arXiv subjects

Jing Zhang

Publications and source records attributed to Jing Zhang.

At least 199 records · Page 11Linked to original sources

arXiv2026

EmoLat: Text-driven Image Sentiment Transfer via Emotion Latent Space

We propose EmoLat, a novel emotion latent space that enables fine-grained, text-driven image sentiment transfer by modeling cross-modal correlations between textual semantics and visual emotion features. Within EmoLat, an emotion semantic graph is constructed to capture the relational structure among emotions, objects, and visual attributes. To enhance the discriminability and transferability of emotion representations, we employ adversarial regularization, aligning the latent emotion distributions across modalities. Building upon EmoLat, a cross-modal sentiment transfer framework is proposed to manipulate image sentiment via joint embedding of text and EmoLat features. The network is optimized using a multi-objective loss incorporating semantic consistency, emotion alignment, and adversarial regularization. To support effective modeling, we construct EmoSpace Set, a large-scale benchmark dataset comprising images with dense annotations on emotions, object semantics, and visual attributes. Extensive experiments on EmoSpace Set demonstrate that our approach significantly outperforms existing state-of-the-art methods in both quantitative metrics and qualitative transfer fidelity, establishing a new paradigm for controllable image sentiment editing guided by textual input. The EmoSpace Set and all the code are available at http://github.com/JingVIPLab/EmoLat.

cs.CV↗

arXiv2026

An Investigation into the Applicability of Friction Velocity Estimation Methods for the Channel with A Deposit Body

This study investigates how the deposit body influences friction characteristics by altering local flow fields, which is closely related to bed shear stress. Using generalized flume experiments, the study assesses the applicability of classical uniform flow friction models in deposit body river sections, revealing frictional changes induced by flow field non-uniformity. Initially, based on $ \frac{u_*}{\sqrt{\overline{w'^2}}} = 0.85 \sim 1.15 $ under uniform flow conditions as the judgment basis, the reliability of the classical model is verified. Four models are then applied to estimate near-bed friction velocity in deposit body sections. Results show a significant alignment between the longitudinal velocity gradient and the peak friction velocity derived from the turbulent kinetic energy method (TKE). Dimensional analysis of friction indicators reveals that: (a) friction velocity is primarily influenced by turbulence intensity, with constricted and narrowed sections resembling uniform flow, while the expansion section forms a peak; (b) models incorporating flow field fluctuations (TKE, Vertical Turbulence Kinetic Energy (TKE w'), Reynolds shear stress method (RSS)) effectively capture the impact of non-uniform flow fields on friction characteristics; (c) when energy states are low or when deposit body proportions are large, the deposit body's resistance ratio increases, and peak friction velocity rises. This study provides theoretical insights into friction estimation and sediment transport in non-uniform flow fields of deposit bodies.

physics.flu-dyn↗

arXiv2026

TableCache: Primary Foreign Key Guided KV Cache Precomputation for Low Latency Text-to-SQL

In Text-to-SQL tasks, existing LLM-based methods often include extensive database schemas in prompts, leading to long context lengths and increased prefilling latency. While user queries typically focus on recurrent table sets-offering an opportunity for KV cache sharing across queries-current inference engines, such as SGLang and vLLM, generate redundant prefix cache copies when processing user queries with varying table orders. To address this inefficiency, we propose precomputing table representations as KV caches offline and querying the required ones online. A key aspect of our approach is the computation of table caches while preserving primary foreign key relationships between tables. Additionally, we construct a Table Trie structure to facilitate efficient KV cache lookups during inference. To enhance cache performance, we introduce a cache management system with a query reranking strategy to improve cache hit rates and a computation loading pipeline for parallelizing model inference and cache loading. Experimental results show that our proposed TableCache achieves up to a 3.62x speedup in Time to First Token (TTFT) with negligible performance degradation.

cs.CL↗

arXiv2026

GP-GS: Gaussian Processes Densification for 3D Gaussian Splatting

3D Gaussian Splatting (3DGS) enables photorealistic rendering but suffers from artefacts due to sparse Structure-from-Motion (SfM) initialisation. To address this limitation, we propose GP-GS, a Gaussian Process (GP) based densification framework for 3DGS optimisation. GP-GS formulates point cloud densification as a continuous regression problem, where a GP learns a local mapping from 2D pixel coordinates to 3D position and colour attributes. An adaptive neighbourhood-based sampling strategy generates candidate pixels for inference, while GP-predicted uncertainty is used to filter unreliable predictions, reducing noise and preserving geometric structure. Extensive experiments on synthetic and real-world benchmarks demonstrate that GP-GS consistently improves reconstruction quality and rendering fidelity, achieving up to 1.12 dB PSNR improvement over strong baselines.

cs.CV↗

arXiv2026

High-Ti induced planar-fault transformation toward superlattice extrinsic stacking faults and microtwins in crept CoNi-based superalloys

Controlling planar fault shearing mechanisms is key for improving the high-temperature creep performance of gamma prime-strengthened high-temperature superalloys. This work examines how the Ti concentration in L12-strengthened CoNi-based alloys affects planar fault formation during creep. Interrupted compressive creep tests were conducted at 1223 K under air with a constant load stress of 241 MPa. We found, for the first time, that high Ti additions shift the dominant gamma prime shearing mode from antiphase boundaries (APBs) in Ti-free and low-Ti alloys to superlattice extrinsic stacking faults (SESFs). Systematic ab initio calculations show that in high-Ti alloys, the elevated APB energy renders APB-shearing mode unfavorable. Nevertheless, the SESF energy decreases relative to that in low-Ti compositions, and an increased ratio of complex intrinsic stacking fault (CISF) to SESF energy promote the transformation of high-energy CISFs into lower-energy SESFs. Chemical analysis using scanning transmission electron microscopy combined with energy-dispersive X-ray spectroscopy further reveals that, SESFs in high-Ti alloys are enriched in Ti, Mo and W, yet no grid-like ordering is observed. Together with the ab initio calculations, Mo and W additions in high Ti alloys could facilitate the transformation from L12 structure to low-energy D024 structure, indicating Mo and W segregation along SESFs is energetically favourable. Furthermore, the successive SESF thickening facilitates microtwinning in the absence of D024 ordering along SESFs, as an additional big carrier for creep strain. These new findings clarify the role of Ti in controlling planar fault shearing mechanisms, providing new insights for optimizing the creep performance of next-generation CoNi-based superalloys.

cond-mat.mtrl-sci↗

arXiv2026

InpaintHuman: Reconstructing Occluded Humans with Multi-Scale UV Mapping and Identity-Preserving Diffusion Inpainting

Reconstructing complete and animatable 3D human avatars from monocular videos remains challenging, particularly under severe occlusions. While 3D Gaussian Splatting has enabled photorealistic human rendering, existing methods struggle with incomplete observations, often producing corrupted geometry and temporal inconsistencies. We present InpaintHuman, a novel method for generating high-fidelity, complete, and animatable avatars from occluded monocular videos. Our approach introduces two key innovations: (i) a multi-scale UV-parameterized representation with hierarchical coarse-to-fine feature interpolation, enabling robust reconstruction of occluded regions while preserving geometric details; and (ii) an identity-preserving diffusion inpainting module that integrates textual inversion with semantic-conditioned guidance for subject-specific, temporally coherent completion. Unlike SDS-based methods, our approach employs direct pixel-level supervision to ensure identity fidelity. Experiments on synthetic benchmarks (PeopleSnapshot, ZJU-MoCap) and real-world scenarios (OcMotion) demonstrate competitive performance with consistent improvements in reconstruction quality across diverse poses and viewpoints.

cs.CV↗

arXiv2026

Knowledge Distillation and Dataset Distillation of Large Language Models: Emerging Trends, Challenges, and Future Directions

The exponential growth of Large Language Models (LLMs) continues to highlight the need for efficient strategies to meet ever-expanding computational and data demands. This survey provides a comprehensive analysis of two complementary paradigms: Knowledge Distillation (KD) and Dataset Distillation (DD), both aimed at compressing LLMs while preserving their advanced reasoning capabilities and linguistic diversity. We first examine key methodologies in KD, such as task-specific alignment, rationale-based training, and multi-teacher frameworks, alongside DD techniques that synthesize compact, high-impact datasets through optimization-based gradient matching, latent space regularization, and generative synthesis. Building on these foundations, we explore how integrating KD and DD can produce more effective and scalable compression strategies. Together, these approaches address persistent challenges in model scalability, architectural heterogeneity, and the preservation of emergent LLM abilities. We further highlight applications across domains such as healthcare and education, where distillation enables efficient deployment without sacrificing performance. Despite substantial progress, open challenges remain in preserving emergent reasoning and linguistic diversity, enabling efficient adaptation to continually evolving teacher models and datasets, and establishing comprehensive evaluation protocols. By synthesizing methodological innovations, theoretical foundations, and practical insights, our survey charts a path toward sustainable, resource-efficient LLMs through the tighter integration of KD and DD principles.

cs.CL↗

arXiv2026

XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression

Learning-based 3D visual geometry models have benefited substantially from large-scale transformers. Among these, StreamVGGT leverages frame-wise causal attention for strong streaming reconstruction, but suffers from unbounded KV cache growth, leading to escalating memory consumption and inference latency as input frames accumulate. We propose XStreamVGGT, a tuning-free approach that systematically compresses the KV cache through joint pruning and quantization, enabling extremely memory-efficient streaming inference. Specifically, redundant KVs originating from multi-view inputs are pruned through efficient token importance identification, enabling a fixed memory budget. Leveraging the unique distribution of KV tensors, we incorporate KV quantization to further reduce memory consumption. Extensive evaluations show that XStreamVGGT achieves mostly negligible performance degradation while substantially reducing memory usage by 4.42$\times$ and accelerating inference by 5.48$\times$, enabling scalable and practical streaming 3D applications. The code is available at https://github.com/ywh187/XStreamVGGT/.

cs.CV↗

arXiv2025

GoMatching++: Parameter- and Data-Efficient Arbitrary-Shaped Video Text Spotting and Benchmarking

Video text spotting (VTS) extends image text spotting (ITS) by adding text tracking, significantly increasing task complexity. Despite progress in VTS, existing methods still fall short of the performance seen in ITS. This paper identifies a key limitation in current video text spotters: limited recognition capability, even after extensive end-to-end training. To address this, we propose GoMatching++, a parameter- and data-efficient method that transforms an off-the-shelf image text spotter into a video specialist. The core idea lies in freezing the image text spotter and introducing a lightweight, trainable tracker, which can be optimized efficiently with minimal training data. Our approach includes two key components: (1) a rescoring mechanism to bridge the domain gap between image and video data, and (2) the LST-Matcher, which enhances the frozen image text spotter's ability to handle video text. We explore various architectures for LST-Matcher to ensure efficiency in both parameters and training data. As a result, GoMatching++ sets new performance records on challenging benchmarks such as ICDAR15-video, DSText, and BOVText, while significantly reducing training costs. To address the lack of curved text datasets in VTS, we introduce ArTVideo, a new benchmark featuring over 30% curved text with detailed annotations. We also provide a comprehensive statistical analysis and experimental results for ArTVideo. We believe that GoMatching++ and the ArTVideo benchmark will drive future advancements in video text spotting. The source code, models and dataset are publicly available at https://github.com/Hxyz-123/GoMatching.

cs.CV↗

arXiv2025

Learning Spatial Decay for Vision Transformers

Vision Transformers (ViTs) have revolutionized computer vision, yet their self-attention mechanism lacks explicit spatial inductive biases, leading to suboptimal performance on spatially-structured tasks. Existing approaches introduce data-independent spatial decay based on fixed distance metrics, applying uniform attention weighting regardless of image content and limiting adaptability to diverse visual scenarios. Inspired by recent advances in large language models where content-aware gating mechanisms (e.g., GLA, HGRN2, FOX) significantly outperform static alternatives, we present the first successful adaptation of data-dependent spatial decay to 2D vision transformers. We introduce \textbf{Spatial Decay Transformer (SDT)}, featuring a novel Context-Aware Gating (CAG) mechanism that generates dynamic, data-dependent decay for patch interactions. Our approach learns to modulate spatial attention based on both content relevance and spatial proximity. We address the fundamental challenge of 1D-to-2D adaptation through a unified spatial-content fusion framework that integrates manhattan distance-based spatial priors with learned content representations. Extensive experiments on ImageNet-1K classification and generation tasks demonstrate consistent improvements over strong baselines. Our work establishes data-dependent spatial decay as a new paradigm for enhancing spatial attention in vision transformers.

cs.CV↗

arXiv2025

Two birds with one stone: simultaneous realization of both Lunar Coordinate Time and lunar geoid time by a single orbital clock

Context. Among options for definition of the lunar reference time, the option taking Lunar Coordinate Time (O1) has its simplicity but cannot be realized by any clock without steering, while another option adopting the lunar geoid (selenoid) proper time (O2) has its convenience for users on the lunar surface but would bring a new scaling of spatial coordinates and mass parameter of the Moon. Aims. We propose a ''time aligned orbit'' that the readings of an ideal clock in this orbit could equal to the selenoid proper time in O2 and these readings could be converted to Lunar Coordinate Time in O1 by a known linear transformation. Methods. We show that there exist the time aligned orbit around the Moon with its semi-major axis of about 1.5 lunar radius slightly depending on its inclination. We conduct a set of numerical simulations to assess to what extent a clock on these orbits could realize O2 in a more realistic lunar environment. Results. We find that the proper time in our simulations would desynchronize from the selenoid proper time up to 190 ns after a year with a frequency offset of 6E-15, which is solely 3.75% of the frequency difference in O2 caused by the lunar surface topography. These numbers might be further reduced to 13 ns and 4E-16, if we could account for the deviation of the mean orbits in our simulations from the nominal ones. Conclusions. One might simultaneously realize O1 and O2 by deployment of a single clock in the time aligned orbit. This approach also has its scalability for other terrestrial planets beyond the Earth-Moon system.

astro-ph.IM↗

arXiv2025

AutoRefiner: Improving Autoregressive Video Diffusion Models via Reflective Refinement Over the Stochastic Sampling Path

Autoregressive video diffusion models (AR-VDMs) show strong promise as scalable alternatives to bidirectional VDMs, enabling real-time and interactive applications. Yet there remains room for improvement in their sample fidelity. A promising solution is inference-time alignment, which optimizes the noise space to improve sample fidelity without updating model parameters. Yet, optimization- or search-based methods are computationally impractical for AR-VDMs. Recent text-to-image (T2I) works address this via feedforward noise refiners that modulate sampled noises in a single forward pass. Can such noise refiners be extended to AR-VDMs? We identify the failure of naively extending T2I noise refiners to AR-VDMs and propose AutoRefiner-a noise refiner tailored for AR-VDMs, with two key designs: pathwise noise refinement and a reflective KV-cache. Experiments demonstrate that AutoRefiner serves as an efficient plug-in for AR-VDMs, effectively enhancing sample fidelity by refining noise along stochastic denoising paths.

cs.CV↗

arXiv2025

SimpleDevQA: Benchmarking Large Language Models on Development Knowledge QA

The Development Knowledge Question Answering (Dev Knowledge QA) task aims to provide natural language answers to knowledge-seeking questions during software development. To investigate its importance and to what extent it has been explored, we analyze real user-LLM dialogues from WildChat and find that: (1) The Dev Knowledge QA task accounts for 39.6% of interactions(highest among all tasks), revealing broad knowledge needs beyond code generation (32.3%). (2) Only 27.5% of real Dev Knowledge QA dialogues focus on code understanding, leaving out development knowledge-seeking. (3) Only 17.1% of real-world Dev Knowledge QA dialogues can be used for constructing a benchmark. Existing benchmarks have two primary limitations for evaluating the Dev Knowledge QA capability of LLMs. First, existing benchmarks offer a limited development knowledge scope, mainly focusing on code understanding and neglecting broader knowledge during development. Second, some benchmarks are not built from real user queries. To bridge this gap, we design a three-phase pipeline that transforms real-world dialogue into simple development knowledge-seeking QA pairs. Through this pipeline, we introduce SimpleDevQA, a multilingual benchmark derived from real user dialogues. It contains 2,740 QA pairs in three languages (English, Chinese, and Russian), and focuses on questions with unique, short, and verifiable answers for accurate and simple evaluation. Experiments show that: Code LLMs generally outperform general LLMs of similar scale; Knowledge injection with the Retrieval-Augmented Generation (RAG) strategy can boost LLM accuracy by 11.3% on average; LLMs show systematic overconfidence in Dev Knowledge QA, and the answering accuracy of LLMs shows a positive correlation with their stated confidence; Generally, LLMs with stronger code generation performance also exhibit stronger performance in Dev Knowledge QA.

cs.SE↗

arXiv2025

On-Demand Microwave Single-Photon Source Based on Tantalum Thin Film

Single-photon sources are crucial for quantum information technologies. Here, we demonstrate a microwave single-photon source fabricated using a tantalum-based thin film, whose favorable material properties enable high-quality and stable photon emission. The antibunching behavior of the emitted radiation is revealed by second-order correlation measurements. Furthermore, traveling-wave parametric amplifiers are used as the pre-amplifier in the detection chains, we substantially improve the signal-to-noise ratio and thereby greatly reduce the acquisition time required for second-order correlation measurements. These results demonstrate the viability of tantalum-based superconducting devices as reliable platforms for microwave quantum photonics.

quant-ph↗

arXiv2025

SteerMusic: Enhanced Musical Consistency for Zero-shot Text-guided and Personalized Music Editing

Music editing is an important step in music production, which has broad applications, including game development and film production. Most existing zero-shot text-guided editing methods rely on pretrained diffusion models by involving forward-backward diffusion processes. However, these methods often struggle to preserve the musical content. Additionally, text instructions alone usually fail to accurately describe the desired music. In this paper, we propose two music editing methods that improve the consistency between the original and edited music by leveraging score distillation. The first method, SteerMusic, is a coarse-grained zero-shot editing approach using delta denoising score. The second method, SteerMusic+, enables fine-grained personalized music editing by manipulating a concept token that represents a user-defined musical style. SteerMusic+ allows for the editing of music into user-defined musical styles that cannot be achieved by the text instructions alone. Experimental results show that our methods outperform existing approaches in preserving both music content consistency and editing fidelity. User studies further validate that our methods achieve superior music editing quality.

cs.SD↗

arXiv2025

Phase-locked amplification enhanced by spin squeezing

Quantum lock-in amplification raises the detection sensitivity of magnetic fields to unprecedented levels by phase-locked pumping the Zeeman levels of a single trapped atom. However, random spin precessions limits the useful detection range of arming times for locking high-contrast signals. To extend this range imposed by the uncertainty limit, quadrature spin squeezing can be introduced, on top of the phase-locking mechanism. We propose a detection scheme using an atomic ensemble whose collected spin is pumped by two lasers for simultaneous squeezing and phase locking. We derive the optimal $π/2$-pulse and $π$-pulse schemes that accomplishes this concurrent action and prove that the resulting phase sensitivity is enhanced while the usable detection window for phase locking is widened.

quant-ph↗

arXiv2025

Stochastic PDEs driven by G-Brownian motion and the associated Backward Doubly Stochastic Differential Equations

Our aim is to study the well-posedness of quasilinear stochastic partial differential equations driven by G-Brownian motion (GSPDEs for short) and the associated backward doubly stochastic differential equations (GBDSDEs for short). We first prove the existence and uniqueness of weak solution to GSPDEs by analytical approach, and then solve the corresponding GBDSDEs. Finally, the relation between GSPDEs and GBDSDEs is established.

math.PR↗

arXiv2025

Complete characterization of beam deflection based on double weak value amplification system

The precise measurement of spatial attitude parameters is critical for applications in inertial navigation, industrial monitoring, instrument calibration, quantum metrology, etc. In this work, we theoretically investigate and experimentally realize the simultaneous measurement of the yaw and pitch angles using a Hermite-Gaussian-postselected double weak value system integrated with two sets of high-order-mode balanced homodyne detections, thereby achieving a complete characterization of the beam deflection. Signals of the yaw and pitch angles that are involved in TEM$_{10}$ and TEM$_{01}$ modes output from two dark ports of the system can be measured independently. As a result, the obtained minimum measurable yaw and pitch angles of beam deflection are 83 prad and 89 prad, respectively. Meanwhile, the corresponding displacements are 0.79 pm and 0.85 pm, respectively. This work expands the beam deflection measurement to two dimensions, which provides a new insight for future high-precision multi-parameter spatial precise detection.

quant-ph↗