arXiv subjects

Wei Jiang

Publications and source records attributed to Wei Jiang.

At least 127 records · Page 7Linked to original sources

arXiv2025

BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow Matching

Bokeh rendering simulates the shallow depth-of-field effect in photography, enhancing visual aesthetics and guiding viewer attention to regions of interest. Although recent approaches perform well, rendering controllable bokeh without additional depth inputs remains a significant challenge. Existing classical and neural controllable methods rely on accurate depth maps, while generative approaches often struggle with limited controllability and efficiency. In this paper, we propose BokehFlow, a depth-free framework for controllable bokeh rendering based on flow matching. BokehFlow directly synthesizes photorealistic bokeh effects from all-in-focus images, eliminating the need for depth inputs. It employs a cross-attention mechanism to enable semantic control over both focus regions and blur intensity via text prompts. To support training and evaluation, we collect and synthesize four datasets. Extensive experiments demonstrate that BokehFlow achieves visually compelling bokeh effects and offers precise control, outperforming existing depth-dependent and generative methods in both rendering quality and efficiency.

cs.CV↗

arXiv2025

Semi-Supervised High Dynamic Range Image Reconstructing via Bi-Level Uncertain Area Masking

Reconstructing high dynamic range (HDR) images from low dynamic range (LDR) bursts plays an essential role in the computational photography. Impressive progress has been achieved by learning-based algorithms which require LDR-HDR image pairs. However, these pairs are hard to obtain, which motivates researchers to delve into the problem of annotation-efficient HDR image reconstructing: how to achieve comparable performance with limited HDR ground truths (GTs). This work attempts to address this problem from the view of semi-supervised learning where a teacher model generates pseudo HDR GTs for the LDR samples without GTs and a student model learns from pseudo GTs. Nevertheless, the confirmation bias, i.e., the student may learn from the artifacts in pseudo HDR GTs, presents an impediment. To remove this impediment, an uncertainty-based masking process is proposed to discard unreliable parts of pseudo GTs at both pixel and patch levels, then the trusted areas can be learned from by the student. With this novel masking process, our semi-supervised HDR reconstructing method not only outperforms previous annotation-efficient algorithms, but also achieves comparable performance with up-to-date fully-supervised methods by using only 6.7% HDR GTs.

cs.CV↗

arXiv2025

History-Aware Reasoning for GUI Agents

Advances in Multimodal Large Language Models have significantly enhanced Graphical User Interface (GUI) automation. Equipping GUI agents with reliable episodic reasoning capabilities is essential for bridging the gap between users' concise task descriptions and the complexities of real-world execution. Current methods integrate Reinforcement Learning (RL) with System-2 Chain-of-Thought, yielding notable gains in reasoning enhancement. For long-horizon GUI tasks, historical interactions connect each screen to the goal-oriented episode chain, and effectively leveraging these clues is crucial for the current decision. However, existing native GUI agents exhibit weak short-term memory in their explicit reasoning, interpreting the chained interactions as discrete screen understanding, i.e., unawareness of the historical interactions within the episode. This history-agnostic reasoning challenges their performance in GUI automation. To alleviate this weakness, we propose a History-Aware Reasoning (HAR) framework, which encourages an agent to reflect on its own errors and acquire episodic reasoning knowledge from them via tailored strategies that enhance short-term memory in long-horizon interaction. The framework mainly comprises constructing a reflective learning scenario, synthesizing tailored correction guidelines, and designing a hybrid RL reward function. Using the HAR framework, we develop a native end-to-end model, HAR-GUI-3B, which alters the inherent reasoning mode from history-agnostic to history-aware, equipping the GUI agent with stable short-term memory and reliable perception of screen details. Comprehensive evaluations across a range of GUI-related benchmarks demonstrate the effectiveness and generalization of our method.

cs.AI↗

arXiv2025

ProBench: Benchmarking GUI Agents with Accurate Process Information

With the deep integration of artificial intelligence and interactive technology, Graphical User Interface (GUI) Agent, as the carrier connecting goal-oriented natural language and real-world devices, has received widespread attention from the community. Contemporary benchmarks aim to evaluate the comprehensive capabilities of GUI agents in GUI operation tasks, generally determining task completion solely by inspecting the final screen state. However, GUI operation tasks consist of multiple chained steps while not all critical information is presented in the final few pages. Although a few research has begun to incorporate intermediate steps into evaluation, accurately and automatically capturing this process information still remains an open challenge. To address this weakness, we introduce ProBench, a comprehensive mobile benchmark with over 200 challenging GUI tasks covering widely-used scenarios. Remaining the traditional State-related Task evaluation, we extend our dataset to include Process-related Task and design a specialized evaluation method. A newly introduced Process Provider automatically supplies accurate process information, enabling presice assessment of agent's performance. Our evaluation of advanced GUI agents reveals significant limitations for real-world GUI scenarios. These shortcomings are prevalent across diverse models, including both large-scale generalist models and smaller, GUI-specific models. A detailed error analysis further exposes several universal problems, outlining concrete directions for future improvements.

cs.AI↗

arXiv2025

Ultrafast symmetry modulation and induced magnetic excitation in the Kagome metal RbV3Sb5

Light-matter interaction in frustrated Kagome metals enables access to hidden quantum states, yet the microscopic origin of symmetry breaking under ultrafast excitation remains elusive. Here, we uncover a microscopic mechanism for laser-induced symmetry breaking in RbV3Sb5 through first-principles real-time simulations. Selective excitation of a single-QM phonon mode dynamically breaks both rotational and time-reversal symmetries within the 2X2X1 charge density wave (CDW) superlattice. The resulting anisotropic lattice distortion lifts geometric frustration and stabilizes a nonequilibrium ferrimagnetic phase, accompanied by a sizable intrinsic anomalous Hall effect. Distinct from prior interpretations based on orbital antiferromagnetism or extrinsic perturbations, our findings reveal a spin-driven pathway for symmetry breaking under strong optical fields. These results provide a microscopic foundation for exploring how spin, lattice and charge degrees of freedom are intertwined in nonequilibrium correlated states.

cond-mat.str-el↗

arXiv2025

$\mathtt{M^3VIR}$: A Large-Scale Multi-Modality Multi-View Synthesized Benchmark Dataset for Image Restoration and Content Creation

The gaming and entertainment industry is rapidly evolving, driven by immersive experiences and the integration of generative AI (GAI) technologies. Training such models effectively requires large-scale datasets that capture the diversity and context of gaming environments. However, existing datasets are often limited to specific domains or rely on artificial degradations, which do not accurately capture the unique characteristics of gaming content. Moreover, benchmarks for controllable video generation remain absent. To address these limitations, we introduce $\mathtt{M^3VIR}$, a large-scale, multi-modal, multi-view dataset specifically designed to overcome the shortcomings of current resources. Unlike existing datasets, $\mathtt{M^3VIR}$ provides diverse, high-fidelity gaming content rendered with Unreal Engine 5, offering authentic ground-truth LR-HR paired and multi-view frames across 80 scenes in 8 categories. It includes $\mathtt{M^3VIR\_MR}$ for super-resolution (SR), novel view synthesis (NVS), and combined NVS+SR tasks, and $\mathtt{M^3VIR\_{MS}}$, the first multi-style, object-level ground-truth set enabling research on controlled video generation. Additionally, we benchmark several state-of-the-art SR and NVS methods to establish performance baselines. While no existing approaches directly handle controlled video generation, $\mathtt{M^3VIR}$ provides a benchmark for advancing this area. By releasing the dataset, we aim to facilitate research in AI-powered restoration, compression, and controllable content generation for next-generation cloud gaming and entertainment.

cs.CV↗

arXiv2025

From Embedding to Control: Representations for Stochastic Multi-Object Systems

This paper studies how to achieve accurate modeling and effective control in stochastic nonlinear dynamics with multiple interacting objects. However, non-uniform interactions and random topologies make this task challenging. We address these challenges by proposing \textit{Graph Controllable Embeddings} (GCE), a general framework to learn stochastic multi-object dynamics for linear control. Specifically, GCE is built on Hilbert space embeddings, allowing direct embedding of probability distributions of controlled stochastic dynamics into a reproducing kernel Hilbert space (RKHS), which enables linear operations in its RKHS while retaining nonlinear expressiveness. We provide theoretical guarantees on the existence, convergence, and applicability of GCE. Notably, a mean field approximation technique is adopted to efficiently capture inter-object dependencies and achieve provably low sample complexity. By integrating graph neural networks, we construct data-dependent kernel features that are capable of adapting to dynamic interaction patterns and generalizing to even unseen topologies with only limited training instances. GCE scales seamlessly to multi-object systems of varying sizes and topologies. Leveraging the linearity of Hilbert spaces, GCE also supports simple yet effective control algorithms for synthesizing optimal sequences. Experiments on physical systems, robotics, and power grids validate GCE and demonstrate consistent performance improvement over various competitive embedding methods in both in-distribution and few-shot tests

eess.SY↗

arXiv2025

Neutron capture measurement of the 165Ho at the CSNS Backn facility in the resonance energy region

The neutron capture yield of 165Ho have been measured at the Back-streaming White neutron beam line (Back-n) of the China Spallation Neutron Source (CSNS) using a 4π BaF2 Gamma Total Absorption Facility (GTAF). The resonance shapes in the 1eV to 1.0keV region were analyzed with the Bayesian R-matrix code SAMMY. For 18 s-wave resonances below 100eV, the resonance energy ER, neutron width Γn, and radiative width Γγ were extracted. The statistical analyses of the resonance parameters show that the nearest-neighbour level-spacing distribution follows a Wigner-Dyson form with mean spacing D0 = 4.53(3)eV,indicating chaotic compound-nucleus behaviour; Using the extracted parameters, the s-wave neutron strength function for 165Ho was derived to be 10-4S0 = 2.01(1), in excellent agreement with the values reported in both the Atlas of Neutron Resonances and ENDF/B-VIII.0 data.

nucl-ex↗

arXiv2025

PEACE: Towards Efficient Project-Level Efficiency Optimization via Hybrid Code Editing

Large Language Models (LLMs) have demonstrated significant capability in code generation, but their potential in code efficiency optimization remains underexplored. Previous LLM-based code efficiency optimization approaches exclusively focus on function-level optimization and overlook interaction between functions, failing to generalize to real-world development scenarios. Code editing techniques show great potential for conducting project-level optimization, yet they face challenges associated with invalid edits and suboptimal internal functions. To address these gaps, we propose Peace, a novel hybrid framework for Project-level code Efficiency optimization through Automatic Code Editing, which also ensures the overall correctness and integrity of the project. Peace integrates three key phases: dependency-aware optimizing function sequence construction, valid associated edits identification, and efficiency optimization editing iteration. To rigorously evaluate the effectiveness of Peace, we construct PeacExec, the first benchmark comprising 146 real-world optimization tasks from 47 high-impact GitHub Python projects, along with highly qualified test cases and executable environments. Extensive experiments demonstrate Peace's superiority over the state-of-the-art baselines, achieving a 69.2% correctness rate (pass@1), +46.9% opt rate, and 0.840 speedup in execution efficiency. Notably, our Peace outperforms all baselines by significant margins, particularly in complex optimization tasks with multiple functions. Moreover, extensive experiments are also conducted to validate the contributions of each component in Peace, as well as the rationale and effectiveness of our hybrid framework design.

cs.SE↗

arXiv2025

Issue Localization via LLM-Driven Iterative Code Graph Searching

Issue solving aims to generate patches to fix reported issues in real-world code repositories according to issue descriptions. Issue localization forms the basis for accurate issue solving. Recently, LLM-based issue localization methods have demonstrated state-of-the-art performance. However, these methods either search from files mentioned in issue descriptions or in the whole repository and struggle to balance the breadth and depth of the search space to converge on the target efficiently. Moreover, they allow LLM to explore whole repositories freely, making it challenging to control the search direction to prevent the LLM from searching for incorrect targets. This paper introduces CoSIL, an LLM-driven, powerful function-level issue localization method without training or indexing. CoSIL employs a two-phase code graph search strategy. It first conducts broad exploration at the file level using dynamically constructed module call graphs, and then performs in-depth analysis at the function level by expanding the module call graph into a function call graph and executing iterative searches. To precisely control the search direction, CoSIL designs a pruner to filter unrelated directions and irrelevant contexts. To avoid incorrect interaction formats in long contexts, CoSIL introduces a reflection mechanism that uses additional independent queries in short contexts to enhance formatted abilities. Experiment results demonstrate that CoSIL achieves a Top-1 localization accuracy of 43.3\% and 44.6\% on SWE-bench Lite and SWE-bench Verified, respectively, with Qwen2.5-Coder-32B, average outperforming the state-of-the-art methods by 96.04\%. When CoSIL is integrated into an issue-solving method, Agentless, the issue resolution rate improves by 2.98\%--30.5\%.

cs.SE↗

arXiv2025

Determination of the absolute energy scale of the DAMPE calorimeter with the geomagnetic rigidity cutoff method

The Dark Matter Particle Explorer (DAMPE) is a satellite-borne detector designed to detect high-energy cosmic ray particles with its core component being a BGO calorimeter capable of measuring energies from $\sim$GeV to $O(100)$ TeV. The 32 radiation lengths thickness of the calorimeter is designed to ensure full containment of showers produced by cosmic ray electrons and positrons (CREs) and $γ$-rays at energies below tens of TeV, providing high resolution in energy measurements. The absolute energy scale therefore becomes a crucial parameter for precise measurements of the CRE energy spectrum. The geomagnetic field induces a rapid drop in the low energy spectrum of electrons and positrons, a phenomenon that provides a method to determine the calorimeter's absolute energy scale. By comparing the cutoff energies of the measured spectra of CREs with those expected from the International Geomagnetic Reference Field model across 4 McIlwain $L$ bins - which cover most regions of the DAMPE orbit - we find that the calorimeter's absolute energy scale exceeds the calibration based on Geant4 simulation by $1.013\pm0.012_{\rm stat}\pm0.026_{\rm sys}$ for energies between 7 GeV and 16 GeV. The absolute energy scale should be taken into account when comparing the absolute CREs fluxes among different detectors.

hep-ex↗

arXiv2025

Collaborative Compression for Large-Scale MoE Deployment on Edge

The Mixture of Experts (MoE) architecture is an important method for scaling Large Language Models (LLMs). It increases model capacity while keeping computation cost low. However, the ultra-large MoE models still have hundreds of billions of parameters, requiring massive memory/storage and leading to difficulties for deployment on resource-constrained edge platforms. Pruning or quantization alone can hardly address the issue, because of the super-aggressive compression ratio with significantly degraded accuracy and output quality. To facilitate the deployment of ultra-large MoEs on edge platforms, we propose a collaborative compression framework by combining expert pruning, mixed-precision quantization, and activation optimization. It can effectively reduce the storage footprint of the ultra-large MoE DeepSeek-V3 from 1.3TB to 103GB, while preserving high output quality with better accuracy than traditional uniform low-bit quantization methods. To the best of our knowledge, we are the first to deploy a compressed model from the ultra-large DeepSeek-V3 on the platform with a strict 128GB total memory limit. Our comprehensive experiments on multiple benchmarks under various memory constraints demonstrate the effectiveness of our method with smaller model sizes and higher accuracy than uniform low-bit quantization methods.

cs.AI↗

arXiv2025

Spatiotemporal Raman Probing of Molecular Transport in sub-2-nm Plasmonic Quasi-2D Nanochannels

Capturing molecular dynamics in nanoconfined channels with high spatiotemporal resolution is a key challenge in nanoscience, crucial for advancing catalysis, energy conversion, and molecular sensing. Bottom-up ultrathin plasmonic nanogaps, such as nanoparticle-on-mirror (NPoM) structures, are ideal for ultrasensitive probing due to their extreme light confinement, but their perceived sealed geometry has cast doubt on the existence of accessible transport pathways. Here, counterintuitively, we demonstrate that ubiquitous ligand-capped NPoM-type nanogaps can form a natural quasi-two-dimensional nanochannel, supporting molecular transport over unprecedented length scales ($\gtrsim5$ $μ$m) with an extreme aspect ratio ($>10^3$). Using wavelength-multiplexed Raman spectroscopy, we resolve the underlying centripetal infiltration pathway with a spatial resolving power of $\sim$20 nm. This redefines the NPoM architecture as a sensitive, \textit{in-situ}, all-in-one "transport-and-probe" platform, enabling real-time, reusable monitoring of analyte with $\sim$10$^{-11}$ M. This work establishes a versatile new platform for advancing super-resolved \textit{in-situ} molecular sensing, nanoscale physicochemical studies, and on-chip nanophotofluidics.

physics.optics↗

arXiv2025

Towards Propagation-aware Representation Learning for Supervised Social Media Graph Analytics

Social media platforms generate vast, complex graph-structured data, facilitating diverse tasks such as rumor detection, bot identification, and influence modeling. Real-world applications like public opinion monitoring and stock trading -- which have a strong attachment to social media -- demand models that are performant across diverse tasks and datasets. However, most existing solutions are purely data-driven, exhibiting vulnerability to the inherent noise within social media data. Moreover, the reliance on task-specific model design challenges efficient reuse of the same model architecture on different tasks, incurring repetitive engineering efforts. To address these challenges in social media graph analytics, we propose a general representation learning framework that integrates a dual-encoder structure with a kinetic-guided propagation module. In addition to jointly modeling structural and contextual information with two encoders, our framework innovatively captures the information propagation dynamics within social media graphs by integrating principled kinetic knowledge. By deriving a propagation-aware encoder and corresponding optimization objective from a Markov chain-based transmission model, the representation learning pipeline receives a boost in its robustness to noisy data and versatility in diverse tasks. Extensive experiments verify that our approach achieves state-of-the-art performance with a unified architecture on a variety of social media graph mining tasks spanning graph classification, node classification, and link prediction. Besides, our solution exhibits strong zero-shot and few-shot transferability across datasets, demonstrating practicality when handling data-scarce tasks.

cs.SI↗

arXiv2025

Achieving Optimal Performance-Cost Trade-Off in Hierarchical Cell-Free Massive MIMO

Cell-free (CF) massive MIMO offers uniform service via distributed access points (APs), which impose high deployment costs. A novel design called hierarchical cell-free (HCF) addresses this problem by replacing some APs with a central base station, thereby lowering the costs of fronthaul network (wireless sites and fiber cables) while preserving performance. To identify the optimal uplink configuration in HCF massive MIMO, this paper provides the first comprehensive analysis, benchmarking it against cellular and CF systems. We develop a unified analytical framework for spectral efficiency that supports arbitrary combining schemes and introduce a novel hierarchical combining approach tailored to HCF two-tier architecture. Through analysis and evaluation of user fairness, system capacity, fronthaul requirements, and computational complexity, this paper identifies that HCF using centralized zero-forcing combining achieves the optimal balance between performance and cost-efficiency.

cs.IT↗

arXiv2025

What is the Most Efficient Technique for Uplink Cell-Free Massive MIMO?

This paper seeks to determine the most efficient uplink technique for cell-free massive MIMO systems. Despite offering great advances, existing works suffer from fragmented methodologies and inconsistent assumptions (e.g., single- vs. multi-antenna access points, ideal vs. spatially correlated channels). To address these limitations, we: (1) establish a unified analytical framework compatible with centralized/distributed processing and diverse combining schemes; (2) develop a universal optimization strategy for max-min power control; and (3) conduct a holistic study among four critical metrics: worst-case user spectral efficiency (fairness), system capacity, fronthaul signaling, and computational complexity. Through analyses and evaluation, this work ultimately identifies the optimal uplink technique for practical cell-free deployments.

cs.IT↗

arXiv2025

Direct measurement of the 103Rh(n,gamma) and 103Rh(gamma,n) cross section up to stellar temperatures at the CSNS Back-n and SSRF SLEGS

The cross sections of 103Rh(n,gamma) and 103Rh(gamma,n) play a crucial role in the stellar nucleosynthesis, rhodium-based self-powered neutron detectors, and nuclear medicine. The cross sections of 103Rh(n,gamma) was measured by the time-of-flight(TOF) method from 1 eV to 1000 keV at the Back-n facility of the Chinese Spallation Neutron Source. In the resolved resonance region, the data reported multiple new resonance structures for the first time. And some discrepancies were observed, offering valuable insights into the differences between the evaluated libraries. Maxwellian-averaged cross sections (MACSs) were calculated within the temperature range of the s process nucleosynthesis model, based on the averaged cross sections in the unresolved resonance region. Meanwhile the cross sections of 103Rh(gamma,n) within the range of p process nucleosynthesis were measured using laser Compton scattering (LCS) gamma rays and a new neutron flat efficiency detector (FED) array at the Shanghai Laser Electron Gamma Source (SLEGS), Shanghai Synchrotron Radiation Facility (SSRF). Using an unfolding iteration method, 103Rh(gamma,n) data were obtained with uncertainty less than 5%, and the inconsistencies between the available experimental data and the evaluated libraries were discussed. This study provides a reliable benchmark for nuclear data evaluation and model optimization, and lays a solid foundation for Rh medical isotope applications and astrophysical research.

nucl-ex↗

arXiv2025

PG-Agent: An Agent Powered by Page Graph

Graphical User Interface (GUI) agents possess significant commercial and social value, and GUI agents powered by advanced multimodal large language models (MLLMs) have demonstrated remarkable potential. Currently, existing GUI agents usually utilize sequential episodes of multi-step operations across pages as the prior GUI knowledge, which fails to capture the complex transition relationship between pages, making it challenging for the agents to deeply perceive the GUI environment and generalize to new scenarios. Therefore, we design an automated pipeline to transform the sequential episodes into page graphs, which explicitly model the graph structure of the pages that are naturally connected by actions. To fully utilize the page graphs, we further introduce Retrieval-Augmented Generation (RAG) technology to effectively retrieve reliable perception guidelines of GUI from them, and a tailored multi-agent framework PG-Agent with task decomposition strategy is proposed to be injected with the guidelines so that it can generalize to unseen scenarios. Extensive experiments on various benchmarks demonstrate the effectiveness of PG-Agent, even with limited episodes for page graph construction.

cs.AI↗