arXiv subjects

Jian Song

Publications and source records attributed to Jian Song.

At least 37 records · Page 2Linked to original sources

arXiv2026

From Technical Metrics to User Perception: A User Study of a Multimodal Human-Robot Interaction System for Object Detection and Grasping

Improvements in the technical performance of human--robot interaction (HRI) systems do not automatically translate into differences that human users can detect during live interaction. This paper investigates whether a 15 percentage point gain in end-to-end task success (from 75% in a multimodal baseline system to 90% in an improved configuration identified through a prior ablation study) is sufficient to produce consistent and measurable differences in user perception. The baseline system combines Whisper for speech recognition, Florence-2 for open-vocabulary object detection, LLaMA 3.1 for action extraction, and an interval Type-2 fuzzy logic controller for motion execution. The improved configuration replaces the perception and language modules with Grounding DINO + SAM and Qwen 3.5 9B, respectively, while retaining the same controller. A within-subject user study with 24 participants compared both systems on the same tabletop object-grasping task. After interacting with each configuration, participants rated perceived speed, reliability, and overall competence and fluency on a 7-point Likert scale. Results show that 17 out of 24 participants (70.83%) preferred the improved system (exact binomial test, p = 0.043, h = 0.43), and all three perceptual constructs were rated significantly higher for the improved configuration after Holm correction, with large to very large effect sizes (p < 0.001). These findings confirm that the identified technical improvements are perceptible to users in direct interaction and underscore the importance of complementing benchmark evaluation with user-centred evidence when assessing robotic manipulation pipelines.

cs.RO↗

arXiv2026

EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery

LLM-based agents have shown increasing potential in automating scientific discovery. Given an optimizable metric and an execution environment, they can propose, validate, and iterate scientific solutions, and have produced results that outperform human-designed approaches. As model capabilities continue to improve, we argue that the bottleneck for autonomous scientific discovery is shifting from prescribing agent workflows to designing agent environments: the resources, constraints, and interfaces that shape agent behavior. We frame this as environment engineering: building environments that amplify productive behaviors, such as open-ended exploration, systematic artifact management, and inter-agent collaboration, while suppressing harmful behaviors, such as reward hacking and high-friction human oversight. We present EurekAgent, an environment-engineered agent system for metric-driven autonomous scientific discovery. EurekAgent engineers the environment along four dimensions: permissions engineering for bounded agent execution and isolated evaluation; artifact engineering for filesystem and Git-based collaboration; budget engineering for budget-aware exploration; and human-in-the-loop engineering for easy human supervision and intervention. EurekAgent sets new state-of-the-art results on multiple mathematics, kernel engineering, and machine learning tasks, including new state-of-the-art 26-circle packing results discovered with less than $11 in total API cost. We open-source our code and results, and call for environment engineering as a core research direction for developing reliable autonomous research agents.

cs.AI↗

arXiv2026

Stochastic partial differential equations associated with Feller processes

For the stochastic partial differential equation $\frac{\partial u}{\partial t}=\mathcal L u +u\dot W$ where $\dot W$ is Gaussian noise colored in time and $\mathcal L$ is the infinitesimal generator of a Feller process $X$, we obtain Feynman-Kac type of representations for the Stratonovich and Skorohod solutions as well as for their moments. The regularity of the law and the Hölder continuity of the solutions are also studied.

math.PR↗

arXiv2026

Controlled fields, rough stochastic calculus, and Itô-Wentzell-Alekseev-Gröbner identities

We develop a calculus of space-time controlled fields for rough stochastic systems. This approach provides a unified composition rule for evaluating random fields along rough semimartingales and yields a rough stochastic Itô-Wentzell formula under natural and verifiable regularity assumptions. Our motivation comes from works of Hudde et al. (2024) and, independently, Del Moral and Singh (2022) where the authors established, respectively, Itô-Alekseev-Gröbner, backward Itô-Wentzell, and diffusion interpolation formulas.

math.PR↗

arXiv2026

RPC-Bench: A Fine-grained Benchmark for Research Paper Comprehension

Understanding research papers remains challenging for foundation models due to specialized scientific discourse and complex figures and tables, yet existing benchmarks offer limited fine-grained evaluation at scale. To address this gap, we introduce RPC-Bench, a large-scale question-answering benchmark built from review-rebuttal exchanges of high-quality computer science papers, containing 15K human-verified QA pairs. We design a fine-grained taxonomy aligned with the scientific research flow to assess models' ability to understand and answer why, what, and how questions in scholarly contexts. We also define an elaborate LLM-human interaction annotation framework to support large-scale labeling and quality control. Following the LLM-as-a-Judge paradigm, we develop a scalable framework that evaluates models on correctness-completeness and conciseness, with high agreement to human judgment. Experiments reveal that even the strongest models (GPT-5) achieve only 68.2% correctness-completeness, dropping to 37.46% after conciseness adjustment, highlighting substantial gaps in precise academic paper understanding. Our code and data are available at https://rpc-bench.github.io/.

cs.CL↗

arXiv2026

Early Preconfiguration Failure: A Novel Predictor of the Repetitive Subconcussion

Early diagnosis and assessment of repetitive subconcussive (rSC) brain injuries are crucial for early clinical intervention. Conventional methods, largely relying on slow fMRI, fail to capture millisecond-level early cortical dynamics, particularly spatiotemporal features associated with pre-configuration dynamics. This study introduces a novel approach integrating dynamic hierarchical spatial features and cortical early behavioral time-domain sensitivity, utilizing EEG and visual attention tasks. We analyzed cortical early behaviors in 24 healthy controls (HC), 21 rSC patients,and a validation cohort of 25 cTBI patients from public datasets. Results reveal distinct temporal patterns in HC: elevated integration at 0-100 ms, rebound dynamics at 100-200ms, and visual perception integration peaks at 200-600 ms. In contrast, rSC patients exhibited significantly impaired dynamic features, with reduced integration levels indicating a decline in pre-configuration dynamics. Signed center distance (SCD) analysis of separation-integration trajectories showed significantly lower early SCD values in rSC patients compared to HC, while cTBI patients displayed negative SCD values, reflecting irreversible damage. Machine learning classification achieved optimal performance in distinguishing between HC, rSC, and cTBI groups using early cortical features, highlighting the critical role of millisecond-level cortical dynamics in rSC diagnosis.

q-bio.NC↗

arXiv2026

PLAS-Net: Pixel-Level Area Segmentation for UAV-Based Beach Litter Monitoring

Accurate quantification of the physical exposure area of beach litter, rather than simple item counts, is essential for credible ecological risk assessment of marine debris. However, automated UAV-based monitoring predominantly relies on bounding-box detection, which systematically overestimates the planar area of irregular litter objects. To address this geometric limitation, we develop PLAS-Net (Pixel-level Litter Area Segmentor), an instance segmentation framework that extracts pixel-accurate physical footprints of coastal debris. Evaluated on UAV imagery from a monsoon-driven pocket beach in Koh Tao, Thailand, PLAS-Net achieves a mAP_50 of 58.7% with higher precision than eleven baseline models, demonstrating improved mask fidelity under complex coastal conditions. To illustrate how the accuracy of the masking affects the conclusions of environmental analysis, we conducted three downstream demonstrations: (i) power-law fitting of normalized plastic density (NPD) to characterize fragmentation dynamics; (ii) area-weighted ecological risk index (ERI) to map spatial pollution hotspots; and (iii) source composition analysis revealing the abundance-area paradox: fishing gear constitutes a small proportion of the total number of items, but has the largest physical area per unit item. Pixel-level area extraction can provide more valuable information for coastal monitoring compared to methods based solely on counting.

cs.CV↗

arXiv2026

Virtual Polarization Modulation: Enabling CSI-Free DCO-OFDM over Dynamic OWC Channels

In dynamically varying optical wireless communication (OWC) links, conventional quadrature amplitude modulation (QAM) in optical orthogonal frequency-division multiplexing (OFDM) requires frequent channel estimation and equalization, incurring pilot overhead and processing latency. This paper proposes a virtual polarization modulation (VPM)-based direct-current-biased optical OFDM (DCO-OFDM) scheme that maps each data symbol onto the three-dimensional Stokes space and places its corresponding Jones vector across two adjacent OFDM subcarriers. Using a rotation-based analytical framework, closed-form symbol error rate (SER) expressions are derived for arbitrary spherical constellations, along with upper and lower bounds and high signal-to-noise ratio (SNR) approximations. The framework is further extended to practical OWC scenarios with frequency-selective channels and atmospheric turbulence. Monte Carlo (MC) simulations validate the theoretical results. The results show that under practical OWC impairments, VPM outperforms QAM with least-squares (LS) channel estimation and minimum mean square error (MMSE) equalization. At a target SER of $10^{-5}$, 16-VPM achieves SNR gains of approximately 7.5 dB and 4 dB over equalized 16-QAM and 8-QAM, respectively, in frequency-selective channels, and a 6 dB advantage over equalized 16-QAM under atmospheric turbulence. By eliminating the need for channel state information, the proposed VPM-based DCO-OFDM provides a robust and low-latency solution for dynamic OWC links.

physics.optics↗

arXiv2026

BCMI-Driven Motion Control Detection: EEG-Based Machine Learning and Interaction Entropy for High-Order Brain Networks

This study investigates the cognitive motor control detection and the underlying neuroregulatory mechanisms during music-assisted simulated driving. Using a dynamic higher-order network model constructed with EEG-based cross-information entropy, we quantify the dynamic coordination within brain networks activated during both music listening and driving. This approach, which contrasts with previous static network analyses, provides novel insights into how musical stimuli modulate the complex interplay of brain regions during demanding tasks. Results demonstrated enhanced third-order connectivity and elevated higher-order information entropy in music-stimulated driving compared to baseline driving, as evidenced by increasing Phi values of higher-order network indices. Supervised machine learning, including support vector machines, revealed a strong correlation between model accuracy and ROC-AUC values and the hierarchy of brain network features. This underscores the importance of higher-order features in decoding brain motor-control states during music-simulated driving. These findings deepen our understanding of the interplay between music cognition and motor control, offering valuable insights for the development of novel brain-computer-music interfaces (BCMI) and adaptive human-machine systems to enhance performance in demanding tasks like driving.

q-bio.NC↗

arXiv2026

Doppler Shift Keying Modulation for Uplink Multiple Access over Doubly-Dispersive Channels

The delay-Doppler (DD) domain modulation has been regarded as one of the most competitive candidates to support wireless communications for emerging high-mobility applications in the sixth-generation mobile networks. Unfortunately, most of the existing designs for DD domain modulation suffer from high peak-to-average power ratio (PAPR) and unbearable detection complexity under uplink transmission since large time duration and bandwidth are required to guarantee high DD resolutions. To address these issues, the Doppler shift keying (DSK) modulation based on the orthogonal delay Doppler division multiplexing modulator is proposed in this paper, where the input-output characterization in the DD domain is fully exploited. The principle of the DSK transceiver is first established with the one-hot mapper and low-complexity iterative successive interference cancellation-maximum ratio combining detector for point-to-point scenarios. The proposed scheme is then generalized to the zero auto-correlation sequence-based implementation, which benefits the extension of multi-user (MU) uplink DSK frameworks. For uplink DSK transmission, Zadoff-Chu (ZC) sequences are adopted as the basis sequences. We optimize the assignment of ZC roots to different user equipments (UEs) by minimizing the maximum inter-user interference. This optimization process, which analyzes the root allocation, directly assigns a specific ZC sequence to each UE. The PAPR and bit error rate performance of the proposed DSK modulation with the low-complexity detector is finally verified by extensive simulation results under doubly-dispersive channels, which demonstrates the superiority of DSK modulation especially for uplink multiple access over doubly dispersive channels.

eess.SP↗

arXiv2026

On a fractional stochastic heat equation arising from the disordered pinning model

We study the mild Skorohod solution to the following fractional stochastic heat equation on $\mathbb{R}$: \begin{equation} \begin{cases} \partial_t u(t,x)=-(-Δ)^{ρ/2} u(t,x) +βu(t,x)δ_0(x)ξ(t),\\ u(0,\cdot)=u_0(x), \end{cases} \end{equation} where $-(-Δ)^{ρ/2}$ with $ρ\in(0,2]$ is the fractional Laplacian and $ξ$ is a Gaussian noise with covariance $\mathbb{E}[ξ(t) ξ(s)]=|t-s|^{2H-2}$ for $H\in(\frac12, 1]$. This equation with $ρ\in(1,2]$ arises naturally in the study of the disordered pinning model. We show that the equation admits a local $L^2$-solution when $ρ= 2$, whereas, for $ρ\in (0,2)$, any solution--if it exists uniquely--cannot be $L^p$-integrable for any $p > 1$. Moreover, inspired by the recent work of Quastel, Ramirez and Virág, we prove that the equation has a unique global $L^1$-solution whenever $\frac{1}ρ+1<2H$. We also establish the strict positivity of the solution. Our work partially fills the gap in the study of the Weinrib-Halperin prediction.

math.PR↗

arXiv2026

On a pinning model in correlated Gaussian random environments

We consider a pinning model in correlated Gaussian random environments. For the model that is disorder relevant, we study its intermediate disorder regime and show that the rescaled partition functions converge to a non-trivial continuum limit in the Skorohod setting and in the Stratonovich setting, respectively. Our results partially confirm the Weinrib--Halperin prediction for disorder relevance/irrelevance.

math.PR↗

arXiv2026

Fundamental groups of compact Kahler varieties with nef anti canonical bundle

It is proved by M. Paun (1997, 2017) that the fundamental group of a compact Kahler manifold X is almost Abelian if the anti-canonical bundle -KX is nef. In this paper, we apply the recent geometric analytic theory of Kahler spaces developed by Guo-Phong-Song-Sturm to study fundamental groups of mildly singular compact Kahler varieties. We first extend Paun's result to log canonical pairs (X,Delta) with smooth X and nef -(KX+Delta) as well as to compact Kahler manifolds X with pseudo-effective -KX under a suitable assumption on the singularities of c1(-KX). We further prove that, for a 3-dimensional log canonical pair (X,Δ) with X being klt, pi 1(X) is almost Abelian if -(KX+Δ) is nef. Moreover, as one of the main ingredients for the proof of these results, we establish the surjectivity of the Albanese maps of compact normal complex varieties X in Fujiki class C that admits an effective R-divisor Δsuch that the pair (X,Δ) is log canonical with nef anti-log canonical divisor -(KX+Δ).This generalizes the corresponding theorems for projective varieties (Zhang, 2005), for klt pairs (Matsumura-Wang-Wu-Zhang, 2025) and for log smooth case (Fu-Han-Zou, 2025)

math.AG↗

arXiv2026

Activation-wise Propagation: A One-Timestep Strategy for Spiking Neural Networks

Spiking neural networks (SNNs) have demonstrated significant potential in real-time multi-sensor perception tasks due to their event-driven and parameter-efficient characteristics. A key challenge is the timestep-wise iterative update of neuronal hidden states (membrane potentials), which complicates the trade-off between accuracy and latency. SNNs tend to achieve better performance with longer timesteps, inevitably resulting in higher computational overhead and latency compared to artificial neural networks (ANNs). Moreover, many recent advances in SNNs rely on architecture-specific optimizations, which, while effective with fewer timesteps, often limit generalizability and scalability across modalities and models. To address these limitations, we propose Activation-wise Membrane Potential Propagation (AMP2), a unified hidden state update mechanism for SNNs. Inspired by the spatial propagation of membrane potentials in biological neurons, AMP2 enables dynamic transmission of membrane potentials among spatially adjacent neurons, facilitating spatiotemporal integration and cooperative dynamics of hidden states, thereby improving efficiency and accuracy while reducing reliance on extended temporal updates. This simple yet effective strategy significantly enhances SNN performance across various architectures, including MLPs and CNNs for point cloud and event-based data. Furthermore, ablation studies integrating AMP2 into Transformer-based SNNs for classification tasks demonstrate its potential as a general-purpose and efficient solution for spiking neural networks.

cs.CV↗

arXiv2026

Experience-Driven Multi-Agent Systems Are Training-free Context-aware Earth Observers

Recent advances have enabled large language model (LLM) agents to solve complex tasks by orchestrating external tools. However, these agents often struggle in specialized, tool-intensive domains that demand long-horizon execution, tight coordination across modalities, and strict adherence to implicit tool constraints. Earth Observation (EO) tasks exemplify this challenge due to the multi-modal and multi-temporal data inputs, as well as the requirements of geo-knowledge constraints (spectrum library, spatial reasoning, etc): many high-level plans can be derailed by subtle execution errors that propagate through a pipeline and invalidate final results. A core difficulty is that existing agents lack a mechanism to learn fine-grained, tool-level expertise from interaction. Without such expertise, they cannot reliably configure tool parameters or recover from mid-execution failures, limiting their effectiveness in complex EO workflows. To address this, we introduce \textbf{GeoEvolver}, a self-evolving multi-agent system~(MAS) that enables LLM agents to acquire EO expertise through structured interaction without any parameter updates. GeoEvolver decomposes each query into independent sub-goals via a retrieval-augmented multi-agent orchestrator, then explores diverse tool-parameter configurations at the sub-goal level. Successful patterns and root-cause attribution from failures are then distilled in an evolving memory bank that provides in-context demonstrations for future queries. Experiments on three tool-integrated EO benchmarks show that GeoEvolver consistently improves end-to-end task success, with an average gain of 12\% across multiple LLM backbones, demonstrating that EO expertise can emerge progressively from efficient, fine-grained interactions with the environment.

cs.AI↗

arXiv2026

Delay-Aware Task Offloading for Heterogeneous VLC-RF-based Vehicular Fog Computing

Vehicular fog computing (VFC) is a promising paradigm for reducing the computation burden of vehicles, thus supporting delay-sensitive services in next-generation transportation networks. However, traditional VFC schemes rely on radio frequency (RF) communications, which limits their adaptability for dense vehicular environments. In this paper, a heterogeneous visible light communication (VLC)-RF architecture is designed for VFC systems to facilitate efficient task offloading. Specifically, computing tasks are dynamically partitioned and offloaded to idle vehicles via both VLC and RF links, thereby fully exploiting the interference resilience of VLC and the coverage advantage of RF. To minimize the average task processing delay (TPD), an optimization problem of task offloading and computing resource allocation is formulated, and then solved by the developed residual-based majorization-minimization (RBMM) algorithm. Simulation results confirm that the heterogeneous VLC-RF architecture with the proposed algorithm achieves a 15% average TPD reduction compared to VFC systems relying solely on VLC or RF.

eess.SP↗

arXiv2026

One-Shot Price Forecasting with Covariate-Guided Experts under Privacy Constraints

Forecasting in power systems often involves multivariate time series with complex dependencies and strict privacy constraints across regions. Traditional forecasting methods require significant expert knowledge and struggle to generalize across diverse deployment scenarios. Recent advancements in pre-trained time series models offer new opportunities, but their zero-shot performance on domain-specific tasks remains limited. To address these challenges, we propose a novel MoE Encoder module that augments pretrained forecasting models by injecting a sparse mixture-of-experts layer between tokenization and encoding. This design enables two key capabilities: (1) trans forming multivariate forecasting into an expert-guided univariate task, allowing the model to effectively capture inter-variable relations, and (2) supporting localized training and lightweight parameter sharing in federated settings where raw data cannot be exchanged. Extensive experiments on public multivariate datasets demonstrate that MoE-Encoder significantly improves forecasting accuracy compared to strong baselines. We further simulate federated environments and show that transferring only MoE-Encoder parameters allows efficient adaptation to new regions, with minimal performance degradation. Our findings suggest that MoE-Encoder provides a scalable and privacy-aware extension to foundation time series models.

cs.LG↗

arXiv2025

How Light Shapes Memory: Beta Synchrony in the Temporal-Parietal Cortex Predicts Cognitive Ergonomics for BCI Applications

Working memory is a promising paradigm for assessing cognitive ergonomics of brain states in brain-computer interfaces(BCIs). This study decodes these states with a focus on environmental illumination effects via two distinct working memory tasks(Recall and Sequence) for mixed-recognition analysis. Leveraging nonlinear patterns in brain connectivity, we propose an innovative framework: multi-regional dynamic interplay patterns based on beta phase synchrony dynamics, to identify low-dimensional EEG regions (prefrontal, temporal, parietal) for state recognition. Based on nonlinear phase map analysis of the above three brain regions using beta-phase connectivity, we found that: (1)Temporal-parietal phase clustering outperforms other regional combinations in distinguishing memory states; (2)Illumination-enhanced environments optimize temporoparietal balance;(3) Machine learning confirms temporal-parietal synchrony as the dominant cross-task classification feature. These results provide a precise prediction algorithm, facilitating a low-dimensional system using temporal and parietal EEG channels with practical value for real-time cognitive ergonomics assessment in BCIs and optimized human-machine interaction.

q-bio.NC↗