arXiv subjects

Liang Yu

Publications and source records attributed to Liang Yu.

At least 19 recordsLinked to original sources

arXiv2026

Can LLM Agents Learn to Test? Maintaining Scoped Experience as Testing Evidence for Mobile GUI Testing

Repeated mobile GUI tests can reuse routes, locators, and recovery strategies from earlier executions. However, a route that worked in one workflow or app version may be irrelevant or misleading in another. We study how an LLM-based tester can retain useful experience while withholding entries contradicted by current observations. We present a maintenance contract for AdaptiTest in which reusable experience has an explicit applicability scope, trace provenance, and a lifecycle for confirmation, revalidation, and withdrawal. The contract reserves persistence for a Reflector role and treats recalled experience as advice. The archived implementation does not establish end-to-end enforcement of every specified mechanism. The design changes retrieved context, not model weights. The evaluation uses read-only Android workflows and archived internal comparisons. A six-task, three-repeat ready subset reports 18/18 completed runs with memory versus 3/18 without it, but a grounded single-agent control also solves the earlier hard-task slice. A separate cross-session probe is excluded from efficacy conclusions because of confounded route schedules and unvalidated state labels. We examine 13 selected real-update hazard records across nine subjects, distinguishing stale-locator observations from policy-based withholding and offline retrieval diagnostics. The latter do not measure live-device failures or actions saved. These events are UI changes, not confirmed regression bugs. The evidence supports a bounded design and case study; it does not establish general efficacy, superiority over independent GUI-agent systems, or unrestricted exploration.

cs.SE↗

arXiv2026

When Does a Cross-Device Run Justify PASS? Obligation-Level Evidence Qualification under Partial Observability

A cross-device test can complete every command yet judge a business claim from evidence belonging to another device or attempt. We introduce an executable evidence contract that makes support qualification an explicit stage before predicate evaluation. It binds each obligation to admissible subjects, episodes, objects and observation scopes, and records unresolved support rather than treating an apparently successful observation as proof. We evaluate two implemented parts of the contract. A prospectively specified, 12-seed controlled study isolates association under reused identifiers across 2,304 claims. Given identical records and business policy, Atomic-Facts Flat produces 160 false PASS and 76.30% PASS recall; supplying computed associations reduces false PASS to five and increases PASS recall to 99.09%. Deterministic Closure produces zero false PASS and 100.00% PASS recall, improving on Atomic Flat in 11 seeds with one tie (two-sided sign p=0.00098). Most of the benefit comes from explicit association rather than graph notation. A separate prospective field characterization spans four workflows, 40 physical episodes and 80 claims. Against frozen reference labels, the physical-evidence verifier attains 95.00% accuracy and 100.00% PASS recall (27/27), with three false PASS judgments. The field results are descriptive: a policy-input mismatch prevents the planned matched-policy comparison, and post-hoc sensitivity does not establish superiority over a policy-informed textual baseline. Together, the studies characterize qualification on physical evidence and isolate the value of explicit association under a controlled matching contract.

cs.SE↗

arXiv2026

Robust Real-Time Monocular Human Pose Estimation with Insole-Based Sensor Fusion

Real-time monocular human pose estimation is an important sensing component for human-centered intelligent systems. While recent camera-based methods have achieved impressive accuracy, fundamental challenges persist, particularly when visual observations are incomplete, such as during lower-body occlusion or short out-of-frame intervals. In these challenging but common scenarios, vision-only systems often struggle to reconstruct physically plausible lower-limb motion and reliable foot-ground contact. Due to the highly unobtrusive and wearable nature of smart insoles, this paper investigates whether simple plantar pressure and acceleration sensors can effectively resolve these visually induced limitations. To systematically investigate this, we first collect a synchronized multimodal dataset and then propose a part-decoupled temporal fusion framework. The proposed model fuses foot-sensing features into the lower-body branch to compensate for incomplete visual evidence, while a lightweight coordinator exchanges information between the upper- and lower-body temporal representations to maintain whole-body consistency. The framework is evaluated with three representative real-time visual backbones based on 2D keypoints, 3D landmarks, and SMPL-based human mesh recovery. We evaluate our framework on three representative real-time visual backbones. Quantitative experiments demonstrate that incorporating simple foot sensors consistently improves pose accuracy, motion smoothness, and gait-related measurements over vision-only baselines, with the most significant gains observed under occlusion and short visual-dropout conditions. Ultimately, our results demonstrate that unobtrusive foot sensing provides vital and complementary physical observability when camera observations are temporarily unavailable.

cs.CV↗

arXiv2026

OntoAR-HAR: Ontology-Guided Agentic RAG with Personalized Memory for Human Activity Recognition

LLMs increasingly support sensor-based human activity recognition (HAR) by linking motion signals with activity semantics and physical knowledge. Retrieval-augmented generation (RAG) grounds decisions in sensor examples and domain features, enabling training-free target-user inference with less dependence on raw numerical arrays. However, existing LLM/RAG-based HAR typically searches single-level activity spaces using static population knowledge. Consequently, they compare many unrelated candidates using the same static population evidence and overlook personalized motion patterns. We propose OntoAR-HAR, an ontology-guided agentic RAG framework combining static population and personalized knowledge. Its tree-structured activity ontology decomposes classification into local decisions among semantically related activities. The static store supplies node-constrained examples, while offline-discovered executable signal features provide numerical evidence for local distinctions. During inference, the personalized store collects selected user observations, which the LLM integrates with static knowledge and signal features while traversing the ontology to an activity label. Cross-subject and heterogeneous-sensing experiments show complementary gains from hierarchical retrieval and personalized memory across multiple LLM backbones, achieving state-of-the-art performance. By explicitly modeling hierarchical relations across activity granularities, OntoAR-HAR also addresses the long-overlooked semantic inclusion problem and avoids treating related labels as independent categories.

cs.AI↗

arXiv2026

Order-preserving maps of the Turing degrees: regularity and consistency strength

We formulate a proof of Part~I of Martin's conjecture for order-preserving maps directly on the quotient of the reals by Turing equivalence. The assumptions are countable choice for reals, the perfect-set property for sets of reals, and continuous uniformization on a comeager domain. The argument applies under $\mathsf{AD}+\mathsf{DC}_{\R}$ and inside the choiceless Solovay model. We then determine the exact consistency strength of the unrestricted order-preserving dichotomy as an axiom over $\mathsf{ZF}+\mathsf{AC}_ω(\R)$: it is equiconsistent with $\mathsf{ZFC}$ plus a strongly inaccessible cardinal.

math.LO↗

arXiv2026

PointVGGT: Zero-Shot Multiview RGB-D Point Cloud Registration with Visual Geometry Foundation Priors

This paper addresses multiview RGB-D point cloud registration, aiming to estimate global rigid poses for unordered RGB-D scans and align them in a metrically consistent coordinate frame. The conventional pairwise-then-global paradigm suffers from locally optimized pairwise registration, severe error propagation and high computational burden. In particular, existing methods typically treat RGB data as a mere auxiliary matching cue and overlook the holistic geometric priors (e.g., camera poses and 3D models) encoded across image sequences. This paper introduces PointVGGT, a zero-shot framework built upon a novel \emph{foundation-then-refinement} paradigm that systematically leverages visual geometry foundation models (e.g., VGGT) as the computational backbone for robust, training-free multiview RGB-D registration. In the foundation stage, we directly recover metrically consistent global poses (without any pairwise estimation) by grounding the scale-ambiguous pose predictions of the foundation model against metric depth observations. In the refinement stage, we introduce an efficient voxelized spatial hashing mechanism that exploits the globally coherent 3D reconstruction (induced by the foundation model) as a shared spatial anchor, enabling dense multiview correspondences in near-linear time. On top of this, an IRLS-based robust motion-only bundle adjustment is performed using a conjugate gradient solver to jointly minimize the correspondence and reprojection residuals for multiview pose refinement. Extensive experiments on indoor/object-centric/outdoor datasets verify the outstanding zero-shot registration accuracy and computational efficiency of our proposed method.

cs.CV↗

arXiv2026

Small additive groups with $A+ξA=\mathbb R$

We prove that, for every irrational $ξ$, any $F_σ$ additive subgroup of $\R$ has an $F_σ$ $\Q$-vector space extension of the same Hausdorff dimension satisfying $A+ξA=\R$. Iteration gives simultaneous surjectivity for any prescribed countable family of irrational multipliers. Such a space exists in every prescribed dimension $d\in[0,1)$. We also construct in ZFC a zero-dimensional lightface $Δ^0_3$ $\Q$-vector subspace $A$ for which $A+ξA=\R$ holds for every irrational $ξ$, answering both parts of Question~2 of Ye, Yu, and Zhao. This universal group is a difference of two $F_σ$ sets, but is neither $F_σ$ nor $G_δ$. Both constructions use direct inductions on finite binary strings and admit effective versions. As applications, we obtain zero-dimensional $F_σ$ groups whose Cartesian squares have Hausdorff dimension one, and relate their dilate sums to Marstrand's projection theorem.

math.LO↗

arXiv2026

Open Problems in Mathematical Logic

These open problems were presented in the Problem Sessions held during the Tianyuan Workshop on Definability and Computation, June 22-26, 2026. The problems are organized into sections named after their contributors, in the order of their presentations during the workshop. Notes were taken and compiled by Wei Dai, Xiangxi Hu, Yingying Jiang, Ruiwen Li, Tianhao Wang, Xu Wang, and Jie Zou.

math.LO↗

arXiv2026

SleepWalking: Privileged Representation Shaping for End-to-End Blind Locomotion in Legged Robots

Partially observable locomotion requires a policy to act when task-relevant properties of the robot--environment state are not fully specified by instantaneous observations. Existing approaches often address this challenge by explicitly estimating missing physical variables or processing extended observation histories through structured architectures. We take a different view: partial observability is fundamentally an information-retention problem. The decisive question is not how task-relevant information enters the network, but whether the policy's internal state retains it. Guided by this perspective, we propose SleepWalking for Robot Locomotion (SWAQ), a one-stage end-to-end framework that uses next-step privileged physical reconstruction to shape what a recurrent history representation retains during policy learning, while the deployed actor uses only a direct history-to-action pathway. Under aligned training settings, SWAQ achieves a 15.0\% higher peak mean terrain level than DWAQ, the strongest non-exteroceptive baseline, while using 44.4\% fewer inference MACs per control step. Layerwise probes further show that information associated with the reconstructed physical variables remains linearly decodable through the policy head up to the layer preceding the action output. Complementary theoretical analysis relates privileged-variable recoverability to the achievable-return gap between history-based and privileged-information policy classes. These results suggest that semantic objectives can structure learning without requiring a corresponding architectural decomposition of the deployed controller.

cs.RO↗

arXiv2026

FUSER: Feed-Forward MUltiview 3D Registration Transformer and SE(3)$^N$ Diffusion Refinement

Registration of multiview point clouds conventionally relies on extensive pairwise matching to build a pose graph for global synchronization, which is computationally expensive and inherently ill-posed without holistic geometric constraints. This paper proposes FUSER, the first feed-forward multiview registration transformer that jointly processes all scans in a unified, compact latent space to directly predict global poses without any pairwise estimation. To maintain tractability, FUSER encodes each scan into low-resolution superpoint features via a sparse 3D CNN that preserves absolute translation cues, and performs efficient intra- and inter-scan reasoning through a Geometric Alternating Attention module. Particularly, we transfer 2D attention priors from off-the-shelf foundation models to enhance 3D feature interaction and geometric consistency. Building upon FUSER, we further introduce FUSER-DF, an SE(3)$^N$ diffusion refinement framework to correct FUSER's estimates via denoising in the joint SE(3)$^N$ space. FUSER acts as a surrogate multiview registration model to construct the denoiser, and a prior-conditioned SE(3)$^N$ variational lower bound is derived for denoising supervision. Extensive experiments on 3DMatch, ScanNet and ArkitScenes demonstrate that our approach achieves the superior registration accuracy and outstanding computational efficiency.

cs.CV↗

arXiv2026

CAX-Agent: A Lightweight Agent Harness for Reliable APDL Automation

Large language models deployed for MAPDL finite-element simulation face practical reliability challenges: without structured execution control, tool encapsulation, and fault recovery, outputs may be inconsistent and task failures are common. The Agent Harness paradigm addresses this by inserting domain-specific orchestration middleware that manages tool lifecycles, workflow state, and recovery escalation. This paper presents the architecture of CAX-Agent, a lightweight agent harness purpose-built for MAPDL automation, and empirically evaluates one of its core components -- the recovery policy.CAX-Agent organizes execution into three layers -- LLM service, agent harness, and solver backend -- with a recovery ladder that escalates from deterministic rule patching through model-driven regeneration to context enrichment and human intervention. We evaluate three recovery strategies (no_recovery, rule_only, and model_only) on 50 standard structural benchmarks with three repeated runs per strategy (450 case-runs total). Two independent human raters score task completion under blind conditions; inter-rater agreement is strong (quadratic weighted Cohen's kappa = 0.84, 96 percent of score pairs within one point). Model_only achieves the best completion rate (0.9267), task score (3.59/4), total score (9.16/10), and zero-intervention rate (0.84), outperforming rule_only (0.7733, 3.17/4, 7.03/10, 0.00) and no_recovery (0.6933, 2.74/4, 5.60/10, 0.00) with large effect sizes (Cliff's delta = 0.81-0.87). The benchmark uses deliberately simple geometries to isolate recovery-policy effects; we discuss the scope of these findings and directions for broader validation.

cs.AI↗

arXiv2026

When is $A + x A =\mathbb{R}$

We show that there is an additive $F_σ$ subgroup $A$ of $\mathbb{R}$ and $x \in \mathbb{R}$ such that $\mathrm{dim_H} (A) = \frac{1}{2}$ and $A + x A =\mathbb{R}$. However, if $A \subseteq \mathbb{R}$ is a subring of $\mathbb{R}$ and there is $x \in \mathbb{R}$ such that $A + x A =\mathbb{R}$, then $A =\mathbb{R}$. Moreover, assuming the continuum hypothesis (CH), there is a subgroup $A$ of $\mathbb{R}$ with $\mathrm{dim_H} (A) = 0$ such that $x \not\in \mathbb{Q}$ if and only if $A + x A =\mathbb{R}$ for all $x \in \mathbb{R}$. A key ingredient in the proof of this theorem consists of some techniques in recursion theory and algorithmic randomness. We believe it may lead to applications to other constructions of exotic sets of reals. Several other theorems on measurable, and especially Borel and analytic subgroups and subfields of the reals are presented. We also discuss some of these results in the $p$-adics.

math.LO↗

arXiv2026

A Review of Hydrogen-Enabled Resilience Enhancement for Multi-Energy Systems

Ensuring resilience in multi-energy systems (MESs) has become increasingly urgent and challenging due to the growing frequency and severity of extreme events, such as natural disasters, extreme weather, and cyber-physical attacks. Among the various approaches to enhancing MES resilience, hydrogen integration offers significant potential in cross-temporal, cross-spatial, and cross-sector flexibility, as well as black-start capability. Although considerable efforts have been devoted to this area, a systematic review of resilience enhancement in hydrogen-enabled MESs is still lacking. To address this gap, this paper presents a comprehensive review of hydrogen-enabled MES resilience enhancement. First, advantages, vulnerabilities, and challenges related to hydrogen-enabled MES resilience enhancement are summarized. Next, a resilience enhancement framework for hydrogen-enabled MESs is proposed, based on which existing resilience metrics and event-oriented contingency models are reviewed and discussed. Planning measures are then classified according to the types of hydrogen-related facilities, together with uncertainty handling methods, scenario generation methods, and planning problem formulation frameworks. In addition, operational enhancement measures are categorized into three response stages: prevention, emergency response, and restoration. Finally, research gaps are identified and future directions are discussed, including comprehensive resilience metric design, advanced extreme-event scenario generation, spatiotemporal cyber-physical contingency modeling under compound extreme events, coordinated planning and operation across multiple networks and timescales, low-carbon resilient planning and operation, and large language model-assisted whole-process resilience enhancement.

eess.SY↗

arXiv2026

End-to-End Learning-based Operation of Integrated Energy Systems for Buildings and Data Centers

Buildings and data centers (DCs) are energy-intensive sectors, playing a critical role to achieve the low-carbon and sustainable energy transition targets. To this end, integrated energy system (IES) that incorporates diverse renewables, energy generation, conversion, and storage technologies to enable coordinated multi-energy supply have been widely investigated for both buildings and DCs. However, few works consider the two sectors jointly within IES to exploit their substantial synergistic benefits. Meanwhile, the operational optimization of IES remains challenging due to the difficulty to predict the multi-energy demand and supply accurately. To address these gaps, this paper investigates IES for coordinated multi-energy supply of buildings and DC, where the waste heat from DCs is recovered and reused to enhance energy efficiency. Moreover, an end-to-end learning-based method is proposed for the operational optimization of IES under uncertainty. Unlike conventional predict-then-optimize approaches, the proposed method integrates the training of prediction models for uncertain variables with the constrained optimization of IES into a unified learning framework, guiding the training of prediction models to improve operational performance, rather than prediction accuracy, thereby mitigating the impacts of predictions errors. Case studies based on real-world datasets show that the proposed methods improves the operational performance of IES by about 7-9% compared to existing predict-then-optimize methods. In addition, coordinating buildings and DCs within IES shows substantial economic benefits. In particular, the waste heat recovery from DCs leads to approximately 10% of total energy cost reduction of the IES.

eess.SY↗

arXiv2026

Leveraging Large Vision Model for Multi-UAV Co-perception in Low-Altitude Wireless Networks

Multi-uncrewed aerial vehicle (UAV) cooperative perception has emerged as a promising paradigm for diverse low-altitude economy applications, where complementary multi-view observations are leveraged to enhance perception performance via wireless communications. However, the massive visual data generated by multiple UAVs poses significant challenges in terms of communication latency and resource efficiency. To address these challenges, this paper proposes a communication-efficient cooperative perception framework, termed Base-Station-Helped UAV (BHU), which reduces communication overhead while enhancing perception performance. Specifically, we employ a Top-K selection mechanism to identify the most informative pixels from UAV-captured RGB images, enabling sparsified visual transmission with reduced data volume and latency. The sparsified images are transmitted to a ground server via multi-user MIMO (MU-MIMO), where a Swin-large-based MaskDINO encoder extracts bird's-eye-view (BEV) features and performs cooperative feature fusion for ground vehicle perception. Furthermore, we develop a diffusion model-based deep reinforcement learning (DRL) algorithm to jointly select cooperative UAVs, sparsification ratios, and precoding matrices, achieving a balance between communication efficiency and perception utility. Simulation results on the Air-Co-Pred dataset demonstrate that, compared with traditional CNN-based BEV fusion baselines, the proposed BHU framework improves perception performance by over 5% while reducing communication overhead by 85%, providing an effective solution for multi-UAV cooperative perception under resource-constrained wireless environments.

cs.CV↗

arXiv2026

Geometry-to-Image Synthesis-Driven Generative Point Cloud Registration

In this paper, we propose a novel 3D registration paradigm, Generative Point Cloud Registration, which bridges advanced 2D generative models with 3D matching tasks to enhance registration performance. Our key idea is to generate cross-view consistent image pairs that are well-aligned with the source and target point clouds, enabling geometry-color feature fusion to facilitate robust matching. To ensure high-quality matching, the generated image pair should feature both 2D-3D geometric consistency and cross-view texture consistency. To this end, we introduce DepthMatch-ControlNet and LiDARMatch-ControlNet, two matching-specific, controllable 2D generative models. Specifically, for depth camera-based 3D registration with point clouds derived from the depth maps, DepthMatch-ControlNet leverages the depth-conditioned generation capabilities of ControlNet to synthesize perspective-view RGB images that are geometrically consistent with depth maps, ensuring accurate 2D-3D alignment. Additionally, by incorporating a coupled conditional denoising scheme and coupled prompt guidance, it further promotes cross-view feature interaction, guiding texture consistency generation. To address LiDAR-based 3D registration with point clouds captured by LiDAR sensors, LiDARMatch-ControlNet extends this framework by conditioning on paired equirectangular range maps projected from 360-degree LiDAR point clouds, generating corresponding panoramic RGB images. Our generative 3D registration paradigm is general and can be seamlessly integrated into a wide range of existing registration methods to improve their performance. Extensive experiments on the 3DMatch and ScanNet datasets (for depth-camera settings), as well as the Dur360BEV dataset (for LiDAR settings), demonstrate the effectiveness of our approach.

cs.CV↗

arXiv2026

Rewarding Creativity: A Human-Aligned Generative Reward Model for Reinforcement Learning in Storytelling

While Large Language Models (LLMs) can generate fluent text, producing high-quality creative stories remains challenging. Reinforcement Learning (RL) offers a promising solution but faces two critical obstacles: designing reliable reward signals for subjective storytelling quality and mitigating training instability. This paper introduces the Reinforcement Learning for Creative Storytelling (RLCS) framework to systematically address both challenges. First, we develop a Generative Reward Model (GenRM) that provides multi-dimensional analysis and explicit reasoning about story preferences, trained through supervised fine-tuning on demonstrations with reasoning chains distilled from strong teacher models, followed by GRPO-based refinement on expanded preference data. Second, we introduce an entropy-based reward shaping strategy that dynamically prioritizes learning on confident errors and uncertain correct predictions, preventing overfitting on already-mastered patterns. Experiments demonstrate that GenRM achieves 68\% alignment with human creativity judgments, and RLCS significantly outperforms strong baselines including Gemini-2.5-Pro in overall story quality. This work provides a practical pipeline for applying RL to creative domains, effectively navigating the dual challenges of reward modeling and training stability.

cs.AI↗

arXiv2026

Beyond Direct Generation: A Decomposed Approach to Well-Crafted Screenwriting with LLMs

The screenplay serves as the foundation for television production, defining narrative structure, character development, and dialogue. While Large Language Models (LLMs) show great potential in creative writing, direct end-to-end generation approaches often fail to produce well-crafted screenplays. We argue this failure stems from forcing a single model to simultaneously master two disparate capabilities: creative narrative construction and rigid format adherence. The resulting outputs may mimic superficial style but lack the deep structural integrity and storytelling substance required for professional use. To enable LLMs to generate high-quality screenplays, we introduce Dual-Stage Refinement (DSR), a decomposed framework that decouples creative narrative generation from format conversion. The first stage transforms a brief outline into rich, novel-style prose. The second stage refines this narrative into a professionally formatted screenplay. This separation enables the model to specialize in one distinct capability at each stage. A key challenge in implementing DSR is the scarcity of paired outline-to-novel training data. We address this through hybrid data synthesis: reverse synthesis deconstructs existing screenplays into structured inputs, while forward synthesis leverages these inputs to generate high-quality narrative texts as training targets. Blind evaluations by professional screenwriters show that DSR achieves a 75% win rate against strong baselines like Gemini-2.5-Pro and reaches 82.7% of human-level performance. Our work demonstrates that decomposed generation architecture with tailored data synthesis effectively specializes LLMs in complex creative domains.

cs.CL↗