arXiv subjects

Shuyang Zhang

Publications and source records attributed to Shuyang Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Deep Uncertainty-aware Tracking for Maneuvering Targets

Traditional target tracking approaches typically presuppose a target motion model. Once the target maneuvers, the model may get mismatched and is incapable of depicting the complex motion characteristics of the target. Most data-driven methods are designed based on a regression-only framework, which increases the difficulty of network training. Moreover, these methods are typically designed under the assumption of a fixed measurement noise distribution. However, the measurement noise distribution of actual radar is influenced by fluctuations in the target's radar cross section. Such fluctuations may lead to a degradation in tracking performance. In this paper, we propose a representation method for radar measurements, referred to as the measurement uncertainty projection operator (MUPO). It projects the measurement onto a target state space to capture the measurement noise distribution. Additionally, we propose a framework that reformulates maneuvering target tracking as a hybrid task of classification and regression. To realize the functionality of this framework, we establish a MUPO-based target tracking network. The rationality of the proposed network structure is supported by the validation experiment. Numerical results demonstrate that the proposed method achieves superior estimation precision compared with existing data-driven methods during target maneuvers. Furthermore, the proposed algorithm retains its superior tracking performance when extended to 3D maneuvering target tracking and multi-target tracking scenarios.

eess.SP↗

arXiv2026

Scaling Model-Generated Distillation Data Can Make Latent Teacher Traits More Recoverable

Scaling model-generated data is usually viewed as improving distillation: more examples should increase coverage, reduce noise, and produce stronger students. We show a second effect: larger datasets can make subtle teacher-specific signals easier to detect in the trained student, even when examples are off-task and never mention the trait. In a controlled setup inspired by subliminal learning, a teacher induced to express a target trait generates restricted off-task data, such as number-only completions. Students trained on different amounts of independent off-task data are evaluated in a separate domain, with matched no-trait controls isolating target-specific transfer. Our main finding is that larger independent datasets make the teacher's induced trait stand out more clearly in the student's later behavior. Other plausible traits may also strengthen with scale, but the target usually grows more. When the small-scale student already favors the target, scaling mainly amplifies that behavior; when it favors a related or salient alternative, more data can shift behavior toward the intended trait. Analyses of learned LoRA updates show a parallel trend. These effects appear across model families, trait types, multi-trait settings, and cross-model transfer. Our results suggest that scaling generated distillation data should be paired with trait-aware curation and evaluation, even when the data appears off-task or benign.

cs.LG↗

arXiv2026

Certified Learning and Equilibrium Implementation under Opaque Partial Commitment

As an extension of existing Bayesian persuasion framework with inadequate message mechanism, we study direct recommendation when a sender is bound by an installed information policy only with probability $ρ$, the realization of binding is hidden, and the receiver does not observe the persistent structural environment. The receiver first sees a payoff-neutral, nonmanipulable calibration sample and then faces a fresh, non-certified deployment interaction. In common, the calibration law identifies only the receiver-facing reduced form, not the latent binding and discretionary kernels. We characterize type-wise $ρ$-implementability, construct the receiver's posterior over the full deployment node, and prove a static direct-following implementation theorem. After every calibration history that passes a posterior-predictive obedience test, the deployment assessment is an exact perfect Bayesian equilibrium: Bayes consistency, receiver sequential rationality, sender sequential rationality, and off-path completion are all verified. Under finite-type separation, common recommendation support, and a positive obedience margin, the test activates such an equilibrium with high probability. Our results keep statistical failure probability distinct from equilibrium approximation. Finally, we embed the original robust value frontier, support-wise linear-programming algorithm, and binary-action fractional-knapsack specialization into this implementation framework

cs.GT↗

arXiv2026

Mitigating ray effects in rarefied flow simulations using an ensemble-of-subproblems strategy with stochastic discrete velocities

In this work, a ensemble-of-subproblems strategy with stochastic discrete velocities is extended to deterministic methods for mitigating ray effects in rarefied flow simulations. The strategy involves performing multiple independent subproblems, each using a small set of randomly sampled velocity points, and then averaging their solutions to obtain the final result. The core idea is to ensure that the distribution function at any velocity can contribute to the final result, approximating highly refined velocity-space resolution without increasing the memory requirement in any single subproblem. We incorporate this strategy within the DUGKS framework, and the resulting method is denoted as SDV-DUGKS. To evaluate the performance of the proposed method, we compare SDV-DUGKS with the original DUGKS on several test cases: (a) the Sod shock tube problem, (b) the one-dimensional Riemann problem, (c) the two-dimensional lid-driven cavity flow, and (d) the two-dimensional Riemann problem. The results show that, in the collisionless limit $\mathrm{Kn} \to \infty$: (1) for one-dimensional compressible flows, SDV-DUGKS reduces memory usage by approximately 2/3 compared with that of the original DUGKS while achieving good agreement; (2) for two-dimensional compressible flows, SDV-DUGKS requires one to two orders of magnitude less memory than the original DUGKS while achieving good agreement. Based on these results, it can be concluded that the proposed method serves as a reliable and effective tool for mitigating ray effects in rarefied flow simulations.

physics.comp-ph↗

arXiv2026

A memory-efficient deterministic method for multiscale gas flows using an ensemble-of-subproblems strategy with stochastic discrete velocities

Deterministic multiscale gas flow simulations have long suffered from the curse of dimensionality: the number of discrete velocities increases dramatically with the velocity space dimension and the Mach number, exhausting available memory and computational resources. To address this issue, this paper proposes a memory-efficient deterministic method based on an ensemble-of-subproblems strategy using stochastic discrete velocities. This strategy transforms the originally computationally expensive problem into a series of independently and efficiently solvable subproblems. To be concrete, the proposed method replaces the conventional large deterministic velocity set with multiple small random velocity sets. Each random set defines a subproblem, which is solved by a deterministic multiscale numerical scheme that computes macroscopic moments via Monte Carlo integration. The final flow field is obtained by arithmetic averaging over all sub-problems. In this work, we employ the discrete unified gas kinetic scheme (DUGKS) for spatial discretization and term the resulting method SDV-DUGKS. To validate the proposed method, several numerical test cases are conducted, including (a) the one-dimensional shock structure, (b) the two-dimensional cavity flow, and (c) supersonic flow around a square cylinder. The results of the one-dimensional shock structure confirm the feasibility of the proposed method. The two-dimensional cases demonstrate that, compared to its deterministic counterpart, the proposed method saves more than 80% of memory usage while maintaining comparable accuracy. These results indicate that the proposed method markedly reduces memory demand for multiscale flow simulations and exhibits strong potential to alleviate the curse of dimensionality that currently hinders deterministic multiscale numerical schemes from being applied to engineering problems.

physics.comp-ph↗

arXiv2026

A specialized reasoning large language model for accelerating rare disease diagnosis: a randomized AI physician assistance trial

Rare diseases affect millions of individuals worldwide, yet timely diagnosis remains a major public health challenge due to scarcity of specialized clinical expertise. While large language models (LLMs) show promise to support rare disease diagnosis, current models are constrained by insufficient clinical deployability, limited clinically grounded evidence, and scarcity of training data. Here we present RaDaR (Rare Disease navigatoR), an open-source, compact reasoning LLM (32B parameters) for rare disease diagnosis. RaDaR was trained with 49,170 publicly available free-text cases and 104,666 synthetic cases with reasoning-enhanced training. RaDaR showed the strongest performance among evaluated open-source models, including the 671B DeepSeek-R1, across public benchmarks and four external validation centers. In a retrospective cohort, RaDaR prioritized the final diagnosis before documented clinical suspicion in 61.06 percent of cases, corresponding to a potential lead time of 1.87 months and 50.18 percent of the within-center interval. In a randomized physician-assistance trial, RaDaR assistance improved physicians' rare-disease diagnostic accuracy by 21.44 percentage points compared with internet search alone. Synthetic-data ablations suggested that phenotype-anchored narratives provide useful training signal for long-tail rare diseases, with a monotonic scaling trend within the tested data range. Together, RaDaR and its development and validation framework provide a deployable rare-disease reasoning model and a reproducible development framework for diagnostic AI under data scarcity.

cs.AI↗

arXiv2025

HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance

Parameter-Efficient Fine-Tuning (PEFT), especially Low-Rank Adaptation (LoRA), has emerged as a promising approach to fine-tuning large language models(LLMs) while reducing computational and memory overhead. However, LoRA assumes a uniform rank \textit{r} for each incremental matrix, not accounting for the varying significance of weight matrices across different modules and layers. AdaLoRA leverages Singular Value Decomposition (SVD) to parameterize updates and employs pruning of singular values to introduce dynamic rank allocation, thereby enhancing adaptability. However, during the training process, it often encounters issues of slow convergence speed and high computational overhead. To address this issue, we propose HyperAdaLoRA, a novel framework that accelerates the convergence of AdaLoRA by leveraging a hypernetwork. Instead of directly optimizing the components of Singular Value Decomposition $(P, Λ, Q)$, HyperAdaLoRA employs a hypernetwork based on attention mechanisms to dynamically generate these parameters. By pruning the outputs of the hypernetwork that generates the singular values, dynamic rank allocation is achieved. Comprehensive experiments on various datasets and models demonstrate that our method achieves faster convergence without sacrificing performance. Additionally, further extension experiments on other LoRA-based approaches validate the broad applicability of our method.

cs.LG↗

arXiv2025

RareAgents: Autonomous Multi-disciplinary Team for Rare Disease Diagnosis and Treatment

Rare diseases, despite their low individual incidence, collectively impact around 300 million people worldwide due to the vast number of diseases. The involvement of multiple organs and systems, and the shortage of specialized doctors with relevant experience, make diagnosing and treating rare diseases more challenging than common diseases. Recently, agents powered by large language models (LLMs) have demonstrated notable applications across various domains. In the medical field, some agent methods have outperformed direct prompts in question-answering tasks from medical examinations. However, current agent frameworks are not well-adapted to real-world clinical scenarios, especially those involving the complex demands of rare diseases. To bridge this gap, we introduce RareAgents, the first LLM-driven multi-disciplinary team decision-support tool designed specifically for the complex clinical context of rare diseases. RareAgents integrates advanced Multidisciplinary Team (MDT) coordination, memory mechanisms, and medical tools utilization, leveraging Llama-3.1-8B/70B as the base model. Experimental results show that RareAgents outperforms state-of-the-art domain-specific models, GPT-4o, and current agent frameworks in diagnosis and treatment for rare diseases. Furthermore, we contribute a novel rare disease dataset, MIMIC-IV-Ext-Rare, to facilitate further research in this field.

cs.CL↗

arXiv2024

Efficient Camera Exposure Control for Visual Odometry via Deep Reinforcement Learning

The stability of visual odometry (VO) systems is undermined by degraded image quality, especially in environments with significant illumination changes. This study employs a deep reinforcement learning (DRL) framework to train agents for exposure control, aiming to enhance imaging performance in challenging conditions. A lightweight image simulator is developed to facilitate the training process, enabling the diversification of image exposure and sequence trajectory. This setup enables completely offline training, eliminating the need for direct interaction with camera hardware and the real environments. Different levels of reward functions are crafted to enhance the VO systems, equipping the DRL agents with varying intelligence. Extensive experiments have shown that our exposure control agents achieve superior efficiency-with an average inference duration of 1.58 ms per frame on a CPU-and respond more quickly than traditional feedback control schemes. By choosing an appropriate reward function, agents acquire an intelligent understanding of motion trends and anticipate future illumination changes. This predictive capability allows VO systems to deliver more stable and precise odometry results. The codes and datasets are available at https://github.com/ShuyangUni/drl_exposure_ctrl.

cs.RO↗

arXiv2024

Identifying Bridges from Asymmetric Load-Bearing Structures in Tapped Granular Packings

Using high-resolution x-ray tomography, we experimentally investigate the bridge structures in tapped granular packings composed of particles with varying friction coefficients. We find that gravity can induce subtle structural changes on the load-bearing contacts, allowing us to identify the correct load-bearing contacts based on structural information alone. Using these identified load-bearing contacts, we investigate the cooperative bridge structures which are mechanical backbones of the system. We characterize the geometric properties of these bridges and find that their cooperativity increases as the packing fraction decreases. The knowledge of bridges can enhance our understanding of the rheological properties of granular materials.

cond-mat.soft↗

arXiv2024

Testing Adam-Gibbs relationship in tapped Granular Packings

Disordered granular packings share many similarities with supercooled liquids, particu-larly in the rapid increase of structural relaxation time within a narrow range of temperature or packing fraction. However, it is unclear whether the dynamics of granular materials align with those of their corresponding thermal hard sphere liquids, and the particular influence of friction of a granular system remains largely unexplored. Here, we experimentally study the slow relaxation and the steady state of monodisperse granular sphere packings with X-ray tomography. We first quantify the thermodynamic parameters under the Edwards' ensemble, (i.e., effective temperature and configurational entropy), of granular spheres with varying friction, and measure their characteristic relaxation time during compaction processes. We then demonstrate a unified picture of the relaxation process in granular systems in which the Adam-Gibbs (AG) relationship is generally followed. These results clarify the close relation-ship between granular materials and the ideal frictionless hard sphere model.

cond-mat.soft↗

arXiv2024

Microscopic Structural Study on the Growth History of Granular Heaps Prepared by the Raining Method

Granular heaps are critical in both industrial applications and natural processes, exhibiting complex behaviors that have sparked significant research interest. The stress dip phenomenon observed beneath granular heaps continues to be a topic of significant debate. Current models based on force transmission often assume that the packing is near the isostatic point, overlooking the critical influence of internal structure and formation history on the mechanical properties of granular heaps. Consequently, these models fail to fully account for diverse observations. In this study, we experimentally explore the structural evolution of three dimensional (3D) granular heaps composed of monodisperse spherical particles prepared using the raining method. Our results reveal the presence of two distinct regions within the heaps, characterized by significant differences in structural properties such as packing fraction, contact number, and contact anisotropy. We attribute these structural variations to the differing formation mechanisms during heap growth. Our findings emphasize the substantial influence of the preparation protocols on the internal structure of granular heaps and provide valuable insights into stress distribution within granular materials. This research may contribute to the development of more accurate constitutive relations for granular materials by informing and refining future modeling approaches

cond-mat.soft↗

arXiv2024

Edwards thermodynamic framework controls density segregation in cyclically sheared granular materials

Using X-ray tomography, we experimentally investigate granular segregation phenomena in a mixture of particles with different densities under quasi-static cyclic shear. We quantitatively characterize their height distributions at steady states by minimizing effective free energy based on a segregation temperature that captures the competition between the mixing entropy and gravitational potential energy. We find this temperature coincides with Edwards' compactivity within error under various pressures and cyclic shear amplitudes. Therefore, we find that granular segregation in quasi-static conditions can be fundamentally explained by an effective granular thermodynamic framework including real energy terms based on the Edwards statistical ensemble.

cond-mat.soft↗

arXiv2024

Accurate Prior-centric Monocular Positioning with Offline LiDAR Fusion

Unmanned vehicles usually rely on Global Positioning System (GPS) and Light Detection and Ranging (LiDAR) sensors to achieve high-precision localization results for navigation purpose. However, this combination with their associated costs and infrastructure demands, poses challenges for widespread adoption in mass-market applications. In this paper, we aim to use only a monocular camera to achieve comparable onboard localization performance by tracking deep-learning visual features on a LiDAR-enhanced visual prior map. Experiments show that the proposed algorithm can provide centimeter-level global positioning results with scale, which is effortlessly integrated and favorable for low-cost robot system deployment in real-world applications.

cs.RO↗

arXiv2024

RareBench: Can LLMs Serve as Rare Diseases Specialists?

Generalist Large Language Models (LLMs), such as GPT-4, have shown considerable promise in various domains, including medical diagnosis. Rare diseases, affecting approximately 300 million people worldwide, often have unsatisfactory clinical diagnosis rates primarily due to a lack of experienced physicians and the complexity of differentiating among many rare diseases. In this context, recent news such as "ChatGPT correctly diagnosed a 4-year-old's rare disease after 17 doctors failed" underscore LLMs' potential, yet underexplored, role in clinically diagnosing rare diseases. To bridge this research gap, we introduce RareBench, a pioneering benchmark designed to systematically evaluate the capabilities of LLMs on 4 critical dimensions within the realm of rare diseases. Meanwhile, we have compiled the largest open-source dataset on rare disease patients, establishing a benchmark for future studies in this domain. To facilitate differential diagnosis of rare diseases, we develop a dynamic few-shot prompt methodology, leveraging a comprehensive rare disease knowledge graph synthesized from multiple knowledge bases, significantly enhancing LLMs' diagnostic performance. Moreover, we present an exhaustive comparative study of GPT-4's diagnostic capabilities against those of specialist physicians. Our experimental findings underscore the promising potential of integrating LLMs into the clinical diagnostic process for rare diseases. This paves the way for exciting possibilities in future advancements in this field.

cs.CL↗

arXiv2024

Directed Acyclic Graph Structure Learning from Dynamic Graphs

Estimating the structure of directed acyclic graphs (DAGs) of features (variables) plays a vital role in revealing the latent data generation process and providing causal insights in various applications. Although there have been many studies on structure learning with various types of data, the structure learning on the dynamic graph has not been explored yet, and thus we study the learning problem of node feature generation mechanism on such ubiquitous dynamic graph data. In a dynamic graph, we propose to simultaneously estimate contemporaneous relationships and time-lagged interaction relationships between the node features. These two kinds of relationships form a DAG, which could effectively characterize the feature generation process in a concise way. To learn such a DAG, we cast the learning problem as a continuous score-based optimization problem, which consists of a differentiable score function to measure the validity of the learned DAGs and a smooth acyclicity constraint to ensure the acyclicity of the learned DAGs. These two components are translated into an unconstraint augmented Lagrangian objective which could be minimized by mature continuous optimization techniques. The resulting algorithm, named GraphNOTEARS, outperforms baselines on simulated data across a wide range of settings that may encounter in real-world applications. We also apply the proposed approach on two dynamic graphs constructed from the real-world Yelp dataset, demonstrating our method could learn the connections between node features, which conforms with the domain knowledge.

cs.LG↗

arXiv2024

CANAMRF: An Attention-Based Model for Multimodal Depression Detection

Multimodal depression detection is an important research topic that aims to predict human mental states using multimodal data. Previous methods treat different modalities equally and fuse each modality by naïve mathematical operations without measuring the relative importance between them, which cannot obtain well-performed multimodal representations for downstream depression tasks. In order to tackle the aforementioned concern, we present a Cross-modal Attention Network with Adaptive Multi-modal Recurrent Fusion (CANAMRF) for multimodal depression detection. CANAMRF is constructed by a multimodal feature extractor, an Adaptive Multimodal Recurrent Fusion module, and a Hybrid Attention Module. Through experimentation on two benchmark datasets, CANAMRF demonstrates state-of-the-art performance, underscoring the effectiveness of our proposed approach.

cs.CL↗

arXiv2023

Experimental Study of the Nematic Transition in Granular Spherocylinder Packings under Tapping

Using x-ray tomography, we experimentally investigate the nematic transition in granular spherocylinder packings induced by tapping. Upon the validation of the Edwards ensemble framework in spherocylinders, we introduce an empirical free energy that accounts for the influence of gravity and the mechanical stability requirements specific to granular systems. This free energy can predict not only the correct phase transition behavior of the system from a disordered state to a nematic phase, but also a phase coexistence range and nucleation energy barriers that agree with experimental observations.

cond-mat.soft↗