arXiv subjects

Song Wang

Publications and source records attributed to Song Wang.

At least 145 records · Page 8Linked to original sources

arXiv2025

Search for Radio Pulsations from Neutron Star Candidates in Detached Binaries

Recent optical astrometric and spectroscopic surveys have identified numerous neutron star (NS) candidates in non-accreting detached binary systems, but their compact-object nature remains unconfirmed. In this work, we present targeted radio observations of 31 such candidates using the Five-hundred-meter Aperture Spherical radio Telescope (FAST), the Robert C. Byrd Green Bank Telescope, and the Shanghai TianMa Radio Telescope. Over a total of 46.65 hours of observing time, we detected neither periodic nor single-pulse radio emissions. These nondetections place stringent upper limits on the flux densities of any potential radio signals, reaching ~4 $μ$Jy for periodic emission and ~10 mJy for single pulses with FAST. Since our observations are highly sensitive and the flux density upper limits are well below the median fluxes of known Galactic pulsars, this suggests that geometric beaming is the most likely explanation for the non-detections if these objects are indeed pulsars. Alternatively, the NSs may be sufficiently old ($\gtrsim$ 10 Gyr) and have become intrinsically radio-quiet. In this case, our findings highlight the inherent difficulty of confirming NSs in such old detached binary systems through radio pulsation searches.

astro-ph.HE↗

arXiv2025

Fairness in Multi-modal Medical Diagnosis with Demonstration Selection

Multimodal large language models (MLLMs) have shown strong potential for medical image reasoning, yet fairness across demographic groups remains a major concern. Existing debiasing methods often rely on large labeled datasets or fine-tuning, which are impractical for foundation-scale models. We explore In-Context Learning (ICL) as a lightweight, tuning-free alternative for improving fairness. Through systematic analysis, we find that conventional demonstration selection (DS) strategies fail to ensure fairness due to demographic imbalance in selected exemplars. To address this, we propose Fairness-Aware Demonstration Selection (FADS), which builds demographically balanced and semantically relevant demonstrations via clustering-based sampling. Experiments on multiple medical imaging benchmarks show that FADS consistently reduces gender-, race-, and ethnicity-related disparities while maintaining strong accuracy, offering an efficient and scalable path toward fair medical image reasoning. These results highlight the potential of fairness-aware in-context learning as a scalable and data-efficient solution for equitable medical image reasoning.

cs.CV↗

arXiv2025

Secure-Instruct: An Automated Pipeline for Synthesizing Instruction-Tuning Datasets Using LLMs for Secure Code Generation

Although Large Language Models (LLMs) show promising solutions to automated code generation, they often produce insecure code that threatens software security. Current approaches (e.g., SafeCoder) to improve secure code generation are limited by small, imbalanced instruction-tuning datasets. In this work, we present Secure-Instruct, a novel pipeline that automatically synthesizes high-quality vulnerable and secure code examples and instruction-tunes LLMs to align task description and secure code generation abilities. We evaluate Secure-Instruct on four representative LLMs using two security-related benchmarks: our own CWEBench and the existing CWEval. CWEBench comprises 93 scenarios on 44 CWEs, all without overlap with Secure-Instruct's synthetic instruction-tuning dataset, while CWEval covers 31 CWEs with 119 manually verified security-critical tasks. We find that Secure-Instruct improves both security and functional correctness in code generation. On CWEBench, Secure-Instruct substantially improves secure code generation, giving a 28.5% increase on average in secure ratio over the pre-trained models and outperforms SafeCoder by 12.6%. On CWEval, Secure-Instruct achieves an increase of 157.3% for CodeLlama-7B and 46.4% for Mistral-7B in Func-Sec@1 over pretrained models, and significantly outperforms SafeCoder.

cs.SE↗

arXiv2025

GUIDE: Gaussian Unified Instance Detection for Enhanced Obstacle Perception in Autonomous Driving

In the realm of autonomous driving, accurately detecting surrounding obstacles is crucial for effective decision-making. Traditional methods primarily rely on 3D bounding boxes to represent these obstacles, which often fail to capture the complexity of irregularly shaped, real-world objects. To overcome these limitations, we present GUIDE, a novel framework that utilizes 3D Gaussians for instance detection and occupancy prediction. Unlike conventional occupancy prediction methods, GUIDE also offers robust tracking capabilities. Our framework employs a sparse representation strategy, using Gaussian-to-Voxel Splatting to provide fine-grained, instance-level occupancy data without the computational demands associated with dense voxel grids. Experimental validation on the nuScenes dataset demonstrates GUIDE's performance, with an instance occupancy mAP of 21.61, marking a 50\% improvement over existing methods, alongside competitive tracking capabilities. GUIDE establishes a new benchmark in autonomous perception systems, effectively combining precision with computational efficiency to better address the complexities of real-world driving environments.

cs.RO↗

arXiv2025

The Visual Counter Turing Test (VCT2): A Benchmark for Evaluating AI-Generated Image Detection and the Visual AI Index (VAI)

The rapid progress and widespread availability of text-to-image (T2I) generative models have heightened concerns about the misuse of AI-generated visuals, particularly in the context of misinformation campaigns. Existing AI-generated image detection (AGID) methods often overfit to known generators and falter on outputs from newer or unseen models. We introduce the Visual Counter Turing Test (VCT2), a comprehensive benchmark of 166,000 images, comprising both real and synthetic prompt-image pairs produced by six state-of-the-art T2I systems: Stable Diffusion 2.1, SDXL, SD3 Medium, SD3.5 Large, DALL.E 3, and Midjourney 6. We curate two distinct subsets: COCOAI, featuring structured captions from MS COCO, and TwitterAI, containing narrative-style tweets from The New York Times. Under a unified zero-shot evaluation, we benchmark 17 leading AGID models and observe alarmingly low detection accuracy, 58% on COCOAI and 58.34% on TwitterAI. To transcend binary classification, we propose the Visual AI Index (VAI), an interpretable, prompt-agnostic realism metric based on twelve low-level visual features, enabling us to quantify and rank the perceptual quality of generated outputs with greater nuance. Correlation analysis reveals a moderate inverse relationship between VAI and detection accuracy: Pearson of -0.532 on COCOAI and -0.503 on TwitterAI, suggesting that more visually realistic images tend to be harder to detect, a trend observed consistently across generators. We release COCOAI, TwitterAI, and all codes to catalyze future advances in generalized AGID and perceptual realism assessment.

cs.CV↗

arXiv2025

An Empirical Study of Reasoning Steps in Thinking Code LLMs

Thinking Large Language Models (LLMs) generate explicit intermediate reasoning traces before final answers, potentially improving transparency, interpretability, and solution accuracy for code generation. However, the quality of these reasoning chains remains underexplored. We present a comprehensive empirical study examining the reasoning process and quality of thinking LLMs for code generation. We evaluate six state-of-the-art reasoning LLMs (DeepSeek-R1, OpenAI-o3-mini, Claude-3.7-Sonnet-Thinking, Gemini-2.0-Flash-Thinking, Gemini-2.5-Flash, and Qwen-QwQ) across 100 code generation tasks of varying difficulty from BigCodeBench. We quantify reasoning-chain structure through step counts and verbosity, conduct controlled step-budget adjustments, and perform a 21-participant human evaluation across three dimensions: efficiency, logical correctness, and completeness. Our step-count interventions reveal that targeted step increases can improve resolution rates for certain models/tasks, while modest reductions often preserve success on standard tasks, rarely on hard ones. Through systematic analysis, we develop a reasoning-problematic taxonomy, identifying completeness as the dominant failure mode. Task complexity significantly impacts reasoning quality; hard problems are substantially more prone to incompleteness than standard tasks. Our stability analysis demonstrates that thinking LLMs maintain consistent logical structures across computational effort levels and can self-correct previous errors. This study provides new insights into the strengths and limitations of current thinking LLMs in software engineering.

cs.AI↗

arXiv2025

Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable features. While SAEs provide crucial insights into LLM explanations, their practical adoption faces a fundamental challenge: better interpretability demands that SAEs' hidden layers have high dimensionality to satisfy sparsity constraints, resulting in prohibitive training and inference costs. Recent Mixture of Experts (MoE) approaches attempt to address this by partitioning SAEs into narrower expert networks with gated activation, thereby reducing computation. In a well-designed MoE, each expert should focus on learning a distinct set of features. However, we identify a \textit{critical limitation} in MoE-SAE: Experts often fail to specialize, which means they frequently learn overlapping or identical features. To deal with it, we propose two key innovations: (1) Multiple Expert Activation that simultaneously engages semantically weighted expert subsets to encourage specialization, and (2) Feature Scaling that enhances diversity through adaptive high-frequency scaling. Experiments demonstrate a 24\% lower reconstruction error and a 99\% reduction in feature redundancy compared to existing MoE-SAE methods. This work bridges the interpretability-efficiency gap in LLM analysis, allowing transparent model inspection without compromising computational feasibility.

cs.LG↗

arXiv2025

LLMs as Judges: Toward The Automatic Review of GSN-compliant Assurance Cases

Assurance cases allow verifying the correct implementation of certain non-functional requirements of mission-critical systems, including their safety, security, and reliability. They can be used in the specification of autonomous driving, avionics, air traffic control, and similar systems. They aim to reduce risks of harm of all kinds including human mortality, environmental damage, and financial loss. However, assurance cases often tend to be organized as extensive documents spanning hundreds of pages, making their creation, review, and maintenance error-prone, time-consuming, and tedious. Therefore, there is a growing need to leverage (semi-)automated techniques, such as those powered by generative AI and large language models (LLMs), to enhance efficiency, consistency, and accuracy across the entire assurance-case lifecycle. In this paper, we focus on assurance case review, a critical task that ensures the quality of assurance cases and therefore fosters their acceptance by regulatory authorities. We propose a novel approach that leverages the \textit{LLM-as-a-judge} paradigm to automate the review process. Specifically, we propose new predicate-based rules that formalize well-established assurance case review criteria, allowing us to craft LLM prompts tailored to the review task. Our experiments on several state-of-the-art LLMs (GPT-4o, GPT-4.1, DeepSeek-R1, and Gemini 2.0 Flash) show that, while most LLMs yield relatively good review capabilities, DeepSeek-R1 and GPT-4.1 demonstrate superior performance, with DeepSeek-R1 ultimately outperforming GPT-4.1. However, our experimental results also suggest that human reviewers are still needed to refine the reviews LLMs yield.

cs.SE↗

arXiv2025

AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction

Recent progress in large language model (LLM)-based multi-agent collaboration highlights the power of structured communication in enabling collective intelligence. However, existing methods largely rely on static or graph-based inter-agent topologies, lacking the potential adaptability and flexibility in communication. In this work, we propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure, offering a significantly larger topology space for multi-agent communication. Our method focuses on two key directions: (1) Next-Agent Prediction, which selects the most suitable agent role at each step, and (2) Next-Context Selection (NCS), which enables each agent to selectively access relevant information from any previous step. Together, these components construct task-adaptive communication pipelines that support both role flexibility and global information flow. Extensive evaluations across multiple benchmarks demonstrate that our approach achieves superior performance while substantially reducing communication overhead.

cs.AI↗

arXiv2025

Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources to address their limitations in accessing up-to-date or specialized information. A natural strategy to increase the likelihood of retrieving relevant information is to expand the number of retrieved documents. However, involving more documents could introduce significant noise, as many documents may be irrelevant or misleading, thereby reducing the overall accuracy of the generated responses. To overcome the challenge associated with handling a larger number of documents, we propose WinnowRAG, a novel RAG framework designed to systematically filter out noisy documents while preserving valuable content -- a process we refer to as winnowing. WinnowRAG operates in two stages: In Stage I, we perform query-aware clustering to group similar documents and form distinct topic clusters. Each cluster is assigned to an LLM agent for generating a unique answer. In Stage II, we perform winnowing, wherein a critic LLM evaluates the outputs of multiple agents and iteratively separates useful documents from noisy ones. To retain useful documents when discarding agents, we propose two strategic merging techniques to ensure that only relevant knowledge is used for generating the final response. Crucially, WinnowRAG is model-agnostic and does not require any model fine-tuning, making it easily adaptable to various tasks. Extensive experiments on various realistic datasets demonstrate the effectiveness of WinnowRAG over state-of-the-art baselines.

cs.CL↗

arXiv2025

From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning

The capability of in-context learning (ICL) enables large language models (LLMs) to perform novel tasks without parameter updates by conditioning on a few input-output examples. However, collecting high-quality examples for new or challenging tasks can be costly and labor-intensive. In this work, we propose a cost-efficient two-stage pipeline that reduces reliance on LLMs for data labeling. Our approach first leverages readily available cross-task examples to prompt an LLM and pseudo-label a small set of target task instances. We then introduce a graph-based label propagation method that spreads label information to the remaining target examples without additional LLM queries. The resulting fully pseudo-labeled dataset is used to construct in-task demonstrations for ICL. This pipeline combines the flexibility of cross-task supervision with the scalability of LLM-free propagation. Experiments across five tasks demonstrate that our method achieves strong performance while lowering labeling costs.

cs.AI↗

arXiv2025

Retrieval-Augmented Test Generation: How Far Are We?

Retrieval Augmented Generation (RAG) has advanced software engineering tasks but remains underexplored in unit test generation. To bridge this gap, we investigate the efficacy of RAG-based unit test generation for machine learning (ML/DL) APIs and analyze the impact of different knowledge sources on their effectiveness. We examine three domain-specific sources for RAG: (1) API documentation (official guidelines), (2) GitHub issues (developer-reported resolutions), and (3) StackOverflow Q&As (community-driven solutions). Our study focuses on five widely used Python-based ML/DL libraries, TensorFlow, PyTorch, Scikit-learn, Google JAX, and XGBoost, targeting the most-used APIs. We evaluate four state-of-the-art LLMs -- GPT-3.5-Turbo, GPT-4o, Mistral MoE 8x22B, and Llama 3.1 405B -- across three strategies: basic instruction prompting, Basic RAG, and API-level RAG. Quantitatively, we assess syntactical and dynamic correctness and line coverage. While RAG does not enhance correctness, RAG improves line coverage by 6.5% on average. We found that GitHub issues result in the best improvement in line coverage by providing edge cases from various issues. We also found that these generated unit tests can help detect new bugs. Specifically, 28 bugs were detected, 24 unique bugs were reported to developers, ten were confirmed, four were rejected, and ten are awaiting developers' confirmation. Our findings highlight RAG's potential in unit test generation for improving test coverage with well-targeted knowledge sources. Future work should focus on retrieval techniques that identify documents with unique program states to optimize RAG-based unit test generation further.

cs.SE↗

arXiv2025

Multi-Agent Debate for LLM Judges with Adaptive Stability Detection

With advancements in reasoning capabilities, Large Language Models (LLMs) are increasingly employed for automated judgment tasks. While LLMs-as-Judges offer promise in automating evaluations, current approaches often rely on simplistic aggregation methods (e.g., majority voting), which can fail even when individual agents provide correct answers. To address this, we propose a multi-agent debate judge framework where agents collaboratively reason and iteratively refine their responses. We formalize the debate process mathematically, analyzing agent interactions and proving that debate amplifies correctness compared to static ensembles. To enhance efficiency, we introduce a stability detection mechanism that models judge consensus dynamics via a time-varying Beta-Binomial mixture, with adaptive stopping based on distributional similarity (Kolmogorov-Smirnov test). This mechanism models the judges' collective correct rate dynamics using a time-varying mixture of Beta-Binomial distributions and employs an adaptive stopping criterion based on distributional similarity (Kolmogorov-Smirnov statistic). Experiments across multiple benchmarks and models demonstrate that our framework improves judgment accuracy over majority voting while maintaining computational efficiency.

cs.AI↗

arXiv2025

Enhancing Diffusion Policy with Classifier-Free Guidance for Temporal Robotic Tasks

Temporal sequential tasks challenge humanoid robots, as existing Diffusion Policy (DP) and Action Chunking with Transformers (ACT) methods often lack temporal context, resulting in local optima traps and excessive repetitive actions. To address these issues, this paper introduces a Classifier-Free Guidance-Based Diffusion Policy (CFG-DP), a novel framework to enhance DP by integrating Classifier-Free Guidance (CFG) with conditional and unconditional models. Specifically, CFG leverages timestep inputs to track task progression and ensure precise cycle termination. It dynamically adjusts action predictions based on task phase, using a guidance factor tuned to balance temporal coherence and action accuracy. Real-world experiments on a humanoid robot demonstrate high success rates and minimal repetitive actions. Furthermore, we assessed the model's ability to terminate actions and examined how different components and parameter adjustments affect its performance. This framework significantly enhances deterministic control and execution reliability for sequential robotic tasks.

cs.RO↗

arXiv2025

Interpretable Neuropsychiatric Diagnosis via Concept-Guided Graph Neural Networks

Nearly one in five adolescents currently live with a diagnosed mental or behavioral health condition, such as anxiety, depression, or conduct disorder, underscoring the urgency of developing accurate and interpretable diagnostic tools. Resting-state functional magnetic resonance imaging (rs-fMRI) provides a powerful lens into large-scale functional connectivity, where brain regions are modeled as nodes and inter-regional synchrony as edges, offering clinically relevant biomarkers for psychiatric disorders. While prior works use graph neural network (GNN) approaches for disorder prediction, they remain complex black-boxes, limiting their reliability and clinical translation. In this work, we propose CONCEPTNEURO, a concept-based diagnosis framework that leverages large language models (LLMs) and neurobiological domain knowledge to automatically generate, filter, and encode interpretable functional connectivity concepts. Each concept is represented as a structured subgraph linking specific brain regions, which are then passed through a concept classifier. Our design ensures predictions through clinically meaningful connectivity patterns, enabling both interpretability and strong predictive performance. Extensive experiments across multiple psychiatric disorder datasets demonstrate that CONCEPTNEURO-augmented GNNs consistently outperform their vanilla counterparts, improving accuracy while providing transparent, clinically aligned explanations. Furthermore, concept analyses highlight disorder-specific connectivity patterns that align with expert knowledge and suggest new hypotheses for future investigation, establishing CONCEPTNEURO as an interpretable, domain-informed framework for psychiatric disorder diagnosis.

cs.LG↗

arXiv2025

Aligning Multilingual Reasoning with Verifiable Semantics from a High-Resource Expert Model

While reinforcement learning has advanced the reasoning abilities of Large Language Models (LLMs), these gains are largely confined to English, creating a significant performance disparity across languages. To address this, we introduce Pivot-Based Reinforcement Learning with Semantically Verifiable Rewards (PB-RLSVR), a novel framework that enhances multilingual reasoning by circumventing the need for human-annotated data in target languages. Our approach employs a high-performing English LLM as a "pivot" model to generate reference responses for reasoning tasks. A multilingual model is then rewarded based on the semantic equivalence of its responses to the English reference, effectively transferring the pivot model's reasoning capabilities across languages. We investigate several cross-lingual semantic reward functions, including those based on embeddings and machine translation. Extensive experiments on a suite of multilingual reasoning benchmarks show that our method significantly narrows the performance gap between English and other languages, substantially outperforming traditional PPO baselines. Specifically, our PB-RLSVR framework improves the average multilingual performance of Llama-3.1-8B-Instruct and Qwen3-32B by 16.41% and 10.17%, respectively, demonstrating a powerful and data-efficient approach to building truly multilingual reasoning agents.

cs.CL↗

arXiv2025

Evolution of Stellar Activity and Habitable zone: I. Ultraviolet Emission of Dwarfs in Open Clusters and Field Stars

Near-ultraviolet (NUV) radiation from dwarf stars plays a critical role in shaping the habitability of planetary systems, yet its long-term evolution across different spectral types remains poorly investigated. Based on GALEX NUV observations, we study the evolution of stellar NUV emission for a sample of 386,500 A- to M-type dwarfs spanning ages from 3 Myr to 10 Gyr, drawn from both open clusters and the field. The normalized NUV emission ($f_{\rm NUV}/f_{\rm J}$) is used to trace the evolutionary trends. Our results reveal distinct evolutionary pathways after considering the distance completeness: A and early-F dwarfs show a weak decline in NUV emission during the main-sequence phase; late-F to G dwarfs exhibit a clear decrease, consistent with continuous spin-down driven by magnetic braking; late-K and M-dwarfs undergo a rapid decline in NUV emission when they evolve from young stellar objects to main-sequence stars. Furthermore, we construct the evolutionary tracks of stellar ultraviolet habitable zone (UHZ). By comparing stellar circumstellar habitable zone (CHZ) and UHZ, we find that G- and K-type stars offer the most stable overlap between thermal and UV habitability over long-term evolution.

astro-ph.SR↗

arXiv2025

Temporal Reasoning with Large Language Models Augmented by Evolving Knowledge Graphs

Large language models (LLMs) excel at many language understanding tasks but struggle to reason over knowledge that evolves. To address this, recent work has explored augmenting LLMs with knowledge graphs (KGs) to provide structured, up-to-date information. However, many existing approaches assume a static snapshot of the KG and overlook the temporal dynamics and factual inconsistencies inherent in real-world data. To address the challenge of reasoning over temporally shifting knowledge, we propose EvoReasoner, a temporal-aware multi-hop reasoning algorithm that performs global-local entity grounding, multi-route decomposition, and temporally grounded scoring. To ensure that the underlying KG remains accurate and up-to-date, we introduce EvoKG, a noise-tolerant KG evolution module that incrementally updates the KG from unstructured documents through confidence-based contradiction resolution and temporal trend tracking. We evaluate our approach on temporal QA benchmarks and a novel end-to-end setting where the KG is dynamically updated from raw documents. Our method outperforms both prompting-based and KG-enhanced baselines, effectively narrowing the gap between small and large LLMs on dynamic question answering. Notably, an 8B-parameter model using our approach matches the performance of a 671B model prompted seven months later. These results highlight the importance of combining temporal reasoning with KG evolution for robust and up-to-date LLM performance. Our code is publicly available at github.com/junhongmit/TREK.

cs.LG↗