arXiv subjects

Yi Huang

Publications and source records attributed to Yi Huang.

At least 19 recordsLinked to original sources

arXiv2026

AI for Science in Space: Orbital Laboratories, Planetary Fieldwork, and Embodied Autonomy

Artificial intelligence for science (AI4S) is extending from interpretation of existing data to the design and execution of experiments. Space offers distinctive scientific opportunities while restricting physical support. Microgravity and extraterrestrial environments expose phenomena that terrestrial experiments cannot fully reproduce; finite samples, constrained resources, and limited opportunities for intervention complicate sustained investigation. This critical review examines orbital laboratories and planetary in situ science across biology, materials, fluid and thermal physics, and adaptive exploration. We distinguish learning from space-derived data, selecting scientific actions, executing them, and preserving experimental validity. Terrestrial self-driving laboratories provide complementary evidence on optimization, dedicated automation, robotic manipulation, and the support needed for unattended operation. The synthesis connects scientific gains already demonstrated by bounded AI systems to gaps in observation, executable actions, and continuity of valid evidence. Space robots can expand the attainable scope of autonomous science when necessary interventions exceed validated instrument capabilities and timely human support is unavailable. Their value must be established against dedicated mechanisms, redundancy, and human-supported operation. We develop a framework connecting sample history, scientific decisions, physical execution, and claim-specific validity. A worked orbital design, a planetary extension, and matched evaluation schemes separate the contributions of sensing, decision policies, and physical actions. The resulting agenda measures autonomy through valid scientific return, task coverage, intervention costs, and evidence integrity across complete campaigns.

cs.RO↗

arXiv2026

Learning a Prior-Data Fitted Network for Graph Foundation Models via Structural Causal Model Priors

Graph Foundation Models (GFMs) have recently emerged as a promising paradigm for learning transferable representations across different graphs and domains. However, existing GFMs face notable limitations, including limited pre-training scale or reliance on aligning with textual information in Large Language Models (LLMs). To overcome these limitations, recent studies have drawn inspiration from prior-data fitted networks (PFNs), which learn from large synthetic datasets and support multi-domain prediction backed by causal learning. However, existing graph PFNs encounter severe difficulties in modeling causal relationships within and across node and edge sets, generating diverse graph structures, and designing suitable architectures that can learn from complex synthetic datasets. To address these challenges, we propose **GSCM-PFN** (Graph SCM-based Prior-Data Fitted Network), a graph PFN pre-trained on synthetic data generated from an SCM-based prior that jointly models nodes and graph topology. Specifically, we (1) design a joint feature-edge-label structural causal model (SCM) to guide synthetic graph generation and capture causal relationships within and across node and edge sets; (2) introduce prior-guided node-edge dependency modeling to instantiate diverse graph generation strategies, and prove that our SCM-based generation prior is more expressive than existing priors; and (3) propose a feature-permutation-invariant dual-path graph network with theoretical guarantees for learning from diverse synthetic graphs. Experiments on 23 real-world benchmarks show that GSCM-PFN outperforms both conventional GFMs and PFN-based GFMs, without utilizing real-world graph data for pre-training. Code: https://anonymous.4open.science/r/GSCM-PFN-A3A3/

cs.LG↗

arXiv2026

Where Should the Evaluation Budget Go in LLM-Driven Agent Scaffold Evolution?

Large language model (LLM)-driven agent scaffold evolution improves agent workflows through iterative candidate generation and evaluation. Evaluation both guides subsequent search and determines the final scaffold, but evaluating every candidate on the full task set incurs substantial execution costs. We investigate how evaluation budgets can be allocated across these two roles. Our experiments show that sparse feedback can sustain productive evolution, while additional targeted evaluation improves final selection. Replay analyses further show that shared informative items and a common scoring reference support comparisons among closely matched candidates. Motivated by these findings, we propose \method, an evaluation allocation framework that combines sparse search-time feedback with targeted final confirmation. A short fully evaluated warm-up establishes a shared informative core and calibrates a response model whose item parameters remain fixed during search. After search, \method refits the model and applies paired successive halving, reusing accumulated observations and executing only missing evaluations. Across four benchmarks and two evolution frameworks, \method achieves higher mean performance than full evaluation in most settings while using approximately half as many evaluation cells.

cs.LG↗

arXiv2026

Track finding and particle identification performance with particle physics foundation models

Modern high energy nuclear and particle physics experiments produce large amounts of sparse data that must be reduced significantly in size before performing physics analysis. Recently, there has been an effort to evaluate Foundation Models as a potential tool for performing data analysis. These models have been shown to learn features in high dimensional datasets based on the multi-modal data they are trained on. To show their effectiveness at performing complex pattern recognition tasks, such as reconstructing charged particles in a magnetic field, we evaluated the performance of a Foundation Model based reconstruction on several downstream tasks with a dataset composed of spacepoints in a Time Projection Chamber. We show that the performance of the Foundation Model based data analysis significantly improves upon that of traditional methods, and furthermore can be adapted to learn additional tasks that are not necessarily related to the initial training objective.

physics.data-an↗

arXiv2026

AstroBench: Benchmarking Free-Floating Capture and Space Robotic Manipulation

Capturing a loose object inside a spacecraft requires a robot to approach a target that can translate and rotate, and whose motion changes when contact is made. These conditions motivate evaluation beyond manipulation of supported objects. We introduce AstroBench, an open benchmark for free-floating capture and space robotic manipulation with a fixed-base arm. The task suite combines four initial-motion tracks with sample-storage operations based on MELFI hardware and cap and captive-screw servicing based on the Robotic Refueling Mission. The two workcells provide nine task definitions and 29 task-target combinations. A metadata-filtered Objaverse inventory supplies 8,414 object instances for asset expansion, alongside five cabin visual contexts and versioned task instructions. We report two acquisition-focused experiments using existing checkpoints. A frozen $π_{0.5}$ DROID joint-position policy captures 2 of 200 static targets and 4 of 200 moving targets across twenty object identities. A cube-specific ACT policy captures 8 of 10 static targets and 6 of 10 moving targets in a separate experiment. Each experiment retains its recorded observation, action and capture configuration. The results document difficult direct transfer for the tested generalist checkpoint and successful task-specific capture behavior, while identifying concrete settings for studying motion-aware perception and contact-sensitive control. Code, task definitions and editable workcell assets are available at https://github.com/AstroUpLab/AstroBench.

cs.RO↗

arXiv2026

Compressing Onboard Language Models for Space Robots under a Behavioral-Fidelity Requirement

Language models are being explored as the interface through which space robots interpret operator commands and select among verified skills. Running them onboard calls for low-bit compression, and flight use adds requirements that generic post-training quantization leaves implicit: a fixed memory budget and storage format, a static artifact under configuration control, and behavior close to the full-precision model validated on the ground. We treat compression as a ground-segment step and study QSelect, which composes one static low-bit model from compatible AWQ, GPTQ, and AutoRound checkpoints by assigning each linear module to one quantizer family and scoring every substitution at the final next-token distribution. The default fidelity mode needs no labels or tuned thresholds and accepts a substitution only when the forward KL divergence from the BF16 reference decreases; an optional target-adapted mode adds answer likelihood on a small labeled set. On DeepSeek-R1-Distill-Qwen-7B, Llama-3.1-8B, and Llama-3.2-3B at 3 and 4 bits, composed models reach lower mean held-out perplexity than every single-family model in all six settings, and the fidelity mode lowers perplexity and KL further. In a matched scaffold, final-output scoring gives lower held-out KL than representation-similarity scoring in all 12 paired runs. With labels from training or development splits of the evaluated task families, the target-adapted mode raises 3-bit pooled accuracy on the two Llama models by 4.3 and 4.5 points over the best single-family model. At 3 bits, unquantized embedding and output layers make up 43-46% of the packed artifact. All evaluations use general-domain benchmarks on a ground GPU; space-domain tasks and flight hardware are left to future work.

cs.RO↗

arXiv2026

Foundation Models for Autonomous Space Robotics: Architectures, Physical Adaptation, and Validation

Space robots must interpret tasks and act despite unfamiliar dynamics, difficult sensing conditions, and limited opportunities for human intervention. Foundation models offer reusable perceptual and behavioral knowledge, but their value depends on how that knowledge reaches physical execution. This critical review follows space-specific requirements through perception, prediction, planning, and action to deployment and validation, emphasizing orbital manipulation and proximity operations. Terrestrial comparisons establish benefits of particular pretraining stages and model interfaces; their transfer to space dynamics and constrained onboard operation remains insufficiently tested. Event cameras offer timely motion observations across strong illumination contrasts, while spiking neural networks provide possible routes to sparse local computation. We examine how sensor degradation, state estimation and computing choices affect feedback and recovery. Higher action throughput need not yield fresher feedback; lower processor power can also coexist with higher energy per inference. We organize validation as an iterative sim-to-ground-to-space pathway, connecting physical tests with telemetry-based diagnosis and closed-loop revalidation. A satellite-capture example links observations to approach, contact and recovery, while a corresponding protocol separates generalization from adaptation with limited target-domain interaction. These comparisons identify what models already contribute and the physical evidence needed to support autonomous space operation.

cs.RO↗

arXiv2026

InstAgent: A Recursively Self-Improving Agent Operating System for Heterogeneous Robot Collaboration

Heterogeneous robot teams enable complex, long-horizon tasks by combining complementary sensing, mobility, and manipulation capabilities across multiple embodiments. Yet existing systems struggle to retain execution-time corrections as reusable experience, maintain task-relevant context memory across space and time for reliable handoffs, and explicitly represent the inter-robot dependencies required for structured collaboration. In order to address these challenges, we present InstAgent, a recursively self-improving (RSI) Agent Operating System for heterogeneous robot collaboration. InstAgent organizes team behaviors as agentic behavior trees (BTs) that explicitly model capability assignment, inter-robot dependencies and handoff checks. The RSI mechanism updates these collaboration programs from execution feedback and preserves successful revisions for reuse in future tasks, while shared multimodal spatio-temporal memory provides context for planning and handoff validation. Experiments on 20 real-world multi-robot tasks with three high-level models show consistent gains in task success, first-attempt completion, and execution efficiency.

cs.RO↗

arXiv2026

MobileJailBench: Red Queen Jailbreak Benchmarking for Mobile Agents

MLLM-based mobile agents are rapidly gaining autonomy in perception, planning, and closed-loop execution in dynamic mobile environments. However, this autonomy also broadens the attack surface and amplifies the risks of malicious misuse, including privacy leakage, device compromise, and large-scale phishing. Existing jailbreak evaluations leave three critical gaps for mobile agents: they focus on conversational attacks instead of mobile workflows, use static task sets with fixed difficulty, and rely narrowly on attack success rate rather than comprehensive security assessment. To close these gaps, we present MobileJailBench, the first evolving jailbreak benchmark for mobile agents, comprising three key components: (1) a benchmark comprising 520 tasks spanning three jailbreak paradigms and 14 risk categories, built on a high-fidelity mobile sandbox that we construct, enabling realistic workflows across over 20 widely used apps; (2) Dual-Dynamic Evolution, which combines Failure-Distilled Jailbreak Evolution with Weakness-Driven Benchmark Expansion; and (3) Stratified Adjudication Framework for assessing security awareness, execution behavior, and risk consequences. Extensive experiments show that current mobile agents are particularly vulnerable to implicit jailbreaks, as their safety alignment remains largely superficial and fails to generalize from conversational refusal to dynamic mobile interactions. Moreover, our dynamic evolution mechanism sharpens practical threat boundaries by continually uncovering new vulnerabilities, reaching a 100% ASR on Qwen3.5-122B. MobileJailBench provides a reproducible, continuously evolving framework for tracking the true security boundaries of mobile agents.

cs.CR↗

arXiv2026

MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection

Multimodal large language model (MLLM)-based mobile agents are rapidly evolving from conversational assistants into autonomous systems that perceive, reason over, and act on smartphone environments. This capability also exposes a new security risk: adversaries can embed malicious objectives in cross-application mobile content and steer agent behavior through indirect multimodal injection. Although prompt injection has been studied in desktop and web settings, its cross-modal properties in mobile ecosystems remain poorly understood, and existing security analyses are still limited. To close this gap, we introduce MobileInject, the first benchmark for evaluating mobile agents against multimodal injection attacks and reasoning-to-action security risks. MobileInject provides a high-fidelity interactive mobile evaluation framework covering 11 scenarios, 9 security-risk categories, and 108 executable risk instances. It further introduces Cross-Modal Consistency Injection to exploit corroboration across modalities, two enhanced attack methods, Multi-Role Collaborative Deception and Reasoning-Camouflage Injection, to intensify trust manipulation and reasoning hijacking, and a Reasoning Security Diagnosis Framework for fine-grained failure analysis. Systematic experiments show that mobile agents are broadly vulnerable to multimodal injection, and that many failures stem from reasoning hijacking at early stages. These findings establish MobileInject as a systematic cross-modal benchmark for studying and improving the security of mobile agents. Code release details are provided in the Appendix Open Science section.

cs.CR↗

arXiv2026

Dirac Points in High-Contrast Dielectric Honeycomb Structures

We study Dirac points for a two-dimensional scalar Helmholtz equation in a periodic dielectric medium with two penetrable inclusions per honeycomb cell. In a joint small-inclusion and high-contrast regime, we reduce the Bloch eigenvalue problem to a two-dimensional interaction matrix and derive a two-term asymptotic expansion for the two relevant eigenvalues, uniformly for quasi-momenta separated from the reciprocal lattice. At a vertex K of the Brillouin zone, rotation and inversion-conjugation symmetries force these eigenvalues to coincide. A Schur-complement analysis of the exact operator pencil, together with a nonvanishing lattice Green-function coefficient, proves that the resulting double eigenvalue has a nonzero conical splitting and gives an asymptotic formula for the conical slope in the scaled eigenvalue. For fixed sufficiently large contrast, symmetry-preserving changes of variables and analytic perturbation theory then continue this Dirac point as the inclusion size varies: it remains nondegenerate except at a relatively closed discrete set of admissible sizes.

math.AP↗

arXiv2026

LiFUSE: Frequency-Spatial Unified Self-Supervised Pretraining for Liver Disease Analysis on Non-contrast CT

Given the growing global burden of liver tumors and diffuse liver diseases, non-contrast computed tomography (NCCT) is increasingly used for opportunistic screening because of its low cost and favorable safety profile. However, downstream tasks such as tumor detection and fine-grained disease diagnosis remain challenging due to NCCT's inherently low tissue contrast, lack of hemodynamic enhancement, and complex anatomical background. These limitations make subtle, heterogeneous, and multifocal hepatic lesions difficult to identify. Although large-scale self-supervised pretraining can learn robust representations from unlabeled NCCT scans, conventional voxel-wise reconstruction does not fully exploit the complementary information available in NCCT. Under weak NCCT contrast, low-level intensity patterns become less informative for pathology recognition, limiting the capture of lesion-specific discriminative features. In this paper, we propose the Liver Frequency-Spatial Unified Self-Supervised Pretraining (LiFUSE). The frequency branch applies random band-stop masking and spectrum reconstruction to encourage the model to capture subtle differences between lesions and surrounding tissues, while the spatial branch performs hybrid-granularity masked volumetric reconstruction to accommodate lesions of diverse sizes and morphologies. Finally, a cross-domain consistency scheme couples the spatial and frequency branches, yielding more discriminative representations for hepatic structures and lesions. Extensive experiments on three clinically relevant tasks across internal cohorts and a public target-domain transfer setting show that LiFUSE consistently outperforms strong baselines. These results suggest that unified frequency-spatial learning can improve liver disease analysis on NCCT, highlighting its potential for large-scale screening.

cs.CV↗

arXiv2026

Cooperative STT and SOT switching in perpendicular magnetic tunnel junctions: Role of the pulse-end magnetization state

Spin--orbit torque MRAM (SOT-MRAM) is a leading candidate for next-generation nonvolatile memory, offering high speed, endurance, and architectural compatibility. However, in conventional SOT switching, the magnetization remains near the in-plane region at pulse termination, making the final state highly sensitive to post-pulse relaxation dynamics and prone to back-switching. To overcome this, we propose a field-free scheme in which the transverse SOT drives large-angle precessional excitation while the perpendicular spin-transfer torque (STT) biases the trajectory toward the reversed $-z$ state. Micromagnetic simulations reveal a nonlinear switching boundary in the $J_{\mathrm{STT}}$--$J_{\mathrm{SOT}}$ parameter space, originating from the distinct dynamical roles of the two torques: SOT primarily governs the excitation and crossing of the dynamical separatrix, whereas STT controls the terminal trajectory and final-state selection. An analytical macrospin model, based on the stability analysis of the current-induced equilibrium, reproduces the critical-boundary trends as functions of current density, Gilbert damping $α$, and uniaxial anisotropy $K_\mathrm{u}$, and distinguishes dynamic anti-damping and static instability branches. Systematic analyses of pulse duration, damping, anisotropy, and the STT--SOT balance further demonstrate that reliable ultrafast switching requires not only sufficient excitation to cross the separatrix before pulse termination, but also precise control of the pulse-end magnetization state to minimize post-pulse relaxation. These results establish that the pulse-end state, rather than the instantaneous torque amplitude, is the decisive factor governing switching speed and reliability in coupled STT--SOT systems.

cond-mat.mes-hall↗

arXiv2026

Robust and Generalizable Background Subtraction on Images of Calorimeter Jets using Unsupervised Generative Learning

Accurate separation of signal from background is one of the main challenges for precision measurements across high-energy and nuclear physics. Conventional supervised learning methods are insufficient here because the required paired signal and background examples are impossible to acquire in real experiments. Here, we introduce an unsupervised unpaired image-to-image translation neural network that learns to separate the signal and background from the input experimental data using cycle-consistency principles. We demonstrate the efficacy of this approach using images composed of simulated calorimeter data from the sPHENIX experiment, where physics signals (jets) are immersed in the extremely dense and fluctuating heavy-ion collision environment. Our method outperforms conventional subtraction algorithms in fidelity and overcomes the limitations of supervised methods. Furthermore, we evaluated the model's robustness in an out-of-distribution test scenario designed to emulate modified jets as in real experimental data. The model, trained on a simpler dataset, maintained its high fidelity on a more realistic, highly modified jet signal. This work represents the first use of unsupervised unpaired generative models for full detector jet background subtraction and offers a path for novel applications in real experimental data, enabling high-precision analyses across a wide range of imaging-based experiments.

nucl-ex↗

arXiv2026

Leveraging Imperfect Restoration for Data Availability Attack

The abundance of online data is at risk of unauthorized usage in training deep learning models. To counter this, various Data Availability Attacks (DAAs) have been devised to make data unlearnable for such models by subtly perturbing the training data. However, existing attacks often excel against either Supervised Learning (SL) or Self-Supervised Learning (SSL) scenarios. Among these, a model-free approach that generates a Convolution-based Unlearnable Dataset (CUDA) stands out as the most robust DAA across both SSL and SL. Nonetheless, CUDA's effectiveness against SSL is underwhelming and it faces a severe trade-off between image quality and its poisoning effect. In this paper, we conduct a theoretical analysis of CUDA, uncovering the sub-optimal gradients it introduces and elucidating the strategy it employs to induce class-wise bias for data poisoning. Building on this, we propose a novel poisoning method named Imperfect Restoration Poisoning (IRP), aiming to preserve high image quality while achieving strong poisoning effects. Through extensive comparisons of IRP with eight baselines across SL and SSL, coupled with evaluations alongside five representative defense methods, we showcase the superiority of IRP. Code: https://github.com/lyumingzhi/IRP

cs.AI↗

arXiv2026

Flippered hyperbolic surfaces and renormalized volumes of their moduli spaces I

We introduce a natural class of hyperbolic surfaces called flippered surfaces that generalize crowned hyperbolic surfaces (i.e.: worldsheets for open strings). We develop their Teichmüller and moduli-space theory, construct generalized Weil-Petersson volume forms and Chekhov's action, and prove that the resulting generalized Mirzakhani volumes are finite. We establish three geometric recursion formulae-neck chopping, disk excision, and crown extraction-which express these volumes in terms of those of topologically simpler surfaces. For the fundamental polygonal and annular cases, we derive integral representations involving conical Legendre functions, as well as explicit formulae in terms of elliptic integrals and polylogarithms. We further describe the arithmetic structure of the Taylor coefficients of these volumes, show that suitable specializations are Kontsevich-Zagier periods, and prove identities at the imaginary boundary length $2π\sqrt{-1}$ that generalize the Do-Norbury paraphrasing of string and dilaton-type equations.

math.GT↗

arXiv2026

No Data? No Problem: Synthesizing Security Graphs for Better Intrusion Detection

Provenance graph analysis plays a vital role in intrusion detection, particularly against Advanced Persistent Threats (APTs), by exposing complex attack patterns. While recent systems combine graph neural networks (GNNs) with natural language processing (NLP) to capture structural and semantic features, their effectiveness is limited by class imbalance in real-world data. To address this, we introduce PROVSYN, a novel hybrid provenance graph synthesis framework, which comprises three components: (1) graph structure synthesis via heterogeneous graph generation models, (2) textual attribute synthesis via fine-tuned Large Language Models (LLMs), and (3) five-dimensional fidelity evaluation. Experiments on six benchmark datasets demonstrate that PROVSYN consistently produces higher-fidelity graphs across the five evaluation dimensions compared to four strong baselines. To further demonstrate the practical utility of PROVSYN, we utilize the synthesized graphs to augment training datasets for downstream APT detection models. The results show that PROVSYN effectively mitigates data imbalance, improving normalized entropy by up to 0.35 in absolute terms, and enhances the generalizability of downstream detection models, yielding an absolute increase of up to 0.38 in balanced accuracy.

cs.CR↗

arXiv2026

Pandora: Leveraging Code-driven Knowledge Transfer for Unified Structured Knowledge Reasoning

Unified Structured Knowledge Reasoning (USKR) aims to answer natural language questions by using structured sources such as tables, databases, and knowledge graphs in a unified way. Existing USKR methods rely on task-specific strategies or bespoke representations, which hinder their ability to dismantle barriers between different SKR tasks, thereby constraining their overall performance in cross-task scenarios. In this paper, we introduce \textsc{Pandora}, a novel USKR framework that addresses the limitations of existing methods by leveraging two key innovations. First, we propose a code-based unified knowledge representation using \textsc{Python}'s \textsc{Pandas} API, which aligns seamlessly with the pre-training of LLMs. This representation facilitates a cohesive approach to handling different structured knowledge sources. Building on this foundation, we employ knowledge transfer to bolster the unified reasoning process of LLMs by automatically building cross-task memory. By adaptively correcting reasoning using feedback from code execution, \textsc{Pandora} showcases impressive unified reasoning capabilities. Extensive experiments on six widely used benchmarks across three SKR tasks demonstrate that \textsc{Pandora} outperforms existing unified reasoning frameworks and competes effectively with task-specific methods.

cs.CL↗