accounts for 30-60% of total operating expense. This high bandwidth consumption stems from a fidelity-first objective of making the stream perceptually indistinguishable from local gameplay. It drives production systems toward best-effort bitrate allocation that pushes the encoder to the highest rate allowed by congestion control. However, the bitrate-perception relationship saturates: beyond a frame-dependent perceptually lossless threshold, additional bits yield negligible perceptual improvement, creating systematic redundant quality that wastes bandwidth. We present SAIL, a production quality-aware rate control system with the goal of achieving perceptually lossless quality while avoiding unnecessary bandwidth waste. SAIL adopts a post-encoding architecture to enable millisecond-scale feedback at near-zero overhead. It comprises three key designs: (i) an encoder-driven quality assessment model that leverages zero-cost encoder outputs for real-time quality estimation; (ii) a hybrid rate control mechanism that balances steady-state adaptation with dynamic spike absorption; and (iii) a network-aware strategy that coordinates with congestion control to prevent capacity underestimation. SAIL has been fully deployed on the T cloud gaming platform and reduces bandwidth consumption by 44.27% and end-to-end latency by 8.37% without degrading perceived quality, serving tens of millions of users and accumulating billions of hours of total gameplay.

cs.NI↗

arXiv2026

Data-Driven Learnability Transition of Measurement-Induced Entanglement

Measurement-induced entanglement (MIE) captures how local measurements generate long-range quantum correlations and drive dynamical phase transitions in many-body systems. Yet estimating MIE experimentally remains challenging: direct evaluation requires extensive post-selection over measurement outcomes, raising the question of whether MIE is accessible with only polynomial resources. We address this challenge by reframing MIE detection as a data-driven learning problem that assumes no prior knowledge of state preparation. Using measurement records alone, we train a neural network in a self-supervised manner to predict the uncertainty metric for MIE--the gap between upper and lower bounds of the average post-measurement bipartite entanglement. Applied to random circuits with one-dimensional all-to-all connectivity, our method reveals a learnability transition with increasing circuit depth: below a threshold the MIE can be effectively learned with resources that grow only polynomially with system size, whereas above it the required resources grow exponentially. This computational phase transition coincides with the breakdown of efficient classical simulation of the underlying quantum state. We further observe signatures of this transition on current noisy quantum devices. These results highlight the power of data-driven approaches for learning MIE and delineate the practical limits of its classical learnability.

quant-ph↗

arXiv2026

The FAST All Sky HI Survey DR2: the FASHI Catalog and the HI Mass Function

The FAST All Sky HI Survey (FASHI) conducted with the Five-hundred-meter Aperture Spherical radio Telescope (FAST) has mapped $\sim 19500\,\mathrm{deg}^2$ of the sky north of DEC $= -14^{\circ}$, detecting $156411$ extragalactic HI sources at $z< 0.09$ with a median sensitivity of $0.57\,\mathrm{mJy}\,\mathrm{beam}^{-1}$ at a velocity resolution of $6.4\,\mathrm{km}\,\mathrm{s}^{-1}$. The survey achieves unprecedented depth and area coverage, significantly improving upon previous single-dish surveys. Through a detailed completeness analysis that accounts for the survey's non-uniform sensitivity and line-width dependence, we construct a robust HI mass function (HIMF) using a completeness-corrected sample of over $109000$ sources. The HIMF is robustly constrained down to $M_{\mathrm{HI}}\sim 10^{6.2}\,M_{\odot}$. When systematic uncertainties are included, the HIMF is well described by a single-Schechter function with a characteristic mass $\log (M_{*} / h_{70}^{-2}M_{\odot}) = 9.89\pm 0.02$, low-mass end slope $α= -1.31\pm 0.02$, and amplitude $ϕ_{*} = (6.38\pm 0.49)\times 10^{-3}\,h_{70}^{3}\,\mathrm{Mpc}^{-3}\,\mathrm{dex}^{-1}$. The derived cosmic HI density is $Ω_{\mathrm{HI}} = (4.71\pm 0.03_{\mathrm{stat}}\pm 0.40_{\mathrm{sys}})\times 10^{-4}\,h_{70}^{-1}$. FASHI provides the most extensive and sensitive HI catalog to date, establishing an important benchmark for studies of gas accretion, galaxy evolution, and large-scale structure in the local universe.

astro-ph.GA↗

arXiv2026

Fast Optical Variability of the TeV Blazar PKS 1725+123 Observed by SVOM-VT and Insights from Multi-wavelength Follow-up Observations

PKS 1725+123 is a flat-spectrum radio quasar (FSRQ) with a redshift of $z=0.586$. The detection of this object in the TeV band was reported by the MAGIC telescopes and H.E.S.S. in August 2025. Subsequently, we promptly initiated Target-of-Opportunity observations using the Space-based multi-band astronomical Variable Objects Monitor (SVOM) satellite. By analyzing the observational optical data from SVOM-VT and comprehensively examining the Fermi-LAT and Swift-XRT observational data, it was found that the source is in a high-flux state across the optical, X-ray, and GeV $γ$-ray bands around the time of the TeV detections. Its optical flux reaches a historically unprecedented high level and shows significant variability on timescale as short as minutes. The variability is accompanied by changes in the color index, exhibiting a bluer when brighter behavior during the high-flux state. Based on the simultaneous multi-wavelength data, we construct the broadband spectral energy distribution (SED) of the source in the high-flux state. PKS 1725+123 demonstrates a remarkably high synchrotron peak frequency, which is distinctly different from that of other FSRQs. We propose a two-zone spine-sheath jet model to reproduce this SED. The optical--X-ray emission is generated by the synchrotron process of the relativistic electrons within a compact zone. The inverse Compton (IC) scattering processes of the same electron population contribute to the low-energy end of the Fermi-LAT spectrum, while the high-energy end of the Fermi-LAT spectrum is ascribed to the IC scattering of the synchrotron photons within the compact zone by the higher-energy electrons in an extended region.

astro-ph.HE↗

arXiv2026

GRE-Diff: Gaussian Room Embeddings for Structured Layout Diffusion

Designing functional and aesthetically coherent floor plans requires exploring a vast space of possible room arrangements, a task that quickly becomes overwhelming for human designers. In this paper, we propose GRE-Diff, a controllable and interactive diffusion-based framework that automates the creation and editing of apartment floor plans under user-specified constraints. By combining AI-generated suggestions with real-time, human-in-the-loop editing, the system enables users to specify room types, room counts, boundary shapes, and editing operations through LLM-parsed instructions or GUI-based interaction. It then generates a diverse set of plausible and well-structured designs for refinement. At the core of our approach is Gaussian Room Embedding (GRE), a continuous latent representation that models each room as a spatial Gaussian distribution capturing its location and extent. Extensive experiments on the RPLAN dataset show that GRE-Diff produces high-quality, constraint-aware, and editable polygonal layouts, offering a practical step toward bridging AI-driven automation and human creativity in spatial design.

cs.CV↗

arXiv2026

Advancing Astrophysics with the SKA II

Advancing Astrophysics with the SKA II (AASKAII), written by our science community, outlines the transformative scientific advances that will be enabled by the SKA telescopes. In the decade since the publication of the previous edition, telescope designs have matured, construction has commenced, and the SKA Organisation has evolved into the SKA Observatory (SKAO). At the same time, observations from SKA precursor and pathfinder telescopes have provided new insights into longstanding scientific challenges while revealing entirely new phenomena. Published in advance of the first science verification campaign for the SKA Observatory, this volume looks ahead to the coming decades of discovery and innovation in radio astronomy. AASKAII spans the broad range of scientific research enabled by the SKA telescopes, SKA-Mid and SKA-Low. The contributions are organised into six thematic categories according to their scientific focus. The opening section presents overview chapters from the SKA Science Working Groups, around which our community is organised. Each overview provides the broader context that connects the contributions in this volume to the key scientific questions being pursued by their respective communities.

astro-ph.IM↗

arXiv2026

Repurposing CLIP to Localize at Pixel Level

Large-scale Vision-Language Models like CLIP have demonstrated impressive open-set localization capabilities at the image level. However, adapting this capability to pixel-level dense prediction poses challenges due to global feature biases. In this paper, we introduce CLIPix, a simple yet effective framework that repurposes CLIP to perform pixel-level localization. By tracing back CLIP's classification process, CLIPix identifies object-specific attentive regions and repurposes them as pixel-level localization cues. To address noise introduced by global biases, we propose a Noise-Resistant Correction strategy, refining these cues for more precise segmentation. Additionally, we introduce a Localization Embedding strategy to integrate both localization and enriched detail information, enabling accurate, high-resolution segmentation. Our approach preserves CLIP's generalization strength and unlocks its potential for segmenting arbitrary objects. Extensive experiments on the PASCAL and COCO datasets demonstrate that CLIPix achieves state-of-the-art performance, underscoring its effectiveness.

cs.CV↗

arXiv2026

Trajectory-Aware Retrieval Agents for Temporal Decision- Making

We study the problem of decision-making from long-form, temporally structured text using large language model (LLM) agents. Standard retrievalaugmented generation (RAG) pipelines fragment chronological context into isolated snippets, discarding the temporal structure that is often critical for correct downstream decisions. We introduce TLM (Trajectory Language Model), a closed-loop agentic framework that iteratively refines the evidence set using SHAP-guided feedback. The key technical contribution is the latent growth curve model (LGCM) over retrieved chunk embeddings, which provides an interpretable mechanism for detecting trajectory trends, turning points, and information gaps. We show that, under a scorer-calibration assumption (which holds approximately in practice), the iterative refinement procedure is monotonically non-decreasing in the probability assigned to the correct label. Empirically, TLM is evaluated on three temporally grounded decision tasks: medical question answering, earnings call surprise prediction, and overnight stock gap prediction. TLM substantially outperforms both zero-shot LLM baselines and standard retrieval-augmented approaches on the medical task, and yields consistent, economically meaningful gains on the two financial tasks.

cs.AI↗

arXiv2026

Signatures of a bilayer structure in the photoelectron spectrum of B$_{80}^-$

Recent photoelectron spectroscopy of B$_{80}^-$ was interpreted in terms of a fullerene-like cage structure. During our systematic investigation of medium-sized boron clusters, we identified a $D_{3h}$-symmetric bilayer isomer whose simulated photoelectron spectrum reproduces the principal features of the experimental photoelectron spectrum within 0.04 eV. The bilayer is energetically competitive with previously proposed structures and remains dynamically stable up to 1400 K according to ab initio molecular dynamics and vibrational analyses. Its electronic structure exhibits a 0.72 eV HOMO-LUMO gap and strong interlayer aromaticity, reflected by a NICS(0) value of $-44.3$ ppm in the interlayer B-B bonding region. These findings reveal a stable bilayer motif in the B$_{80}$ energy landscape and support its viability as a possible alternative structural assignment for the experimentally observed B$_{80}^-$.

physics.atm-clus↗

arXiv2026

TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL

Autoregressive (AR) video diffusion models enable low-latency streaming generation by synthesizing videos chunk by chunk with cached visual context, but this chunk-wise formulation makes temporal instruction following ambiguous. A single global prompt does not specify which sub-event should be realized in each chunk, while naively switching to step-wise prompts often leads to delayed reactions, blended step semantics, and error propagation across prompt transitions. These failures are difficult to address with supervised fine-tuning or distillation alone: SFT suffers from exposure bias, while rollout-based distillation still optimizes low-level denoising or teacher-distribution matching rather than directly enforcing action ordering and prompt-transition correctness. We address these challenges with TempAct, a planner--executor reinforcement learning framework that jointly optimizes temporal decomposition and step-conditioned execution for temporally plausible AR video generation. TempAct uses an LLM planner to explore span-aware step prompts that are executable by the video model, and trains an AR diffusion executor to follow these prompts under its own generated histories. Its key mechanism is hierarchical group exploration: candidate plans form planning groups, and each plan induces an execution group of multiple continuations from a shared visual context, enabling plan-level credit assignment for long-horizon temporal outcomes and executor-level credit assignment for prompt-switch behavior. We further design hierarchical rewards that combine plan-quality and full-video temporal feedback for the planner with local transition-level step-following rewards, aesthetic regularization, and KL constraints for the executor. Experiments on Self-Forcing and LongLive show that TempAct improves temporal consistency while preserving overall visual quality.

cs.CV↗

arXiv2026

On the generalized Turán number of the complete bipartite graph $K_{3,b+1}$

For graphs $F$ and $H$, let $\mathrm{ex}(n,H,F)$ denote the maximum number of copies of $H$ in an $n$-vertex $F$-free graph. Very recently, Janzer, Longbrake, and Yepremyan proved that for $3<a\leq b$ and sufficiently large $t$, \begin{equation*} \mathrm{ex}(n,K_{a,b},K_{3,t})=Θ_{a,b,t}(n^3). \end{equation*} Later, Hou, Hu, and Wang made this threshold explicit by showing that the conclusion holds for all $t\geq 2\max\{3,\lceil b/2\rceil\}+1$. In particular, for every even $b\geq 6$, this matches the necessary threshold $t=b+1$. In this paper, we resolve the remaining case where $b$ is odd. More precisely, we prove that for all fixed integers $b\geq 5$ and $3<a\leq b$, \begin{equation*} \mathrm{ex}(n,K_{a,b},K_{3,b+1})=Θ_{a,b}(n^3). \end{equation*} Our construction uses a finite-field point set in $\mathrm{PG}(5,q)$ together with an orthogonal polarity. The key new ingredient is the polynomial splitting lemma due to Andrade, Bary-Soroker, and Rudnick, which produces many planes whose intersections with the point set and their polar planes both have size $b$. This gives a $K_{3,b+1}$-free incidence graph while preserving $Ω_{a,b}(n^3)$ copies of $K_{a,b}$.

math.CO↗

arXiv2026

Seeing is Believing: Aligning Prompt Rewriting with Visual Anchors for Text-to-Image Generation

Despite the impressive capabilities of text-to-image (T2I) models, an intent-generation gap often persists due to the brevity and ambiguity of user prompts. Existing approaches primarily polish the prompt for fluency and readability. However, the enhancement process still lacks visual grounding. As a result, the rewriter may over-infer missing details, causing an intent-generation gap. To address this limitation, we propose FaithRewriter, a novel prompt-enhancement framework for T2I generation. Specifically, FaithRewriter first leverages a multimodal MLLM to generate an image from the original prompt as an intermediate visual cue. This cue is then combined with the prompt and fed into a large-scale LLM to produce visually grounded augmentations that better reflect how the intended content should appear in images. Finally, these augmentations are distilled into a small-scale LLM for efficient deployment, enhancing its ability to generate effective T2I prompts. Experiments show that FaithRewriter yields prompts that are more faithful to the user intent and more visually plausible than strong baselines, helping narrow the intent-generation gap.

cs.CV↗