arXiv subjects

Xiangyu Guo

Publications and source records attributed to Xiangyu Guo.

At least 19 recordsLinked to original sources

arXiv2026

A compact low-frequency optomechanical triaxial inertial sensor

Triaxial optomechanical accelerometers offer compact, ground-testable alternatives to electrostatic sensors for satellite geodesy, seismometry, and various other applications. We demonstrate a low-CSWaP triaxial sensor using monolithic fused-silica resonators with dual heterodyne interferometric readout. The X axis reaches a 60~pico-g/$\sqrt{\mathrm{Hz}}$ readout noise floor, and the in-plane axes resolve ambient seismic ground motion in agreement with a co-located commercial seismometer from 4~mHz to 8~Hz. The Z axis exhibits higher noise under $1g$ loading due to gravity-induced geometric stiffening (44.45~Hz versus 11.07~Hz in a 0g-equivalent configuration), with measurements indicating in-orbit performance on par with the in-plane sensors. These results support the feasibility of triaxial optomechanical accelerometry for space missions and ground-based applications.

physics.optics↗

arXiv2026

UnsDrive: Towards Robust End-to-End Autonomous Driving in Unstructured Scenes

End-to-end planning has shown strong promise for autonomous driving, but most existing methods are designed for structured urban roads and generalize poorly to unstructured mining environments. In such settings, weak road structure, terrain-induced occlusions, degraded visibility, and large unobserved regions make safe planning particularly challenging. To address these challenges, we propose UnsDrive, an end-to-end planner designed for unstructured mining scenes. UnsDrive builds an unknown-aware occupancy representation that explicitly models occupied, free, and unknown space using multi-frame visibility cues, and conditions a flow-matching planner on this representation to generate multimodal future trajectories. To improve safety under partial observability, we further introduce an occupancy trajectory consistency loss and an uncertainty-aware trajectory scorer that penalize trajectories entering non-traversable or unobserved regions. We also present MineLoop, a mining-oriented closed-loop simulator for evaluating autonomous driving under irregular road geometry, degraded visibility, heavy-vehicle interactions, and mining-specific operational constraints. Experiments in both open-loop and closed-loop settings show that UnsDrive consistently outperforms strong baselines in trajectory accuracy, collision avoidance, and long-horizon driving robustness. These results demonstrate the value of explicit unknown-space reasoning for autonomous driving in unstructured mining environments.

cs.RO↗

arXiv2026

CaVE: A Constraint Storage Approach to Handling Integrity Constraints

This paper presents Constraints as Verifiers and Emitters (CaVE), a constraint storage approach for handling integrity constraints in stableKanren. stableKanren is a normal logic-program solver based on extended unification and resolution. Integrity constraints control the outcomes of goals in normal logic programs, which is critical for non-monotonic reasoning. There is no resolution-based algorithm for handling integrity constraints that can be used in stableKanren. Therefore, we design Constraints as Verifiers and Emitters (CaVE), a constraint storage that works with resolution to support integrity constraints. We discuss variants of CaVE with respect to the integrity constraints, ranging from propositional to grounded and predicate versions. We implement CaVE using Scheme in stableKanren and show a series of example normal programs written in stableKanren with integrity constraints.

cs.PL↗

arXiv2026

HintMR: Eliciting Stronger Mathematical Reasoning in Small Language Models

Small language models (SLMs) often struggle with complex mathematical reasoning due to limited capacity to maintain long chains of intermediate steps and to recover from early errors. We address this challenge by introducing a hint-assisted reasoning framework that incrementally guides SLMs through multi-step mathematical problem solving. Our approach decomposes solutions into sequential reasoning steps and provides context-aware hints, where hints are generated by a separate SLM trained via distillation from a strong large language model. While the hint-generating SLM alone is not capable of solving the problems, its collaboration with a reasoning SLM enables effective guidance, forming a cooperative two-model system for reasoning. Each hint is generated conditionally on the problem statement and the accumulated reasoning history, providing stepwise, localized guidance without revealing full solutions. This reduces error propagation and allows the reasoning model to focus on manageable subproblems. Experiments across diverse mathematical benchmarks and models demonstrate that hint assistance consistently improves reasoning accuracy for SLMs, yielding substantial gains over standard prompting while preserving model efficiency. These results highlight that structured collaboration between SLMs-via hint generation and reasoning-offers an effective and lightweight mechanism for enhancing mathematical reasoning.

cs.AI↗

arXiv2025

Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks

Recent advancements in driving world models enable controllable generation of high-quality RGB videos or multimodal videos. Existing methods primarily focus on metrics related to generation quality and controllability. However, they often overlook the evaluation of downstream perception tasks, which are $\mathbf{really\ crucial}$ for the performance of autonomous driving. Existing methods usually leverage a training strategy that first pretrains on synthetic data and finetunes on real data, resulting in twice the epochs compared to the baseline (real data only). When we double the epochs in the baseline, the benefit of synthetic data becomes negligible. To thoroughly demonstrate the benefit of synthetic data, we introduce Dream4Drive, a novel synthetic data generation framework designed for enhancing the downstream perception tasks. Dream4Drive first decomposes the input video into several 3D-aware guidance maps and subsequently renders the 3D assets onto these guidance maps. Finally, the driving world model is fine-tuned to produce the edited, multi-view photorealistic videos, which can be used to train the downstream perception models. Dream4Drive enables unprecedented flexibility in generating multi-view corner cases at scale, significantly boosting corner case perception in autonomous driving. To facilitate future research, we also contribute a large-scale 3D asset dataset named DriveObj3D, covering the typical categories in driving scenarios and enabling diverse 3D-aware video editing. We conduct comprehensive experiments to show that Dream4Drive can effectively boost the performance of downstream perception models under various training epochs. Page: https://wm-research.github.io/Dream4Drive/ GitHub Link: https://github.com/wm-research/Dream4Drive

cs.CV↗

arXiv2025

Encoding Numeric Computations and Infusing Heuristic Knowledge Using Integrity Constraints in stableKanren

This paper presents examples of using integrity constraints in stableKanren to encode numeric computations for problem solving. Then, we use one of the examples to introduce multiple ways to infuse heuristic knowledge and reduce solving time. stableKanren is an extension of miniKanren that supports normal logic programs under stable model semantics. stableKanren further supports numeric computation by constructing a constraint store for integrity constraints. There are three ways to extend a relational programming language with numeric computations: relational number representation, grounding numbers to symbols, and constraint store construction. We demonstrate that the numeric computations in stableKanren have a straightforward numerical representation compared to relational number representations. More importantly, stableKanren balances symbolic and numeric computation in relational programming by avoiding the grounding of all numbers to symbols. Lastly, it also has simpler syntax compared to other constraint store construction approaches. stableKanren supports combinatorial search problem solving under a declarative generate and test paradigm. Such a paradigm generates all possible combinations of solutions to the problem, then applies a set of constraints to prune out the unwanted solutions. We demonstrate that different approaches to writing programs or queries affect the solver's performance in the SEND+MORE=MONEY puzzle. The performance gradually improves as more heuristic knowledge is infused through the programs or queries. Additionally, we show how to use an external function to achieve a hybrid solution.

cs.PL↗

arXiv2025

Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency

We present Genesis, a unified framework for joint generation of multi-view driving videos and LiDAR sequences with spatio-temporal and cross-modal consistency. Genesis employs a two-stage architecture that integrates a DiT-based video diffusion model with 3D-VAE encoding, and a BEV-aware LiDAR generator with NeRF-based rendering and adaptive sampling. Both modalities are directly coupled through a shared latent space, enabling coherent evolution across visual and geometric domains. To guide the generation with structured semantics, we introduce DataCrafter, a captioning module built on vision-language models that provides scene-level and instance-level supervision. Extensive experiments on the nuScenes benchmark demonstrate that Genesis achieves state-of-the-art performance across video and LiDAR metrics (FVD 16.95, FID 4.24, Chamfer 0.611), and benefits downstream tasks including segmentation and 3D detection, validating the semantic fidelity and practical utility of the generated data.

cs.CV↗

arXiv2025

ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving

Recent studies have explored leveraging the world knowledge and cognitive capabilities of Vision-Language Models (VLMs) to address the long-tail problem in end-to-end autonomous driving. However, existing methods typically formulate trajectory planning as a language modeling task, where physical actions are output in the language space, potentially leading to issues such as format-violating outputs, infeasible actions, and slow inference speeds. In this paper, we propose ReCogDrive, a novel Reinforced Cognitive framework for end-to-end autonomous Driving, unifying driving understanding and planning by integrating an autoregressive model with a diffusion planner. First, to instill human driving cognition into the VLM, we introduce a hierarchical data pipeline that mimics the sequential cognitive process of human drivers through three stages: generation, refinement, and quality control. Building on this cognitive foundation, we then address the language-action mismatch by injecting the VLM's learned driving priors into a diffusion planner to efficiently generate continuous and stable trajectories. Furthermore, to enhance driving safety and reduce collisions, we introduce a Diffusion Group Relative Policy Optimization (DiffGRPO) stage, reinforcing the planner for enhanced safety and comfort. Extensive experiments on the NAVSIM and Bench2Drive benchmarks demonstrate that ReCogDrive achieves state-of-the-art performance. Additionally, qualitative results across diverse driving scenarios and DriveBench highlight the model's scene comprehension. All code, model weights, and datasets will be made publicly available to facilitate subsequent research.

cs.CV↗

arXiv2025

MARAGE: Transferable Multi-Model Adversarial Attack for Retrieval-Augmented Generation Data Extraction

Retrieval-Augmented Generation (RAG) offers a solution to mitigate hallucinations in Large Language Models (LLMs) by grounding their outputs to knowledge retrieved from external sources. The use of private resources and data in constructing these external data stores can expose them to risks of extraction attacks, in which attackers attempt to steal data from these private databases. Existing RAG extraction attacks often rely on manually crafted prompts, which limit their effectiveness. In this paper, we introduce a framework called MARAGE for optimizing an adversarial string that, when appended to user queries submitted to a target RAG system, causes outputs containing the retrieved RAG data verbatim. MARAGE leverages a continuous optimization scheme that integrates gradients from multiple models with different architectures simultaneously to enhance the transferability of the optimized string to unseen models. Additionally, we propose a strategy that emphasizes the initial tokens in the target RAG data, further improving the attack's generalizability. Evaluations show that MARAGE consistently outperforms both manual and optimization-based baselines across multiple LLMs and RAG datasets, while maintaining robust transferability to previously unseen models. Moreover, we conduct probing tasks to shed light on the reasons why MARAGE is more effective compared to the baselines and to analyze the impact of our approach on the model's internal state.

cs.CL↗

arXiv2024

Improving stableKanren's Backward Compatibility

We improve the backward compatibility of stableKanren to run miniKanren programs. stableKanren is a miniKanren extension capable of non-monotonic reasoning through stable model semantics. However, standard miniKanren programs that produce infinite results do not run as expected in stableKanren. According to stable model semantics, the contradictions are created by negations. A standard miniKanren's relations do not involve negation, and the coarse contradictions handling in stableKanren causes this compatibility issue. Therefore, we provide a find-grinded contradiction handling to restrict the checking scope. As a result, standard miniKanren relations can produce answers. We also add a ``run-partial'' interface so that standard miniKanren's relations implemented with ``define''/``defineo'' can generate answers even if they coexist with non-terminating or unsatisfiable stableKanren relations in the same environment. The ``run-partial'' interface also supports running stratified negation programs faster without checking global unavoidable contradictions. A dependency graph analysis can be applied to the input query in the future, so the ``run'' interface can implicitly decide whether to perform unavoidable contradictions checking to improve usability.

cs.PL↗

arXiv2024

To Be or Not To Be: Adding Integrity Constraints to stableKanren to Make a Decision

We integrate integrity constraints to stableKanren to enable a new problem-solving paradigm in combinatorial search problems. stableKanren extends miniKanren to reasoning about contradictions under stable model semantics. However, writing programs to solve combinatorial search problems in stableKanren did not fully utilize the contradiction reasoning. This is mainly due to the lack of control over the predicate (goal function) outcome during resolution. Integrity constraints defined by answer set programming (ASP) provide the ability to constrain the predicate outcome. However, integrity constraints are headless normal clauses, and stableKanren cannot create a goal function without a valid head. There are two approaches to handling integrity constraints, but they do not fit stableKanren. Therefore, we design a new approach to integrate integrity constraints into stableKanren. We show a uniform framework to solve combinatorial search problems using integrity constraints in extended stableKanren.

cs.PL↗

arXiv2024

ANVIL: Anomaly-based Vulnerability Identification without Labelled Training Data

Supervised-learning-based vulnerability detectors often fall short due to limited labelled training data. In contrast, Large Language Models (LLMs) are trained on vast unlabelled code corpora, yet perform only marginally better than coin flips when directly prompted to detect vulnerabilities. In this paper, we reframe vulnerability detection as anomaly detection, based on the premise that vulnerable code is rare and thus anomalous relative to patterns learned by LLMs. We introduce ANVIL, which performs a masked code reconstruction task: The LLM reconstructs a masked line of code, and deviations from the original are scored as anomalies. We propose a hybrid anomaly score that combines exact match, cross-entropy loss, prediction confidence, and structural complexity. We evaluate our approach across multiple LLM families, scoring methods, and context sizes, and against vulnerabilities after the LLM's training cut-off. On the PrimeVul dataset, ANVIL outperforms state-of-the-art supervised detectors - LineVul, LineVD, and LLMAO - achieving up to 2x higher Top-3 accuracy, 75% better Normalized MFR, and a significant improvement on ROC-AUC. Finally, by integrating ANVIL with fuzzers, we uncover two previously unknown vulnerabilities, demonstrating the practical utility of anomaly-guided detection.

cs.CR↗

arXiv2023

STGIC: a graph and image convolution-based method for spatial transcriptomic clustering

Spatial transcriptomic (ST) clustering employs spatial and transcription information to group spots spatially coherent and transcriptionally similar together into the same spatial domain. Graph convolution network (GCN) and graph attention network (GAT), fed with spatial coordinates derived adjacency and transcription profile derived feature matrix are often used to solve the problem. Our proposed method STGIC (spatial transcriptomic clustering with graph and image convolution) utilizes an adaptive graph convolution (AGC) to get high quality pseudo-labels and then resorts to dilated convolution framework (DCF) for virtual image converted from gene expression information and spatial coordinates of spots. The dilation rates and kernel sizes are set appropriately and updating of weight values in the kernels is made to be subject to the spatial distance from the position of corresponding elements to kernel centers so that feature extraction of each spot is better guided by spatial distance to neighbor spots. Self-supervision realized by KL-divergence, spatial continuity loss and cross entropy calculated among spots with high confidence pseudo-labels make up the training objective of DCF. STGIC attains state-of-the-art (SOTA) clustering performance on the benchmark dataset of human dorsolateral prefrontal cortex (DLPFC). Besides, it's capable of depicting fine structures of other tissues from other species as well as guiding the identification of marker genes. Also, STGIC is expandable to Stereo-seq data with high spatial resolution.

q-bio.QM↗

arXiv2022

A Hierarchical Grouping Algorithm for the Multi-Vehicle Dial-a-Ride Problem

Ride-sharing is an essential aspect of modern urban mobility. In this paper, we consider a classical problem in ride-sharing - the Multi-Vehicle Dial-a-Ride Problem (Multi-Vehicle DaRP). Given a fleet of vehicles with a fixed capacity stationed at various locations and a set of ride requests specified by origins and destinations, the goal is to serve all requests such that no vehicle is assigned more passengers than its capacity at any point along its trip. We propose an algorithm HRA, which is the first non-trivial approximation algorithm for the Multi-Vehicle DaRP. The main technical contribution is to reduce the Multi-Vehicle DaRP to a certain capacitated partitioning problem, which we solve using a novel hierarchical grouping algorithm. Experimental results show that the vehicle routes produced by our algorithm not only exhibit less total travel distance compared to state-of-the-art baselines, but also enjoy a small in-transit latency, which crucially relates to riders' traveling times. This suggests that HRA enhances rider experience while being energy-efficient.

cs.DS↗

arXiv2022

Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks

One major problem in black-box adversarial attacks is the high query complexity in the hard-label attack setting, where only the top-1 predicted label is available. In this paper, we propose a novel geometric-based approach called Tangent Attack (TA), which identifies an optimal tangent point of a virtual hemisphere located on the decision boundary to reduce the distortion of the attack. Assuming the decision boundary is locally flat, we theoretically prove that the minimum $\ell_2$ distortion can be obtained by reaching the decision boundary along the tangent line passing through such tangent point in each iteration. To improve the robustness of our method, we further propose a generalized method which replaces the hemisphere with a semi-ellipsoid to adapt to curved decision boundaries. Our approach is free of pre-training. Extensive experiments conducted on the ImageNet and CIFAR-10 datasets demonstrate that our approach can consume only a small number of queries to achieve the low-magnitude distortion. The implementation source code is released online at https://github.com/machanic/TangentAttack.

cs.CV↗

arXiv2021

Online Food Delivery to Minimize Maximum Flow Time

We study a common delivery problem encountered in nowadays online food-ordering platforms: Customers order dishes online, and the restaurant delivers the food after receiving the order. Specifically, we study a problem where $k$ vehicles of capacity $c$ are serving a set of requests ordering food from one restaurant. After a request arrives, it can be served by a vehicle moving from the restaurant to its delivery location. We are interested in serving all requests while minimizing the maximum flow-time, i.e., the maximum time length a customer waits to receive his/her food after submitting the order. We show that the problem is hard in both offline and online settings: There is a hardness of approximation of $Ω(n)$ for the offline problem, and a lower bound of $Ω(n)$ on the competitive ratio of any online algorithm, where $n$ is number of points in the metric. Our main result is an $O(1)$-competitive online algorithm for the uncapaciated (i.e, $c = \infty$) food delivery problem on tree metrics. Then we consider the speed-augmentation model. We develop an exponential time $(1+ε)$-speeding $O(1/ε)$-competitive algorithm for any $ε> 0$. A polynomial time algorithm can be obtained with a speeding factor of $α_{TSP}+ ε$ or $α_{CVRP}+ ε$, depending on whether the problem is uncapacitated. Here $α_{TSP}$ and $α_{CVRP}$ are the best approximation factors for the traveling salesman (TSP) and capacitated vehicle routing (CVRP) problems respectively. We complement the results with some negative ones.

cs.DS↗

arXiv2021

The SPIIR online coherent pipeline to search for gravitational waves from compact binary coalescences

This paper presents the SPIIR pipeline used for public alerts during the third advanced LIGO and Virgo observation run (O3 run). The SPIIR pipeline uses infinite impulse response (IIR) filters to perform extremely low-latency matched filtering and this process is further accelerated with graphics processing units (GPUs). It is the first online pipeline to select candidates from multiple detectors using a coherent statistic based on the maximum network likelihood ratio statistic principle. Here we simplify the derivation of this statistic using the singular-value-decomposition (SVD) technique and show that single-detector signal-to-noise ratios from matched filtering can be directly used to construct the statistic for each sky direction. Coherent searches are in general more computationally challenging than coincidence searches due to extra search over sky direction parameters. The search over sky directions follows an embarrassing parallelization paradigm and has been accelerated using GPUs. The detection performance is reported using a segment of public data from LIGO-Virgo's second observation run. We demonstrate that the median latency of the SPIIR pipeline is less than 9 seconds, and present an achievable roadmap to reduce the latency to less than 5 seconds. During the O3 online run, SPIIR registered triggers associated with 38 of the 56 non-retracted public alerts. The extreme low-latency nature makes it a competitive choice for joint time-domain observations, and offers the tantalizing possibility of making public alerts prior to the merger phase of binary coalescence systems involving at least one neutron star.

gr-qc↗

arXiv2020

Estimating Stochastic Linear Combination of Non-linear Regressions Efficiently and Scalably

Recently, many machine learning and statistical models such as non-linear regressions, the Single Index, Multi-index, Varying Coefficient Index Models and Two-layer Neural Networks can be reduced to or be seen as a special case of a new model which is called the \textit{Stochastic Linear Combination of Non-linear Regressions} model. However, due to the high non-convexity of the problem, there is no previous work study how to estimate the model. In this paper, we provide the first study on how to estimate the model efficiently and scalably. Specifically, we first show that with some mild assumptions, if the variate vector $x$ is multivariate Gaussian, then there is an algorithm whose output vectors have $\ell_2$-norm estimation errors of $O(\sqrt{\frac{p}{n}})$ with high probability, where $p$ is the dimension of $x$ and $n$ is the number of samples. The key idea of the proof is based on an observation motived by the Stein's lemma. Then we extend our result to the case where $x$ is bounded and sub-Gaussian using the zero-bias transformation, which could be seen as a generalization of the classic Stein's lemma. We also show that with some additional assumptions there is an algorithm whose output vectors have $\ell_\infty$-norm estimation errors of $O(\frac{1}{\sqrt{p}}+\sqrt{\frac{p}{n}})$ with high probability. We also provide a concrete example to show that there exists some link function which satisfies the previous assumptions. Finally, for both Gaussian and sub-Gaussian cases we propose a faster sub-sampling based algorithm and show that when the sub-sample sizes are large enough then the estimation errors will not be sacrificed by too much. Experiments for both cases support our theoretical results. To the best of our knowledge, this is the first work that studies and provides theoretical guarantees for the stochastic linear combination of non-linear regressions model.

cs.LG↗