arXiv subjects

Jing Zhang

Publications and source records attributed to Jing Zhang.

At least 361 records · Page 20Linked to original sources

arXiv2025

VisualSimpleQA: A Benchmark for Decoupled Evaluation of Large Vision-Language Models in Fact-Seeking Question Answering

Large vision-language models (LVLMs) have demonstrated remarkable achievements, yet the generation of non-factual responses remains prevalent in fact-seeking question answering (QA). Current multimodal fact-seeking benchmarks primarily focus on comparing model outputs to ground truth answers, providing limited insights into the performance of modality-specific modules. To bridge this gap, we introduce VisualSimpleQA, a multimodal fact-seeking benchmark with two key features. First, it enables streamlined and decoupled evaluation of LVLMs in visual and linguistic modalities. Second, it incorporates well-defined difficulty criteria to guide human annotation and facilitates the extraction of a challenging subset, VisualSimpleQA-hard. Experiments on 15 LVLMs show that even state-of-the-art models such as GPT-4o achieve merely 60%+ correctness in multimodal fact-seeking QA on VisualSimpleQA and 30%+ on VisualSimpleQA-hard. Furthermore, the decoupled evaluation across these models highlights substantial opportunities for improvement in both visual and linguistic modules. The dataset is available at https://huggingface.co/datasets/WYLing/VisualSimpleQA.

cs.CL↗

arXiv2025

BrainNet-MoE: Brain-Inspired Mixture-of-Experts Learning for Neurological Disease Identification

The Lewy body dementia (LBD) is the second most common neurodegenerative dementia after Alzheimer's disease (AD). Early differentiation between AD and LBD is crucial because they require different treatment approaches, but this is challenging due to significant clinical overlap, heterogeneity, complex pathogenesis, and the rarity of LBD. While recent advances in artificial intelligence (AI) demonstrate powerful learning capabilities and offer new hope for accurate diagnosis, existing methods primarily focus on designing "neural-level networks". Our work represents a pioneering effort in modeling system-level artificial neural network called BrainNet-MoE for brain modeling and diagnosing. Inspired by the brain's hierarchical organization of bottom-up sensory integration and top-down control, we design a set of disease-specific expert groups to process brain sub-network under different condition, A disease gate mechanism guides the specializa-tion of expert groups, while a transformer layer enables communication be-tween all sub-networks, generating a comprehensive whole-brain represen-tation for downstream disease classification. Experimental results show superior classification accuracy with interpretable insights into how brain sub-networks contribute to different neurodegenerative conditions.

cs.LG↗

arXiv2025

Diversifying Question Generation over Knowledge Base via External Natural Questions

Previous methods on knowledge base question generation (KBQG) primarily focus on enhancing the quality of a single generated question. Recognizing the remarkable paraphrasing ability of humans, we contend that diverse texts should convey the same semantics through varied expressions. The above insights make diversifying question generation an intriguing task, where the first challenge is evaluation metrics for diversity. Current metrics inadequately assess the above diversity since they calculate the ratio of unique n-grams in the generated question itself, which leans more towards measuring duplication rather than true diversity. Accordingly, we devise a new diversity evaluation metric, which measures the diversity among top-k generated questions for each instance while ensuring their relevance to the ground truth. Clearly, the second challenge is how to enhance diversifying question generation. To address this challenge, we introduce a dual model framework interwoven by two selection strategies to generate diverse questions leveraging external natural questions. The main idea of our dual framework is to extract more diverse expressions and integrate them into the generation model to enhance diversifying question generation. Extensive experiments on widely used benchmarks for KBQG demonstrate that our proposed approach generates highly diverse questions and improves the performance of question answering tasks.

cs.CL↗

arXiv2025

Dynamic Parallel Tree Search for Efficient LLM Reasoning

Tree of Thoughts (ToT) enhances Large Language Model (LLM) reasoning by structuring problem-solving as a spanning tree. However, recent methods focus on search accuracy while overlooking computational efficiency. The challenges of accelerating the ToT lie in the frequent switching of reasoning focus, and the redundant exploration of suboptimal solutions. To alleviate this dilemma, we propose Dynamic Parallel Tree Search (DPTS), a novel parallelism framework that aims to dynamically optimize the reasoning path in inference. It includes the Parallelism Streamline in the generation phase to build up a flexible and adaptive parallelism with arbitrary paths by fine-grained cache management and alignment. Meanwhile, the Search and Transition Mechanism filters potential candidates to dynamically maintain the reasoning focus on more possible solutions and have less redundancy. Experiments on Qwen-2.5 and Llama-3 with Math500 and GSM8K datasets show that DPTS significantly improves efficiency by 2-4x on average while maintaining or even surpassing existing reasoning algorithms in accuracy, making ToT-based reasoning more scalable and computationally efficient.

cs.AI↗

arXiv2025

Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning

In offline reinforcement learning, it is necessary to manage out-of-distribution actions to prevent overestimation of value functions. One class of methods, the policy-regularized method, addresses this problem by constraining the target policy to stay close to the behavior policy. Although several approaches suggest representing the behavior policy as an expressive diffusion model to boost performance, it remains unclear how to regularize the target policy given a diffusion-modeled behavior sampler. In this paper, we propose Diffusion Actor-Critic (DAC) that formulates the Kullback-Leibler (KL) constraint policy iteration as a diffusion noise regression problem, enabling direct representation of target policies as diffusion models. Our approach follows the actor-critic learning paradigm in which we alternatively train a diffusion-modeled target policy and a critic network. The actor training loss includes a soft Q-guidance term from the Q-gradient. The soft Q-guidance is based on the theoretical solution of the KL constraint policy iteration, which prevents the learned policy from taking out-of-distribution actions. We demonstrate that such diffusion-based policy constraint, along with the coupling of the lower confidence bound of the Q-ensemble as value targets, not only preserves the multi-modality of target policies, but also contributes to stable convergence and strong performance in DAC. Our approach is evaluated on D4RL benchmarks and outperforms the state-of-the-art in nearly all environments. Code is available at https://github.com/Fang-Lin93/DAC.

cs.LG↗

arXiv2025

Deep Learning for Camera Calibration and Beyond: A Survey

Camera calibration involves estimating camera parameters to infer geometric features from captured sequences, which is crucial for computer vision and robotics. However, conventional calibration is laborious and requires dedicated collection. Recent efforts show that learning-based solutions have the potential to be used in place of the repeatability works of manual calibrations. Among these solutions, various learning strategies, networks, geometric priors, and datasets have been investigated. In this paper, we provide a comprehensive survey of learning-based camera calibration techniques, by analyzing their strengths and limitations. Our main calibration categories include the standard pinhole camera model, distortion camera model, cross-view model, and cross-sensor model, following the research trend and extended applications. As there is no unified benchmark in this community, we collect a holistic calibration dataset that can serve as a public platform to evaluate the generalization of existing methods. It comprises both synthetic and real-world data, with images and videos captured by different cameras in diverse scenes. Toward the end of this paper, we discuss the challenges and provide further research directions. To our knowledge, this is the first survey for the learning-based camera calibration (spanned 10 years). The summarized methods, datasets, and benchmarks are available and will be regularly updated at https://github.com/KangLiao929/Awesome-Deep-Camera-Calibration.

cs.CV↗

arXiv2025

Using Structural Similarity and Kolmogorov-Arnold Networks for Anatomical Embedding of Cortical Folding Patterns

The 3-hinge gyrus (3HG) is a newly defined folding pattern, which is the conjunction of gyri coming from three directions in cortical folding. Many studies demonstrated that 3HGs can be reliable nodes when constructing brain networks or connectome since they simultaneously possess commonality and individuality across different individual brains and populations. However, 3HGs are identified and validated within individual spaces, making it difficult to directly serve as the brain network nodes due to the absence of cross-subject correspondence. The 3HG correspondences represent the intrinsic regulation of brain organizational architecture, traditional image-based registration methods tend to fail because individual anatomical properties need to be fully respected. To address this challenge, we propose a novel self-supervised framework for anatomical feature embedding of the 3HGs to build the correspondences among different brains. The core component of this framework is to construct a structural similarity-enhanced multi-hop feature encoding strategy based on the recently developed Kolmogorov-Arnold network (KAN) for anatomical feature embedding. Extensive experiments suggest that our approach can effectively establish robust cross-subject correspondences when no one-to-one mapping exists.

cs.CV↗

arXiv2025

Scintillation and Timing Performance of a 3at% Yttrium-Doped Barium Fluoride Crystal

We report the scintillation and timing performance of a new developed 200 * 20 mm * 20 mm large size barium fluoride crystal doped with 3at% yttrium (BaF2:Y) to enhance the application for high time resolution. This doping effectively suppresses the slow scintillation component while maintaining most of the fast component, as confirmed by X-ray excited luminescence measurements. The BaF2:Y crystal demonstrated a transmittance of near 90% in the visible spectrum and a light response uniformity parameter of delta = (-2.74 +- 1.15)% when coupled with the tail end. The actual yttrium content varied from 2.1at% near the seed end to 3.7at% at the tail end. The assembled large BaF2:Y detector with silicon photomultipliers exhibited a time resolution of (82.2 +- 2.6) ps using constant fraction discrimination method in a cosmic ray test and (140.1 +- 3.8) ps using a low fixed threshold method in a beam test at Shanghai Synchrotron Radiation Facility with an 1.35 GeV electron beam. These results indicate the significant potential of BaF2:Y crystal for various applications, such as detectors for particle physics and nuclear physics.

physics.ins-det↗

arXiv2025

Unsupervised CP-UNet Framework for Denoising DAS Data with Decay Noise

Distributed acoustic sensor (DAS) technology leverages optical fiber cables to detect acoustic signals, providing cost-effective and dense monitoring capabilities. It offers several advantages including resistance to extreme conditions, immunity to electromagnetic interference, and accurate detection. However, DAS typically exhibits a lower signal-to-noise ratio (S/N) compared to geophones and is susceptible to various noise types, such as random noise, erratic noise, level noise, and long-period noise. This reduced S/N can negatively impact data analyses containing inversion and interpretation. While artificial intelligence has demonstrated excellent denoising capabilities, most existing methods rely on supervised learning with labeled data, which imposes stringent requirements on the quality of the labels. To address this issue, we develop a label-free unsupervised learning (UL) network model based on Context-Pyramid-UNet (CP-UNet) to suppress erratic and random noises in DAS data. The CP-UNet utilizes the Context Pyramid Module in the encoding and decoding process to extract features and reconstruct the DAS data. To enhance the connectivity between shallow and deep features, we add a Connected Module (CM) to both encoding and decoding section. Layer Normalization (LN) is utilized to replace the commonly employed Batch Normalization (BN), accelerating the convergence of the model and preventing gradient explosion during training. Huber-loss is adopted as our loss function whose parameters are experimentally determined. We apply the network to both the 2-D synthetic and filed data. Comparing to traditional denoising methods and the latest UL framework, our proposed method demonstrates superior noise reduction performance.

cs.SD↗

arXiv2025

Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition

Few-shot adaptation for Vision-Language Models (VLMs) presents a dilemma: balancing in-distribution accuracy with out-of-distribution generalization. Recent research has utilized low-level concepts such as visual attributes to enhance generalization. However, this study reveals that VLMs overly rely on a small subset of attributes on decision-making, which co-occur with the category but are not inherently part of it, termed spuriously correlated attributes. This biased nature of VLMs results in poor generalization. To address this, 1) we first propose Spurious Attribute Probing (SAP), identifying and filtering out these problematic attributes to significantly enhance the generalization of existing attribute-based methods; 2) We introduce Spurious Attribute Shielding (SAS), a plug-and-play module that mitigates the influence of these attributes on prediction, seamlessly integrating into various Parameter-Efficient Fine-Tuning (PEFT) methods. In experiments, SAP and SAS significantly enhance accuracy on distribution shifts across 11 datasets and 3 generalization tasks without compromising downstream performance, establishing a new state-of-the-art benchmark.

cs.LG↗

arXiv2025

TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios

We introduce TableLLM, a robust large language model (LLM) with 8 billion parameters, purpose-built for proficiently handling tabular data manipulation tasks, whether they are embedded within documents or spreadsheets, catering to real-world office scenarios. We propose a distant supervision method for training, which comprises a reasoning process extension strategy, aiding in training LLMs to understand reasoning patterns more effectively as well as a cross-way validation strategy, ensuring the quality of the automatically generated data. To evaluate the performance of TableLLM, we have crafted benchmarks tailored to address both document and spreadsheet formats as well as constructed a well-organized evaluation pipeline capable of handling both scenarios. Thorough evaluations underscore the advantages of TableLLM when compared to various existing general-purpose and tabular data-focused LLMs. We have publicly released the model checkpoint, source code, benchmarks, and a web application for user interaction. Our codes and data are publicly available at https://github.com/TableLLM/TableLLM.

cs.CL↗

arXiv2025

Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL

Direct Preference Optimization (DPO) has proven effective in complex reasoning tasks like math word problems and code generation. However, when applied to Text-to-SQL datasets, it often fails to improve performance and can even degrade it. Our investigation reveals the root cause: unlike math and code tasks, which naturally integrate Chain-of-Thought (CoT) reasoning with DPO, Text-to-SQL datasets typically include only final answers (gold SQL queries) without detailed CoT solutions. By augmenting Text-to-SQL datasets with synthetic CoT solutions, we achieve, for the first time, consistent and significant performance improvements using DPO. Our analysis shows that CoT reasoning is crucial for unlocking DPO's potential, as it mitigates reward hacking, strengthens discriminative capabilities, and improves scalability. These findings offer valuable insights for building more robust Text-to-SQL models. To support further research, we publicly release the code and CoT-enhanced datasets.

cs.CL↗

arXiv2025

Simultaneous optical power delivery and distributed sensing through cross-band wavelength multiplexing over fiber link

Optical fibers offer significant advantages in both power delivery and distributed sensing. In remote areas where stable power supply is not easy to access, the distributed optical fiber sensing (DOFS) which offers long distance monitoring capability and the power-over-fiber (PoF) which can provide energy for connected electronics or other sensors are highly desired simultaneously. In this letter, the PoF-DOFS hybrid system is proposed and experimentally verified for the first time. By multiplexing the power channel and sensing channel with large wavelength separation, the cross-talk is greatly reduced. The results show that the Brillouin frequency shift under different temperature in the Brillouin optical time domain reflectometry remains unaffected by the high-power transmission background and the power delivery efficiency up to ~66% can be achieved over 1.3 km fiber link. This work paves the way for further research on PoF-DOFS hybrid system and gives a valuable solution for creating multi-parameter, multi-scale sensing network without the need for local power source.

physics.optics↗

arXiv2025

SEW: Self-calibration Enhanced Whole Slide Pathology Image Analysis

Pathology images are considered the ``gold standard" for cancer diagnosis and treatment, with gigapixel images providing extensive tissue and cellular information. Existing methods fail to simultaneously extract global structural and local detail features for comprehensive pathology image analysis efficiently. To address these limitations, we propose a self-calibration enhanced framework for whole slide pathology image analysis, comprising three components: a global branch, a focus predictor, and a detailed branch. The global branch initially classifies using the pathological thumbnail, while the focus predictor identifies relevant regions for classification based on the last layer features of the global branch. The detailed extraction branch then assesses whether the magnified regions correspond to the lesion area. Finally, a feature consistency constraint between the global and detail branches ensures that the global branch focuses on the appropriate region and extracts sufficient discriminative features for final identification. These focused discriminative features prove invaluable for uncovering novel prognostic tumor markers from the perspective of feature cluster uniqueness and tissue spatial distribution. Extensive experiment results demonstrate that the proposed framework can rapidly deliver accurate and explainable results for pathological grading and prognosis tasks.

cs.CV↗

arXiv2025

Deep Learning-Based Beamlet Model for Generic X-Ray Beam Dose Calculation

Modeling the absorbed dose during X-ray imaging is essential for optimizing radiation exposure. Monte Carlo simulations (MCS) are the gold standard for precise 3D dose estimation but require significant computation time. Deep learning offers faster dose prediction but often lacks generality, as models are typically trained for specific anatomical sites and beam geometries. The aim in this work was proposing a generic deep-learning approach for dose calculation that can be used for multiple X-ray imaging systems. This article proposes a versatile approach combining beamlet decomposition with deep learning, where the X-ray beam is broken down into beamlets. By using a sampling approach, various beam shapes can be generated, reducing learning complexity. The model learns the dose response of a beamlet for different energies and patient properties, making it adaptable to new system geometries without altering the learning model. In this work, we propose combining two U-Net networks (1D+3D) trained on different body parts to predict the dose of a beamlet regardless of its orientation and energy. Results have shown that the deep learning-based dose engine achieved a relative dose error of approximately 1.2+/-3.87% compared to the reference dose. For a more realistic simulation in cone-beam CT, dose results exhibited a relative error within the beam of 5% compared to a full MCS. The convergence of the proposed method was faster compared to MCS, with a speedup of 130 times for equivalent dose results. The versatility of the proposed solution allows for the simulation of multiple X-ray systems without the need to retrain the deep learning model with new beam specificities. The same trained model is capable of calculating the 3D dose within the patient for helical CT, cone-beam CT, fan-beam CT, or any collimated beam shape.

physics.med-ph↗

arXiv2025

Chiral Raman coupling for spin-orbit coupling in ultracold atomic gases

Spin-orbit coupling (SOC) in ultracold atoms is engineered by light-atom interaction, such as two-photon Raman transitions between two Zeeman spin states. In this work, we propose and experimentally realize chiral Raman coupling to generate SOC in ultracold atomic gases, which exhibits high quantization axis direction-dependence. Chiral Raman coupling for SOC is created by chiral light-atom interaction, in which a circularly polarized electromagnetic field generated by two Raman lasers interacts with two Zeeman spin states $δm_{F}=\pm 1$ (chiral transition). We present a simple scheme of chiral one-dimension (1D) Raman coupling by employing two Raman lasers at an intersecting angle 90$^{\circ}$ with the proper polarization configuration. In this case, Raman coupling for SOC exist in one direction of the magnetic quantization axis and disappears in the opposite direction. Then we extend this scheme into a chiral 2D optical square Raman lattice configuration to generate the 1D SOC. There are two orthogonal 1D SOC, which exists in the positive and negative directions of the magnetic quantization axis respectively. This case is compared with 2D SOC based on the nonchiral 2D optical Raman lattice scheme for studying the topological energy band. This work broadens the horizon for understanding chiral physics and simulating topological quantum systems.

cond-mat.quant-gas↗

arXiv2025

MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights

Molecular representation learning plays a crucial role in various downstream tasks, such as molecular property prediction and drug design. To accurately represent molecules, Graph Neural Networks (GNNs) and Graph Transformers (GTs) have shown potential in the realm of self-supervised pretraining. However, existing approaches often overlook the relationship between molecular structure and electronic information, as well as the internal semantic reasoning within molecules. This omission of fundamental chemical knowledge in graph semantics leads to incomplete molecular representations, missing the integration of structural and electronic data. To address these issues, we introduce MOL-Mamba, a framework that enhances molecular representation by combining structural and electronic insights. MOL-Mamba consists of an Atom & Fragment Mamba-Graph (MG) for hierarchical structural reasoning and a Mamba-Transformer (MT) fuser for integrating molecular structure and electronic correlation learning. Additionally, we propose a Structural Distribution Collaborative Training and E-semantic Fusion Training framework to further enhance molecular representation learning. Extensive experiments demonstrate that MOL-Mamba outperforms state-of-the-art baselines across eleven chemical-biological molecular datasets.

cs.LG↗

arXiv2025

Power-over-fiber and distributed acoustic sensing hybridization in single fiber channel

The efficient and independent operation of power-over-fiber (PoF) and distributed acoustic sensing (DAS) has been demonstrated using standard single-mode fiber (SSMF). A transmission optical power efficiency (OPTE) of 6.67% was achieved over an 11.8 km fiber link, supporting both power delivery and distributed optical fiber sensing (DOFS). To minimize cross-talk, the system separates the power and sensing channels by a 40 THz bandwidth. In the experiment, the power and sensing light wavelengths are 1064 nm (continuous) and 1550 nm (pulsed), respectively. As the transmitted optical power increased from 0 W to 2.13 W, the DAS system successfully localized vibration sources and reconstructed phase information, confirming its ability to operate under high optical power. The reported scheme verifies the possibility of constructing the sensing-energy hybrid network based on conventional optical fiber with the advantages of flexibility and low cost.

physics.optics↗