arXiv subjects

Ziyi Song

Publications and source records attributed to Ziyi Song.

14 recordsLinked to original sources

arXiv2026

DH-VLM: Dual-Horizon Cooperative Latent Reasoning for Autonomous Driving

Large-scale language models for autonomous driving enable enhanced global understanding and long-horizon planning. However, when deployed in isolated vehicles, limited sensing range and occlusions restrict reliable decision-making, and the substantial computational and latency overhead makes on-board deployment impractical. Cooperative driving provides a potential solution by leveraging external agents for information exchange, but existing methods remain limited in semantic reasoning capability under practical constraints. To address these challenges, we propose DH-VLM, a dual-horizon cooperative latent reasoning framework that enables asymmetric semantic cooperation between the infrastructure and ego vehicle. The infrastructure aggregates multi-layer hidden states to form a global-reasoning horizon latent guidance, which is integrated into the ego model through an Infrastructure-Driven Latent Evolution mechanism for conditional latent refinement. This enables the ego vehicle to leverage long-range contextual understanding while preserving autonomous decision-making within its local planning horizon. Furthermore, we construct a cooperation-oriented question-answer (QA) dataset covering fundamental scene understanding and ego-personalized comprehension to support counterfactual and safety-aware reasoning. Extensive experiments demonstrate that DH-VLM achieves state-of-the-art planning performance, outperforming the previous state of the art by 14.6% in L2 error and 26.9% in collision rate. Compared with query-based end-to-end cooperative driving methods, our approach reduces the communication cost by 57.3% and GPU memory usage by 25.5%, while maintaining strong robustness against infrastructure guidance errors, providing a practical and robust paradigm for cooperative autonomous driving.

cs.RO↗

arXiv2026

Field-Induced Dissociation Reveals Excitonic Long-Range Photocarrier Transport in Bulk-Insulating Bi2Se3 Nanoribbons

Photoexcited charge carriers in topological insulators display anomalously long-range transport at cryogenic temperatures, but the underlying mechanism remains under debate. Here we use a transverse electric field as a discriminating probe of photocarrier dynamics in bulk-insulating Sb-doped Bi2Se3 nanoribbons, combining scanning photocurrent microscopy (SPCM) with ultrafast transient photovoltage (TPV) measurements. SPCM shows that suppression of the photocurrent requires a transverse electric field nearly 50 times larger than that needed to deflect free carriers, yet comparable to the expected exciton dissociation field. TPV measurements at 12 K and low excitation fluence reveal that the photocarrier diffusivity exceeds the value implied by the Einstein relation and the measured drift mobility by more than an order of magnitude, a bound that holds even at the lower end of the fitting uncertainty. Together, these observations indicate that the long-range photoresponse is not carried by free charge carriers but by a charge-neutral correlated state.

cond-mat.mes-hall↗

arXiv2026

EMPA: Evaluating Persona-Aligned Empathy as a Process

Evaluating persona-aligned empathy in LLM-based dialogue agents remains challenging. User states are latent, feedback is sparse and difficult to verify in situ, and seemingly supportive turns can still accumulate into trajectories that drift from persona-specific needs. We introduce EMPA, a process-oriented framework that evaluates persona-aligned support as sustained intervention rather than isolated replies. EMPA distills real interactions into controllable, psychologically grounded scenarios, couples them with an open-ended multi-agent sandbox that exposes strategic adaptation and failure modes, and scores trajectories in a latent psychological space by directional alignment, cumulative impact, and stability. The resulting signals and metrics support reproducible comparison and optimization of long-horizon empathic behavior, and they extend to other agent settings shaped by latent dynamics and weak, hard-to-verify feedback.

cs.AI↗

arXiv2025

Multiple Source Localization via Local Radio Map Construction in Urban Environments

Accurately and efficiently addressing the multiple source localization (MSL) problem in urban environments, particularly designing a general method adaptable to an arbitrary number of sources, plays a crucial role in various fields such as cognitive radio (CR). Existing methods either fail to effectively utilize received signal strength (RSS) information without redundancy or lack generalizability to an arbitrary number of sources. In this work, we propose the Local Radio Map-Aided Multiple Source Localization Framework (LRM-MSL), which is a general method capable of handling an arbitrary number of sources. First, this framework constructs a local radio map that retains only the RSS information around the sources and binarizes it. Then, the connected component analysis tool is applied to the binarized map, which implements multi-source separation, transforming the MSL problem into a series of single-source localization (SSL) tasks. Finally, we design a numerical coordinate regression network to perform the SSL tasks. Since there is no publicly available RSS dataset for MSL, we construct the VaryTxLoc dataset to evaluate the performance of LRM-MSL. Experimental results demonstrate that LRM-MSL is an accurate and effective method, outperforming state-of-the-art approaches. Our code and dataset can be downloaded from https://github.com/hereis77/LRM-MSL.

eess.SP↗

arXiv2025

Echo-N1: Affective RL Frontier

The LLM field has spent a year perfecting RL for tasks machines already excel at, math, code, and deterministic reasoning, while completely sidestepping the domain that actually defines human intelligence: subjective, emotionally grounded, personality sensitive conversation. This space has often been regarded as inherently subjective and challenging to formalize, making it appear unsuitable for conventional RL pipelines. We show that it is not only possible and it is a solvable and transformative RL problem. We propose the first framework that infers user personality on the fly and optimizes model behavior toward personalized conversational preferences. Contrary to the widespread belief that RL collapses in non-verifiable settings, our method produces consistent, robust, and dramatic improvements in humanlike interaction quality. We also introduce the first dynamic emotional intelligence evaluation suite to quantify these gains. Our model, which is introduced as Echo-N1, behaves far above its base version and outperforming the proprietary Doubao 1.5 Character. This work establishes a new frontier for RL: optimizing models for the deeply subjective, deeply human dimensions of conversation.

cs.AI↗

arXiv2025

UniMM-V2X: MoE-Enhanced Multi-Level Fusion for End-to-End Cooperative Autonomous Driving

Autonomous driving holds transformative potential but remains fundamentally constrained by the limited perception and isolated decision-making with standalone intelligence. While recent multi-agent approaches introduce cooperation, they often focus merely on perception-level tasks, overlooking the alignment with downstream planning and control, or fall short in leveraging the full capacity of the recent emerging end-to-end autonomous driving. In this paper, we present UniMM-V2X, a novel end-to-end multi-agent framework that enables hierarchical cooperation across perception, prediction, and planning. At the core of our framework is a multi-level fusion strategy that unifies perception and prediction cooperation, allowing agents to share queries and reason cooperatively for consistent and safe decision-making. To adapt to diverse downstream tasks and further enhance the quality of multi-level fusion, we incorporate a Mixture-of-Experts (MoE) architecture to dynamically enhance the BEV representations. We further extend MoE into the decoder to better capture diverse motion patterns. Extensive experiments on the DAIR-V2X dataset demonstrate our approach achieves state-of-the-art (SOTA) performance with a 39.7% improvement in perception accuracy, a 7.2% reduction in prediction error, and a 33.2% improvement in planning performance compared with UniV2X, showcasing the strength of our MoE-enhanced multi-level cooperative paradigm.

cs.RO↗

arXiv2025

Repulsive Mixture Model with Projection Determinantal Point Process

In many scientific domains, clustering aims to reveal interpretable latent structure that reflects relevant subpopulations or processes. Widely used Bayesian mixture models for model-based clustering often produce overlapping or redundant components because priors on cluster locations are specified independently, hindering interpretability. To mitigate this, repulsive priors have been proposed to encourage well-separated components, yet existing approaches face both computational and theoretical challenges. We introduce a fully tractable Bayesian repulsive mixture model by assigning a projection Determinantal Point Process (DPP) prior to the component locations. Projection DPPs induce strong repulsion and allow exact sampling, enabling parsimonious and interpretable posterior clustering. Leveraging their analytical tractability, we derive closed-form posterior and predictive distributions. These results, in turn, enable two efficient inference algorithms: a conditional Gibbs sampler and the first fully implementable marginal sampler for DPP-based mixtures. We also provide strong frequentist guarantees, including posterior consistency for density estimation, elimination of redundant components, and contraction of the mixing measure. Simulation studies confirm superior mixing and clustering performance compared to alternatives in misspecified settings. Finally, we demonstrate the utility of our method on event-related potential functional data, where it uncovers interpretable neuro-cognitive subgroups. Our results support the projection DPP mixtures as a theoretically sound and practically effective solution for Bayesian clustering.

stat.ME↗

arXiv2025

Impact of Level 2/3 Automated Driving Technology on Road Work Zone Safety

As China's road network enters the maintenance era, work zones will become a common sight on the roads. With the development of automated driving, vehicles equipped with Level 2/3 automated driving capabilities will also become a common presence on the roads. When these vehicles pass through work zones, automated driving may disengage, which can have complex effects on traffic safety. This paper explores the impact of Level 2/3 automated driving technology on road safety in high-speed highway work zone environments. Through microscopic traffic simulation method and using full-type traffic conflict technique, factors such as market penetration rate (MPR), traffic volume level, disengagement threshold, and driver takeover style are studied to understand their impact on work zone safety. The study found that the impact of automated driving technology on work zone safety is complex. Disengagement of automated vehicles in work zones reduces the proportion of vehicles that can maintain automated driving status. If takeover is not timely or adequate, it can easily lead to new traffic conflicts. Different factors have varying degrees of impact on work zone safety. Increasing MPR helps reduce the occurrence of single-vehicle conflicts, but it also increases the possibility of multi-vehicle conflicts. Therefore, future research and improvement directions should focus on optimizing the disengagement detection and takeover mechanisms of automated driving systems.

cs.AI↗

arXiv2025

Super-diffusion of Photoexcited Carriers in Topological Insulator Nanoribbons

Understanding the ultrafast dynamics and transport of photoexcited carriers in topological insulators is crucial for the optical manipulation of spins and may shed light on the nature of topological excitons. Here we investigate bulk-insulating Sb-doped $\mathrm{Bi_2Se_3}$ nanoribbons via ultrafast transient photovoltage microscopy. The probe-pulse-induced photovoltage is substantially suppressed by a pump pulse. Recovery time increases from 50 to 1600 picoseconds as the pump fluence increases. We found that the diffusivity of photoexcited carriers increases significantly at lower carrier concentrations, up to 800 cm$^2$/s at 21 K, two to three orders of magnitude higher than that of band-edge carriers. Remarkably, the photoexcited carriers travel up to 10 $\mu$m for hundreds of picoseconds at this high diffusivity. The diffusivity peaks in intrinsic devices and is reduced at high temperatures. We discuss the possible mechanisms of long-ranged super-diffusion in the frames of hot carriers and exciton condensation.

cond-mat.mes-hall↗

arXiv2024

WHALES: A Multi-Agent Scheduling Dataset for Enhanced Cooperation in Autonomous Driving

Cooperative perception research is hindered by the limited availability of datasets that capture the complexity of real-world Vehicle-to-Everything (V2X) interactions, particularly under dynamic communication constraints. To address this gap, we introduce WHALES (Wireless enhanced Autonomous vehicles with Large number of Engaged agents), the first large-scale V2X dataset explicitly designed to benchmark communication-aware agent scheduling and scalable cooperative perception. WHALES introduces a new benchmark that enables state-of-the-art (SOTA) research in communication-aware cooperative perception, featuring an average of 8.4 cooperative agents per scene and 2.01 million annotated 3D objects across diverse traffic scenarios. It incorporates detailed communication metadata to emulate real-world communication bottlenecks, enabling rigorous evaluation of scheduling strategies. To further advance the field, we propose the Coverage-Aware Historical Scheduler (CAHS), a novel scheduling baseline that selects agents based on historical viewpoint coverage, improving perception performance over existing SOTA methods. WHALES bridges the gap between simulated and real-world V2X challenges, providing a robust framework for exploring perception-scheduling co-design, cross-data generalization, and scalability limits. The WHALES dataset and code are available at https://github.com/chensiweiTHU/WHALES.

cs.CV↗

arXiv2024

Clustering Computer Mouse Tracking Data with Informed Hierarchical Shrinkage Partition Priors

Mouse-tracking data, which record computer mouse trajectories while participants perform an experimental task, provide valuable insights into subjects' underlying cognitive processes. Neuroscientists are interested in clustering the subjects' responses during computer mouse-tracking tasks to reveal patterns of individual decision-making behaviors and identify population subgroups with similar neurobehavioral responses. These data can be combined with neuro-imaging data to provide additional information for personalized interventions. In this article, we develop a novel hierarchical shrinkage partition (HSP) prior for clustering summary statistics derived from the trajectories of mouse-tracking data. The HSP model defines a subjects' cluster as a set of subjects that gives rise to more similar (rather than identical) nested partitions of the conditions. The proposed model can incorporate prior information about the partitioning of either subjects or conditions to facilitate clustering, and it allows for deviations of the nested partitions within each subject group. These features distinguish the HSP model from other bi-clustering methods that typically create identical nested partitions of conditions within a subject group. Furthermore, it differs from existing nested clustering methods, which define clusters based on common parameters in the sampling model and identify subject groups by different distributions. We illustrate the unique features of the HSP model on a mouse tracking dataset from a pilot study and in simulation studies. Our results show the ability and effectiveness of the proposed exploratory framework in clustering and revealing possible different behavioral patterns across subject groups.

stat.ME↗

arXiv2024

Electrically Switchable Circular Photogalvanic Effect in Methylammonium Lead Iodide Microcrystals

We investigate the circular photogalvanic effect (CPGE) in single-crystalline methylammonium lead iodide microcrystals under a static electric field. The external electric field can enhance the magnitude of the helicity dependent photocurrent (HDPC) by two orders of magnitude and flip its sign, which we attribute to magnetic shift currents induced by the Rashba-Edelstein effect. This HDPC induced by the static electric field may be viewed as an unusually strong third-order photoresponse, which produces a current two orders of magnitude larger than second-order injection current. Furthermore, the HDPC is highly nonlocal and can be created by photoexcitation out of the device channel, indicating a spin diffusion length up to 50 $μ$m at 78 K.

cond-mat.mes-hall↗

arXiv2023

TextDiff: Mask-Guided Residual Diffusion Models for Scene Text Image Super-Resolution

The goal of scene text image super-resolution is to reconstruct high-resolution text-line images from unrecognizable low-resolution inputs. The existing methods relying on the optimization of pixel-level loss tend to yield text edges that exhibit a notable degree of blurring, thereby exerting a substantial impact on both the readability and recognizability of the text. To address these issues, we propose TextDiff, the first diffusion-based framework tailored for scene text image super-resolution. It contains two modules: the Text Enhancement Module (TEM) and the Mask-Guided Residual Diffusion Module (MRD). The TEM generates an initial deblurred text image and a mask that encodes the spatial location of the text. The MRD is responsible for effectively sharpening the text edge by modeling the residuals between the ground-truth images and the initial deblurred images. Extensive experiments demonstrate that our TextDiff achieves state-of-the-art (SOTA) performance on public benchmark datasets and can improve the readability of scene text images. Moreover, our proposed MRD module is plug-and-play that effectively sharpens the text edges produced by SOTA methods. This enhancement not only improves the readability and recognizability of the results generated by SOTA methods but also does not require any additional joint training. Available Codes:https://github.com/Lenubolim/TextDiff.

cs.CV↗

arXiv2022

Surface Effects on Anisotropic Photoluminescence in One-Dimensional Organic Metal Halide Hybrids

One-dimensional (1D) organic metal halide hybrids exhibit strongly anisotropic optical properties, highly efficient light emission, and large Stokes shift, holding promises for novel photodetection and lighting applications. However, the fundamental mechanisms governing their unique optical properties and in particular the impacts of surface effects are not understood. Here, we investigate 1D C4N2H14PbBr4 by polarization-dependent time-averaged and time-resolved photoluminescence (TRPL) spectroscopy, as a function of photoexcitation energy. Surprisingly, we find that the emission under photoexcitation polarized parallel to the 1D metal halide chains can be either stronger or weaker than that under perpendicular polarization, depending on the excitation energy. We attribute the excitation-energy-dependent anisotropic emission to fast surface recombination, supported by first-principles calculations of optical absorption in this material. The fast surface recombination is directly confirmed by TRPL measurements, when the excitation is polarized parallel to the chains. Our comprehensive studies provide a more complete picture for a deeper understanding of the optical anisotropy in 1D organic metal halide hybrids.

cond-mat.mtrl-sci↗