arXiv subjects

Song Wang

Publications and source records attributed to Song Wang.

At least 127 records · Page 7Linked to original sources

arXiv2026

Privacy-Concealing Cooperative Perception for BEV Scene Segmentation

Cooperative perception systems for autonomous driving aim to overcome the limited perception range of a single vehicle by communicating with adjacent agents to share sensing information. While this improves perception performance, these systems also face a significant privacy-leakage issue, as sensitive visual content can potentially be reconstructed from the shared data. In this paper, we propose a novel Privacy-Concealing Cooperation (PCC) framework for Bird's Eye View (BEV) semantic segmentation. Based on commonly shared BEV features, we design a hiding network to prevent an image reconstruction network from recovering the input images from the shared features. An adversarial learning mechanism is employed to train the network, where the hiding network works to conceal the visual clues in the BEV features while the reconstruction network attempts to uncover these clues. To maintain segmentation performance, the perception network is integrated with the hiding network and optimized end-to-end. The experimental results demonstrate that the proposed PCC framework effectively degrades the quality of the reconstructed images with minimal impact on segmentation performance, providing privacy protection for cooperating vehicles. The source code will be made publicly available upon publication.

cs.CV↗

arXiv2026

BrainTAP: Brain Disorder Prediction with Adaptive Distill and Selective Prior Integration

Predicting clinical outcomes from brain networks in large-scale neuroimaging cohorts such as the Adolescent Brain Cognitive Development (ABCD) study requires effectively integrating functional connectivity (FC) and structural connectivity (SC) while incorporating expert neurobiological knowledge. However, existing multimodal fusion approaches are shallow or over-homogenize the inherently heterogeneous characteristics of FC and SC, while expert-defined anatomical priors are underutilized with static integration. To address these limitations, we propose Brain Transformer with Adaptive Mutual-Distill and Selective Prior Fusion (BrainTAP). We introduce Adaptive Mutual Distill (AMD), which enables layer-wise information exchange between modalities through learnable distill-intact ratios, preserving modality-specific signals while capturing cross-modal synergies. We further develop Selective Prior Fusion (SPF), which integrates expert-defined anatomical priors in an adaptive way. Evaluated on the ABCD dataset for predicting attention-related disorders, BrainTAP achieves superior performance over state-of-the-art baselines, demonstrating its effectiveness for brain disorder prediction.

cs.CE↗

arXiv2026

How Much Reasoning Do Retrieval-Augmented Models Add beyond LLMs? A Benchmarking Framework for Multi-Hop Inference over Hybrid Knowledge

Large language models (LLMs) continue to struggle with knowledge-intensive questions that require up-to-date information and multi-hop reasoning. Augmenting LLMs with hybrid external knowledge, such as unstructured text and structured knowledge graphs, offers a promising alternative to costly continual pretraining. As such, reliable evaluation of their retrieval and reasoning capabilities becomes critical. However, many existing benchmarks increasingly overlap with LLM pretraining data, which means answers or supporting knowledge may already be encoded in model parameters, making it difficult to distinguish genuine retrieval and reasoning from parametric recall. We introduce HybridRAG-Bench, a framework for constructing benchmarks to evaluate retrieval-intensive, multi-hop reasoning over hybrid knowledge. HybridRAG-Bench automatically couples unstructured text and structured knowledge graph representations derived from recent scientific literature on arXiv, and generates knowledge-intensive question-answer pairs grounded in explicit reasoning paths. The framework supports flexible domain and time-frame selection, enabling contamination-aware and customizable evaluation as models and knowledge evolve. Experiments across three domains (artificial intelligence, governance and policy, and bioinformatics) demonstrate that HybridRAG-Bench rewards genuine retrieval and reasoning rather than parametric recall, offering a principled testbed for evaluating hybrid knowledge-augmented reasoning systems. We release our code and data at github.com/junhongmit/HybridRAG-Bench.

cs.LG↗

arXiv2026

The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation

Data-centric distillation, including data augmentation, selection, and mixing, offers a promising path to creating smaller, more efficient student Large Language Models (LLMs) that retain strong reasoning abilities. However, there still lacks a comprehensive benchmark to systematically assess the effect of each distillation approach. This paper introduces DC-CoT, the first data-centric benchmark that investigates data manipulation in chain-of-thought (CoT) distillation from method, model and data perspectives. Utilizing various teacher models (e.g., o4-mini, Gemini-Pro, Claude-3.5) and student architectures (e.g., 3B, 7B parameters), we rigorously evaluate the impact of these data manipulations on student model performance across multiple reasoning datasets, with a focus on in-distribution (IID) and out-of-distribution (OOD) generalization, and cross-domain transfer. Our findings aim to provide actionable insights and establish best practices for optimizing CoT distillation through data-centric techniques, ultimately facilitating the development of more accessible and capable reasoning models. The codebase can be accessed at https://github.com/UNITES-Lab/Distillation-Bench

cs.AI↗

arXiv2026

MedRoute: RL-Based Dynamic Specialist Routing in Multi-Agent Medical Diagnosis

Medical diagnosis using Large Multimodal Models (LMMs) has gained increasing attention due to capability of these models in providing precise diagnoses. These models generally combine medical questions with visual inputs to generate diagnoses or treatments. However, they are often overly general and unsuitable under the wide range of medical conditions in real-world healthcare. In clinical practice, diagnosis is performed by multiple specialists, each contributing domain-specific expertise. To emulate this process, a potential solution is to deploy a dynamic multi-agent LMM framework, where each agent functions as a medical specialist. Current approaches in this emerging area, typically relying on static or predefined selection of various specialists, cannot be adapted to the changing practical scenario. In this paper, we propose MedRoute, a flexible and dynamic multi-agent framework that comprises of a collaborative system of specialist LMM agents. Furthermore, we add a General Practitioner with an RL-trained router for dynamic specialist selection, and a Moderator that produces the final decision. In this way, our framework closely mirrors real clinical workflows. Extensive evaluations on text and image-based medical datasets demonstrate improved diagnostic accuracy, outperforming the state-of-the-art baselines. Our work lays a strong foundation for future research. Code and models are available at https://github.com/UCF-CRCV/MedRoute/.

eess.IV↗

arXiv2026

Physics-Driven Local-Whole Elastic Deformation Modeling for Point Cloud Representation Learning

Existing point cloud representation learning methods primarily rely on data-driven strategies to extract geometric information from large amounts of scattered data. However, most methods focus solely on the spatial distribution features of point clouds while overlooking the relationship between local information and the whole structure, which limits the accuracy of point cloud representation. Local information reflect the fine-grained variations of an object, while the whole structure is determined by the interaction and combination of these local features, collectively defining the object's shape. In real-world, objects undergo deformation under external forces, and this deformation gradually affects the whole structure through the propagation of forces from local regions, thereby altering the object's geometric features. Therefore, appropriately introducing a physics-driven mechanism to capture the topological relationships between local parts and the whole object can effectively mitigate for the limitations of data-driven point cloud methods in structural modeling, and enhance the generalization and interpretability of point cloud representations for downstream tasks such as understanding and recognition. Inspired by this, we incorporate a physics-driven mechanism into the data-driven method to learn fine-grained features in point clouds and model the structural relationship between local regions and the whole shape. Specifically, we design a dual-task encoder-decoder framework that combines the geometric modeling capability of data-driven implicit fields with physics-driven elastic deformation. Through the integration of physics-based loss functions, the framework is guided to predict localized deformation and explicitly capture the correspondence between local structural changes and whole shape variations.

cs.CV↗

arXiv2026

GenMRP: A Generative Multi-Route Planning Framework for Efficient and Personalized Real-Time Industrial Navigation

Existing industrial-scale navigation applications contend with massive road networks, typically employing two main categories of approaches for route planning. The first relies on precomputed road costs for optimal routing and heuristic algorithms for generating alternatives, while the second, generative methods, has recently gained significant attention. However, the former struggles with personalization and route diversity, while the latter fails to meet the efficiency requirements of large-scale real-time scenarios. To address these limitations, we propose GenMRP, a generative framework for multi-route planning. To ensure generation efficiency, GenMRP first introduces a skeleton-to-capillary approach that dynamically constructs a relevant sub-network significantly smaller than the full road network. Within this sub-network, routes are generated iteratively. The first iteration identifies the optimal route, while the subsequent ones generate alternatives that balance quality and diversity using the newly proposed correctional boosting approach. Each iteration incorporates road features, user historical sequences, and previously generated routes into a Link Cost Model to update road costs, followed by route generation using the Dijkstra algorithm. Extensive experiments show that GenMRP achieves state-of-the-art performance with high efficiency in both offline and online environments. To facilitate further research, we have publicly released the training and evaluation dataset. GenMRP has been fully deployed in a real-world navigation app, demonstrating its effectiveness and benefits.

cs.RO↗

arXiv2026

RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents

LLM-based deep research agents are largely built on the ReAct framework. This linear design makes it difficult to revisit earlier states, branch into alternative search directions, or maintain global awareness under long contexts, often leading to local optima, redundant exploration, and inefficient search. We propose Re-TRAC, an agentic framework that performs cross-trajectory exploration by generating a structured state representation after each trajectory to summarize evidence, uncertainties, failures, and future plans, and conditioning subsequent trajectories on this state representation. This enables iterative reflection and globally informed planning, reframing research as a progressive process. Empirical results show that Re-TRAC consistently outperforms ReAct by 15-20% on BrowseComp with frontier LLMs. For smaller models, we introduce Re-TRAC-aware supervised fine-tuning, achieving state-of-the-art performance at comparable scales. Notably, Re-TRAC shows a monotonic reduction in tool calls and token usage across rounds, indicating progressively targeted exploration driven by cross-trajectory reflection rather than redundant search.

cs.CL↗

arXiv2026

Dynamical Mass Loss at the End of TP-AGB stars

The thermally pulsating asymptotic giant branch (TP-AGB) phase plays a key role in the evolution of low- to intermediate-mass stars, driving mass loss that influences their final stages and contributes to galactic chemical enrichment. However, the mechanisms behind mass loss, particularly at the end of AGB, are still not well understood. We aim to investigate the relationship between stellar parameters and envelope dynamics during the TP-AGB phase, evaluating whether dynamical instabilities in the envelope can act as a possible mass-loss mechanism. We use hydrodynamics method in MESA to simulate the dynamical pulsations and resulting mass loss during the TP-AGB phase of a star evolved from a 1.5 Msun zero-age main sequence. Our simulations reproduce the dynamical pulsation behavior of stars during the TP-AGB phase, demonstrating that the envelope mass is a key factor governing pulsational properties. As the envelope mass decreases, both the pulsation period and radial amplitude increase, consistent with observational trends. For 1.5 Msun model, once the envelope mass declines to approximately 0.25 Msun, the model enters a regime of violent pulsations, potentially ejecting the remaining envelope within a few hundred years. We suggest that the instability can act as the dominant mass-loss mechanism in the end of the TP-AGB phase, marking a rapid transitional stage toward the post-AGB phase.

astro-ph.SR↗

arXiv2026

Evolution of Stellar Activity and Habitable Zone II: Ca H&K Emissions of Late-type Dwarfs

Stellar chromospheric activity serves as a valuable proxy for estimating stellar ages, though its applicable range and accurate functional form are still debated. In this study, utilizing the LAMOST spectra we compiled a catalog of open cluster members and field stars to investigate $R_{\rm{HK}}^{'}$--age relations across various spectral types. We find that a linear model, specifically a Skumanich-type relation, can best describe the overall decline of chromospheric activity with age, with the slope varying across different spectral types. However, we also identify variations in the decay rate along the main sequence, which call for more accurate follow-up investigation. Finally, we find that lower-metallicity stars exhibit enhanced activity for F-, G-, and K-type stars, whereas no clear metallicity dependence is observed for M dwarfs.

astro-ph.SR↗

arXiv2026

Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction

Large Language Model based multi-agent systems (MAS) excel at collaborative problem solving but remain brittle to cascading errors: a single faulty step can propagate across agents and disrupt the trajectory. In this paper, we present MASC, a metacognitive framework that endows MAS with real-time, unsupervised, step-level error detection and self-correction. MASC rethinks detection as history-conditioned anomaly scoring via two complementary designs: (1) Next-Execution Reconstruction, which predicts the embedding of the next step from the query and interaction history to capture causal consistency, and (2) Prototype-Guided Enhancement, which learns a prototype prior over normal-step embeddings and uses it to stabilize reconstruction and anomaly scoring under sparse context (e.g., early steps). When an anomaly step is flagged, MASC triggers a correction agent to revise the acting agent's output before information flows downstream. On the Who&When benchmark, MASC consistently outperforms all baselines, improving step-level error detection by up to 8.47% AUC-ROC ; When plugged into diverse MAS frameworks, it delivers consistent end-to-end gains across architectures, confirming that our metacognitive monitoring and targeted correction can mitigate error propagation with minimal overhead.

cs.AI↗

arXiv2026

Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems

The rapid advancement of autonomous systems, including self-driving vehicles and drones, has intensified the need to forge true Spatial Intelligence from multi-modal onboard sensor data. While foundation models excel in single-modal contexts, integrating their capabilities across diverse sensors like cameras and LiDAR to create a unified understanding remains a formidable challenge. This paper presents a comprehensive framework for multi-modal pre-training, identifying the core set of techniques driving progress toward this goal. We dissect the interplay between foundational sensor characteristics and learning strategies, evaluating the role of platform-specific datasets in enabling these advancements. Our central contribution is the formulation of a unified taxonomy for pre-training paradigms: ranging from single-modality baselines to sophisticated unified frameworks that learn holistic representations for advanced tasks like 3D object detection and semantic occupancy prediction. Furthermore, we investigate the integration of textual inputs and occupancy representations to facilitate open-world perception and planning. Finally, we identify critical bottlenecks, such as computational efficiency and model scalability, and propose a roadmap toward general-purpose multi-modal foundation models capable of achieving robust Spatial Intelligence for real-world deployment.

cs.CV↗

arXiv2026

Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future

Autonomous driving has long relied on modular "Perception-Decision-Action" pipelines, where hand-crafted interfaces and rule-based components often break down in complex or long-tailed scenarios. Their cascaded design further propagates perception errors, degrading downstream planning and control. Vision-Action (VA) models address some limitations by learning direct mappings from visual inputs to actions, but they remain opaque, sensitive to distribution shifts, and lack structured reasoning or instruction-following capabilities. Recent progress in Large Language Models (LLMs) and multimodal learning has motivated the emergence of Vision-Language-Action (VLA) frameworks, which integrate perception with language-grounded decision making. By unifying visual understanding, linguistic reasoning, and actionable outputs, VLAs offer a pathway toward more interpretable, generalizable, and human-aligned driving policies. This work provides a structured characterization of the emerging VLA landscape for autonomous driving. We trace the evolution from early VA approaches to modern VLA frameworks and organize existing methods into two principal paradigms: End-to-End VLA, which integrates perception, reasoning, and planning within a single model, and Dual-System VLA, which separates slow deliberation (via VLMs) from fast, safety-critical execution (via planners). Within these paradigms, we further distinguish subclasses such as textual vs. numerical action generators and explicit vs. implicit guidance mechanisms. We also summarize representative datasets and benchmarks for evaluating VLA-based driving systems and highlight key challenges and open directions, including robustness, interpretability, and instruction fidelity. Overall, this work aims to establish a coherent foundation for advancing human-compatible autonomous driving systems.

cs.RO↗

arXiv2025

Detection of dark companions via the combination of eclipse timing variation, Hipparcos and/or Gaia astrometry: the cases of V Puppis and CY Ari

The third body is expected to shape the formation and evolution of close binary systems. In this work, we develop a method to detect and characterize the tertiary companion around eclipsing binaries through the combined analysis of eclipse timing variation, Hipparcos and/or Gaia astrometry. This method allows us to determine both the true mass and the inclination of the tertiary body that inferred from light-travel time effect. For the massive B-type binary V Pup, we do not confirm the previously reported 5.47-yr signal; instead, we identify a longer period of 14 yr. The orbital semi-major axis and mass of the outer body are revised to $a_C={17.88}_{-0.15}^{+0.15}$\,au and $M_C={7.73}_{-0.14}^{+0.14}\,M_\odot$, confirming it as a promising stellar-mass black-hole candidate for further follow-up study. For the tertiary of the contact binary CY Ari, we obtain $P_C=5.406_{-0.016}^{+0.017}$ yr, $e_C=0.526_{-0.027}^{+0.032}$, $I_C={85.6}_{-6.5}^{+7.8}$$^\circ$, and a true mass of $M_C=0.640_{-0.029}^{+0.029}\,M_\odot$, supporting the white dwarf hypothesis proposed in previous study. The orbits of both systems are nearly edge-on ($I=90^{\circ}$), implying that they may form in a coplanar environment. We highlight the advantages of our method for detecting dark companions in binary and triple systems.

astro-ph.SR↗

arXiv2025

IGR J17091-3624: Newly Formed Periodic Dips and Multiwavelength Activity During the 2025 Outburst

The black hole low-mass X-ray binary (LMXB) candidate IGR J17091-3624 experienced a hard-state-only outburst in 2025. In this paper, we show that IXPE detected a series of intermittent X-ray dips, spanning a total interval of ~1 day. Subsequent observations with NICER, EP, NuSTAR, and Swift reveal that these dips recur with a period of 2.83$\pm$0.07 days and are accompanied by an increase in spectral hardness. This is the first time such quasi-periodic dipping behavior has been observed in this target since discovery. Our spectral analysis shows that the dips can be explained by obscuration from an ionized absorber characterized by an ionization parameter of $logξ$ ~1-3 erg cm s$^{-1}$ and an equivalent hydrogen column density of $N^{\rm zxipcf}_{\rm H}$~(1-30)$\times10^{22}$ cm$^{-2}$. The periodic reappearance of the absorber is likely caused by obscuring material located in the outer accretion disk, modulated by the binary orbital period. If confirmed, this period would suggest that the donor star in IGR J17091-3624 has deviated from the standard main-sequence evolutionary path and is likely a (partially) stripped giant. In the optical band, no significant periodicity or correlation with the X-ray dips was detected, whereas the radio counterpart exhibited a flat to steep spectrum, in contrast to the inverted spectrum typically observed during the hard state of LMXBs.

astro-ph.HE↗

arXiv2025

Decoding Human-LLM Collaboration in Coding: An Empirical Study of Multi-Turn Conversations in the Wild

Large language models (LLMs) are increasingly acting as dynamic conversational interfaces, supporting multi-turn interactions that mimic human-like conversation and facilitate complex tasks like coding. While datasets such as LMSYS-Chat-1M and WildChat capture real-world user-LLM conversations, few studies systematically explore the mechanisms of human-LLM collaboration in coding scenarios. What tortuous paths do users experience during the interaction process? How well do the LLMs follow instructions? Are users satisfied? In this paper, we conduct an empirical analysis on human-LLM coding collaboration using LMSYS-Chat-1M and WildChat datasets to explore the human-LLM collaboration mechanism, LLMs' instruction following ability, and human satisfaction. This study yields interesting findings: 1) Task types shape interaction patterns(linear, star and tree), with code quality optimization favoring linear patterns, design-driven tasks leaning toward tree structures, and queries preferring star patterns; 2) Bug fixing and code refactoring pose greater challenges to LLMs' instruction following, with non-compliance rates notably higher than in information querying; 3) Code quality optimization and requirements-driven development tasks show lower user satisfaction, whereas structured knowledge queries and algorithm designs yield higher levels. These insights offer recommendations for improving LLM interfaces and user satisfaction in coding collaborations, while highlighting avenues for future research on adaptive dialogue systems. We believe this work broadens understanding of human-LLM synergies and supports more effective AI-assisted development.

cs.SE↗

arXiv2025

Demystifying Errors in LLM Reasoning Traces: An Empirical Study of Code Execution Simulation

Understanding a program's runtime reasoning behavior, meaning how intermediate states and control flows lead to final execution results, is essential for reliable code generation, debugging, and automated reasoning. Although large language models (LLMs) can accurately predict program outputs, most prior work has focused on output accuracy and performance, treating reasoning as a black box. As a result, little is known about the structure or failure modes of their reasoning traces. To address this gap, we conduct the first empirical study on runtime behavior inference with reasoning LLMs, aiming to uncover and characterize errors in their reasoning traces. We curate a benchmark from HumanEval Plus and LiveCodeBench, containing 427 code snippets. For each snippet, we test three input types: regular, edge, and invalid. Twelve input values are selected per snippet, each paired with its ground-truth execution result. We evaluate four state-of-the-art reasoning LLMs. Our results show that these models reach accuracies between 85 percent and 98 percent across input types. We also analyze the produced reasoning traces and develop a taxonomy with nine categories of inference errors. Finally, we explore tool-augmented reasoning. Using failures in the Computation Errors category as a case study, our experiments show that this approach corrects 58 percent of such errors, demonstrating the potential of tool support for improving LLM reasoning.

cs.SE↗

arXiv2025

Variability of H$α$ chromospheric activity of solar-like stars revealed by the time-domain data of LAMOST Medium-Resolution Spectroscopic Survey

The variability of H$α$ chromospheric activity of solar-like stars is investigated by using the time-domain data of LAMOST Medium-Resolution Spectroscopic Survey (MRS). We use $R_\mathrm{Hα}$ index (ratio of H$α$ luminosity to bolometric luminosity) to measure the H$α$ activity intensity of a spectrum, and utilize the median of the $R_\mathrm{Hα}$ values of multiple observations ($R_\mathrm{Hα}^\mathrm{median}$) as the representative activity intensity of a stellar source. The H$α$ variability of a stellar source is indicated by the extent of $R_\mathrm{Hα}$ fluctuation ($R_\mathrm{Hα}^\mathrm{EXT}$) of multiple observations. Our sample shows that $R_\mathrm{Hα}^\mathrm{EXT}$ of solar-like stars is about one order of magnitude smaller than $R_\mathrm{Hα}^\mathrm{median}$. The distribution of $\log R_\mathrm{Hα}^\mathrm{EXT}$ versus $\log R_\mathrm{Hα}^\mathrm{median}$ reveals the distinct behaviors between the stellar source categories with lower ($\log R_\mathrm{Hα}^\mathrm{median} < -4.85$) and higher ($\log R_\mathrm{Hα}^\mathrm{median} > -4.85$) activity intensity. For the former stellar source category, the top envelope of the distribution first increases and then decreases with $\log R_\mathrm{Hα}^\mathrm{median}$; while for the latter category, the top envelope of the distribution is largely along a positive correlation line. In addition, for the stellar sources with lower activity intensity, the large-$\log R_\mathrm{Hα}^\mathrm{EXT}$ objects near the top envelope of the $\log R_\mathrm{Hα}^\mathrm{EXT}$ versus $\log R_\mathrm{Hα}^\mathrm{median}$ distribution tend to have long-term and regular variations of H$α$ activity; while for the stellar sources with higher activity intensity, the H$α$ variations are more likely to be random fluctuations.

astro-ph.SR↗