arXiv subjects

Jiyuan Wang

Publications and source records attributed to Jiyuan Wang.

At least 19 recordsLinked to original sources

arXiv2026

QDiff: Differential Testing of Quantum Software Stacks

Over the past few years, several quantum software stacks (QSS) have been developed in response to rapid hardware advances in quantum computing. A QSS includes a quantum programming language, an optimizing compiler that translates a quantum algorithm written in a high-level language into quantum gate instructions, a quantum simulator that emulates these instructions on a classical device, and a software controller that sends analog signals to a very expensive quantum hardware based on quantum circuits. In comparison to traditional compilers and architecture simulators, QSSes are difficult to tests due to the probabilistic nature of results, the lack of clear hardware specifications, and quantum programming complexity. This work devises a novel differential testing approach for QSSes, named QDIFF with three major innovations: (1) We generate input programs to be tested via semantics-preserving, source to source transformation to explore program variants. (2) We speed up differential testing by filtering out quantum circuits that are not worthwhile to execute on quantum hardware by analyzing static characteristics such as a circuit depth, 2 qubit gate operations, gate error rates, and T1 relaxation time. (3) We design an extensible equivalence checking mechanism via distribution comparison functions such as Kolmogorov Smirnov test and cross entropy

quant-ph↗

arXiv2026

CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating

In this paper, we propose Concentrate and Concentrate (CaC), a coarse-to-fine anomaly reward model based on Vision-Language Models. During inference, it first conducts a global temporal scan to anchor anomalous time windows, then performs fine-grained spatial grounding within the localized interval, and finally derives robust judgments via structured spatiotemporal Chain-of-Thought reasoning. To equip the model with these capabilities, we construct the first large-scale generated video anomaly dataset with per-frame bounding-box annotations, temporal anomaly windows, and fine-grained attribution labels. Building on this dataset, we design a three-stage progressive training paradigm. The model initially learns spatial and temporal anchoring through single- and multi-frame supervised fine-tuning, and then is optimized by a reinforcement learning strategy based on two-turn Group Relative Policy Optimization (GRPO). Beyond conventional accuracy rewards, we introduce Temporal and Spatial IoU rewards to supervise the intermediate localization process, effectively guiding the model toward more grounded and interpretable spatiotemporal reasoning. Extensive experiments demonstrate that CaC can stably concentrate on subtle anomalies, achieving a 25.7% accuracy improvement on fine-grained anomaly benchmarks and, when used as a reward signal, CaC reduces generated-video anomalies by 11.7% while improving overall video quality.

cs.CV↗

arXiv2026

Precedent or Intent? What Coding Agents Follow When Evolving Existing Code

Existing code reveals past implementation decisions but rarely explains the reasoning behind them. When coding agents implement new features or modify existing functionality, past decisions may conflict with new task instructions. This raises a fundamental question for agentic software evolution: when multiple implementations satisfy the same functional requirements, how do coding agents decide whether to follow existing code or new task instructions? We investigate this question through bidirectional, controlled experiments in purpose-built repositories, followed by validation in real-world open-source repositories. Our approach isolates three competing sources of guidance: (1) agents' default preferences, (2) repository precedents, and (3) explicit task instructions. We conduct 5,625 trials across four coding agents and six implementation pairs, with validation in four open-source repositories spanning three programming languages. We find that agents share the same default implementation choices, yet overwhelmingly follow repository precedent when it conflicts with those defaults (359/360 trials). Crucially, not all precedents carry equal influence: three supporting local files yield 96% adoption, compared with only 4% for sibling-resource files, and changing file placement alone can shift adoption from 0% to 100% at a fixed example count. When new task intent conflicts with existing code, written priority rules achieve substantially higher success than code examples alone (59/60 versus 38/60 joint successes for two agents on two implementation pairs). The effectiveness of explicit rules also extends to open-source repositories, where a harness-loaded rule raises joint success from 0/120 to 117/120. These findings motivate design-decision traceability that preserves not only implementation choices but also the rationale and priorities that should guide future changes.

cs.SE↗

arXiv2026

DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation

Diffusion-based generative AI has achieved remarkable success in e-commerce applications such as virtual try-on, poster generation, and product background synthesis. However, when making online purchasing decisions for apparel, consumers also desire the freedom to examine specific detail regions of interest, such as collars, cuffs, and fabric textures, yet existing methods have not explicitly studied this setting. We therefore formalize a new, non-template task: Fashion Detail Generation with focus conditioning, and release FDBench, the first benchmark comprising 40K+ human-verified reference-detail pairs across 41 different categories. This task poses a unique semantic gap challenge: the model must bridge the correspondence between a focus marker on a product reference image and a photorealistic close-up view of the indicated region, while faithfully preserving the garment's identity, without any precise prompt. To bridge this gap, we propose Cross-modal Feature Alignment Distillation (CFAD), which leverages a fine-tuned DINOv3 teacher to align both branches of a Multimodal Diffusion Transformer in a shared semantic space via dual-branch distillation. To further improve consistency between generated details and reference images, we introduce a consistency reward model that jointly scores image pairs along three quality axes and optimizes generation via reinforcement learning. Experiments show that our model DetailAnywhere significantly outperforms all state-of-the-art opensource methods across all metrics and human evaluations.

cs.CV↗

arXiv2026

IndusAgent: Agentic Reinforcement Learning for Cross-Category Industrial Anomaly Detection

Small defects in unfamiliar product categories can be difficult to distinguish from benign appearance variations in a global view. Additional reasoning over the same view may leave this ambiguity unresolved. We introduce IndusAgent, a Qwen3-VL-8B inspection policy trained through supervised fine-tuning and tool-augmented reinforcement learning for cross-category industrial anomaly detection. The policy selects among six tools for cropping, enhancement, measurement, within-image comparison, texture analysis, and external visual opinions from Qwen3-VL-Max, then integrates returned observations into a structured diagnosis. Indus-CoT provides 3,000 trajectories from 26 Real-IAD categories, generated with actual tool feedback and screened against annotations after teacher generation. GRPO optimizes an accuracy-gated objective that conditions localization, type, and tool rewards, including call costs, on final diagnostic correctness while retaining an independent format reward. Across five benchmarks, IndusAgent achieves 83.5% mean balanced accuracy, compared with 79.4% for direct Max inference under the common protocol. Across three training seeds, the five-benchmark mean balanced accuracy is 80.5\% for a weight-matched ungated control and 83.5% for the gated policy. Evaluation uses disjoint product categories and a fixed defect vocabulary.

cs.CV↗

arXiv2026

Thinker-WM: A Unified World Model with Shared Multimodal Representations for Embodied Intelligence

World models have emerged as a promising paradigm for embodied AI, yet existing systems often remain fragmented in the modalities they model and the functions they support. In particular, visual dynamics, geometric structure, and executable action are commonly coupled through separate interfaces or downstream modules rather than being jointly represented and evolved within a shared dynamics model. In this work, we present Thinker-WM, a unified multimodal world model that jointly models and generates RGB, metric depth, and robot action through a shared intermediate Unified Dynamics Transformer with modality-specific encoders and decoders. The model performs multimodal unification at the representation level: appearance, geometry, and action are transformed into a common dynamic representation and jointly evolved by shared parameters, while their distinct output structures are preserved. The same parameterization supports multiple functions, including joint video-action generation, world prediction, policy inference, action-conditioned generation, video-to-action generation, and inverse dynamics. To examine whether the shared representation captures action-related information, we introduce a lightweight motion probe that shows the frozen visual representation contains recoverable motion information. Thinker-WM is trained on a heterogeneous corpus comprising approximately 20K hours of egocentric video, 10K hours of real-robot data, and 1K hours of simulation data, including approximately 4K hours of real-robot data with aligned depth supervision. Extensive experiments demonstrate strong performance across embodied world-model evaluations. Thinker-WM ranks first on EWMBench, WorldOlympiad and WorldArena, while controlled studies further demonstrate the benefits of action conditioning, geometric interaction, and multi-function training within the shared representation.

cs.AI↗

arXiv2026

Are We Testing the Wrong Quantum Bugs? A Study of Fault Representation Gaps in Quantum Software Testing

Quantum software relies on compilers, intermediate representations, and execution frameworks that transform programs before execution. Faults in these components can change the behavior of otherwise correct quantum programs. Yet quantum testing techniques are often evaluated using mutation-generated faults and curated bug benchmarks. We investigate how well the faults represented by these artifacts reflect those encountered in modern quantum software. We audit four quantum mutation-testing tools and three curated bug benchmarks, and collect 410 verified bugs from ten quantum software repositories over two years. We classify faults from all three sources into a common taxonomy of 56 bug families and compare their representation across mutation operators, curated benchmarks, and recent real-world bugs. The mutation tools support 20 bug families, and curated benchmarks add 15 more. Yet only 56 of the 410 real-world bugs (13.7%) belong to families represented by either source; the remaining 354 (86.3%) belong to families absent from both. The largest unrepresented families concern compiler transformations (66 bugs), type handling (53), and input validation (47). Unlike local gate or statement changes, these faults often depend on intermediate representations, compiler pipelines, input types, or dependency versions. Existing mutation operators primarily modify circuits and program constructs, whereas many real-world faults arise in the compilers, representations, and framework interfaces that process them. Addressing this gap requires looking beyond circuit-level faults toward testing semantic preservation across compiler transformations, correctness at representation boundaries, and interactions between software components. Our study provides empirical evidence to guide fault models and benchmarks that capture these mechanisms and preserve the contexts needed to reproduce them.

cs.SE↗

arXiv2026

Isolating Recurring Backend-Dependent Abnormal Patterns on NISQ Quantum Devices

Quantum hardware remains highly susceptible to noise, making compilation a critical step for obtaining reliable execution on existing devices. Today's quantum compilers approximate hardware noise using calibration-derived costs over gates, qubits, and coupling edges, and use the costs to guide qubit mapping, routing, and scheduling. However, this abstraction is incomplete: semantically equivalent circuits with identical compiler-predicted hardware noise can still behave very differently on real devices. Execution context can contribute to this gap: short ordered gate sequences on specific qubit neighborhoods can be associated with hardware-model mismatch. Identifying these backend-dependent abnormal patterns can guide gate-ordering rewrites in the circuit family and layout where they were observed. To find these patterns, we propose QRisk, a framework that isolates recurring abnormal gate sequences from quantum hardware executions. QRisk starts from a circuit whose hardware output is much worse than predicted by the calibration-based noise model. It then reduces the circuit at the segment level, identifying groups of segments whose removal lowers the discrepancy ratio or whose retention within the tested circuit context preserves an elevated ratio. The resulting circuit fragments are treated as candidate abnormal patterns. On three IBM Heron r2 backends (quantum devices) across 30 qubit layouts, QRisk finds 25 recurring abnormal gate patterns. Reordering commuting gates to break the two highest-recurrence patterns in their Grover discovery circuits reduces mean hardware-model mismatch by 24% on ibm_fez and 45% on ibm_marrakesh.

cs.SE↗

arXiv2026

X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoning

Chest X-ray (CXR) interpretation often requires integrating visual findings with task-specific evidence rather than relying on direct visual recognition alone. While tool-augmented medical agents can supply such evidence via external modules, they often lack explicit mechanisms for learning when auxiliary evidence is needed and for preventing inapplicable quantitative evidence from entering diagnostic reasoning. To address this, we propose X-Ragent, a post-training framework for tool-augmented reinforcement learning that decouples learned auxiliary-evidence seeking from validity-gated quantitative measurement acquisition for evidence-grounded CXR reasoning. We construct Rad-CoT, a 7.7K-sample corpus combining causally ordered tool-augmented trajectories with report-style diagnostic reasoning, and use it to initialize Qwen3-VL-8B via agentic supervised fine-tuning (SFT). We then optimize the policy with Group Relative Policy Optimization (GRPO) using an accuracy-gated reward that applies process-level terms for measurement consistency and auxiliary-tool cost only to correct trajectories, preventing plausible process behavior from compensating for an incorrect diagnosis. Across three CXR benchmarks, X-Ragent achieves the strongest results, including an 8.6-point improvement on the fully held-out ChestAgentBench. By seeking evidence selectively and admitting only valid measurements, X-Ragent supports more faithful and evidence-grounded CXR reasoning.

cs.CV↗

arXiv2026

NeuroCLIP: Brain-Inspired Prompt Tuning for EEG-to-Image Multimodal Contrastive Learning

Recent advances in brain-inspired artificial intelligence have sought to align neural signals with visual semantics using multimodal models such as CLIP. However, existing methods often treat CLIP as a static feature extractor, overlooking its adaptability to neural representations and the inherent physiological-symbolic gap in EEG-image alignment. To address these challenges, we present NeuroCLIP, a prompt tuning framework tailored for EEG-to-image contrastive learning. Our approach introduces three core innovations: (1) We design a dual-stream visual embedding pipeline that combines dynamic filtering and token-level fusion to generate instance-level adaptive prompts, which guide the adjustment of patch embedding tokens based on image content, thereby enabling fine-grained modulation of visual representations under neural constraints; (2) We are the first to introduce visual prompt tokens into EEG-image alignment, acting as global, modality-level prompts that work in conjunction with instance-level adjustments. These visual prompt tokens are inserted into the Transformer architecture to facilitate neural-aware adaptation and parameter optimization at a global level; (3) Inspired by neuroscientific principles of human visual encoding, we propose a refined contrastive loss that better model the semantic ambiguity and cross-modal noise present in EEG signals. On the THINGS-EEG2 dataset, NeuroCLIP achieves a Top-1 accuracy of 63.2% in zero-shot image retrieval, surpassing the previous best method by +12.3%, and demonstrates strong generalization under inter-subject conditions (+4.6% Top-1), highlighting the potential of physiology-aware prompt tuning for bridging brain signals and visual semantics.

cs.IR↗

arXiv2026

TextRefine: Improving Textual Fidelity, Spatial Placement, and Glyph Rendering for Text Editing in Product Posters

Text editing in product posters entails inserting new text or replacing existing text while preserving product appearance, background content, and global composition. Despite recent progress in instruction-based image editing, general-purpose models remain unreliable in this setting: they often omit or incorrectly render the target text, place it over salient products or pre-existing content, and produce structurally distorted or visually inconsistent glyphs. We introduce \textbf{TextRefine}, a task-aligned post-training framework that combines supervised fine-tuning with operation-specific reward optimization to address these complementary failure modes. For text insertion, our text-span-level reward jointly assesses semantic fidelity and target-span coverage, penalizes spatial conflicts with products and existing text, and employs a gated structural constraint to preserve non-text regions. For text replacement, our glyph-level reward leverages the connectionist temporal classification (CTC) posterior of the target character to provide graded supervision for fine-grained defects, including missing strokes, structural deformations, and confusion among visually similar characters. We further introduce \textbf{OpenTextEdit}, a dataset comprising 100K images for text editing in product posters, with multi-text layouts, detailed text attributes, product masks, and challenging low-frequency characters. Extensive experiments on both insertion and replacement demonstrate that TextRefine consistently outperforms the evaluated image editing baselines in textual fidelity, placement reliability, and glyph quality while better preserving source-image content.

cs.CV↗

arXiv2026

RePer-360: Releasing Perspective Priors for 360$^\circ$ Depth Estimation via Self-Modulation

Recent depth foundation models trained on perspective imagery achieve strong performance, yet generalize poorly to 360$^\circ$ images due to the substantial geometric discrepancy between perspective and panoramic domains. Moreover, fully fine-tuning these models typically requires large amounts of panoramic data. To address this issue, we propose RePer-360, a distortion-aware self-modulation framework for monocular panoramic depth estimation that adapts depth foundation models while preserving powerful pretrained perspective priors. Specifically, we design a lightweight geometry-aligned guidance module to derive a modulation signal from two complementary projections (i.e., ERP and CP) and use it to guide the model toward the panoramic domain without overwriting its pretrained perspective knowledge. We further introduce a Self-Conditioned AdaLN-Zero mechanism that produces pixel-wise scaling factors to reduce the feature distribution gap between the perspective and panoramic domains. In addition, a cubemap-domain consistency loss further improves training stability and cross-projection alignment. By shifting the focus from complementary-projection fusion to panoramic domain adaptation under preserved pretrained perspective priors, RePer-360 surpasses standard fine-tuning methods while using only 1\% of the training data. Under the same in-domain training setting, it further achieves an approximately 20\% improvement in RMSE. The code is available at https://github.com/munimo/RePer360.

cs.CV↗

arXiv2026

Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editing

Leveraging the priors of 2D diffusion models for 3D editing has emerged as a promising paradigm. However, multi-view consistency remains challenging in edited results, and the extreme scarcity of paired 3D-consistent editing data makes supervised fine-tuning (SFT) impractical, despite its effectiveness for editing tasks. In this paper, we observe that, while generating multi-view consistent 3D content is highly challenging, verifying 3D consistency is tractable, naturally positioning reinforcement learning (RL) as a feasible solution. Motivated by this, we propose RL3DEdit, a single-pass framework driven by RL optimization with novel rewards derived from the 3D foundation model, VGGT. Specifically, we leverage VGGT's robust priors learned from massive real-world data, feed the edited images into it, and utilize the output confidence maps and pose estimation errors as reward signals, effectively anchoring the 2D editing priors onto a 3D-consistent manifold via RL. Extensive experiments demonstrate that RL3DEdit achieves stable multi-view consistency and outperforms state-of-the-art methods in editing quality with high efficiency. To promote the development of 3D editing, we will release the code and model.

cs.CV↗

arXiv2026

Tensor Algebraic Property Skeletons: Amplifying Property-Based Testing for AI Compilers

Deep learning (DL) compilers such as TVM and ONNX-MLIR lower tensor computation graphs into optimized executables for target backends. Testing these compilers has made substantial progress in generating well-formed inputs in the context of fuzzing. However, such generation alone does not catch semantic drifts from algebraic invariants that graph transformations and optimizations are expected to preserve. While tensor algebra has been studied for decades, it has not been transformed into executable property-based tests (PBTs) for DL compilers because doing so requires the time-consuming and error-prone task of jointly constructing operators, tensors, and oracles. The central challenge is no longer generating well-formed inputs for fuzzing DL compilers, but bootstrapping executable PBTs with such inputs and correct oracles based on tensor algebra. We realize this vision in Propilot, an LLM-driven agentic property-based testing framework for DL compilers. First, Propilot represents tensor algebra knowledge as reusable property skeletons, each coupled with operator constraints and oracle templates. Second, given a target compiler, Propilot instantiates these skeletons into executable PBTs by generating paired tensor computation graphs, tensor inputs, and expected semantic relations as oracles. Third, to prevent generated tests from degenerating into invalid or uninformative PBTs, Propilot validates each PBT candidate before execution for applicability and safety. Validation feedback, execution results, and coverage signals guide subsequent generation. We evaluate Propilot on TVM with 212 operators and 20 property skeletons, generating 4,579 PBTs. Compared with direct LLM-based PBT generation, Propilot reduces redundancy by 49% and eliminates invalid tests through explicit property skeletons. This effectiveness translates into finding semantic errors and numerical discrepancies.

cs.SE↗

arXiv2026

Finding Compiler-Platform Interaction Bugs in Deep Learning Pipelines via Cross-Layer Constraints

The growing deployment of artificial intelligence (AI) necessitates robust deep learning (DL) compilers, such as TVM and ONNX-MLIR. These compilers take as input high-level AI models, lower them through multi-layer transformations, and specialize them to diverse hardware. Testing such compilers is uniquely challenging as correctness depends on implicit constraints embedded throughout the compilation stack. Existing testing approaches largely take type constraints to restrict input model generation and therefore emphasize type validation and monitor compilation crashes or coverage gains. This focus overlooks compiler-platform interaction bugs that arise from interleaved effects across compilation and execution environments. In this work, we propose a scalable, automated DL compiler testing framework for, in tandem, (1) finding compiler-platform interaction bugs and (2) enabling behavior equivalence partitioning. Our key insight is that these bugs are caused by violated assumptions arising from interactions across compilation passes and hardware platforms. Therefore, we move beyond constraining input generation and derive full-stack constraints. Our approach is three-fold. First, we design an automated approach to extract full-stack constraints that jointly guide model generation and characterize compilation behaviors. Second, we prioritize constraints that expose interaction-sensitive behaviors, so our generated models are capable of exercising deep compilation logic. Third, we enable behavior equivalence partitioning by automatically inserting assertions to monitor distinct compilation symptoms that coverage or pass/fail signals miss. We evaluated our tool, XCheck, on three widely-used DL compilers and found 2,034 bug-revealing cases, including memory overflows, integer overflows, and silent unexpected compilations that were rooted in compiler-platform interactions.

cs.SE↗

arXiv2026

Needle in the Repo: A Benchmark for Maintainability in AI-Generated Repository Edits

AI coding agents can now complete complex programming tasks, but existing evaluations largely emphasize behavioral correctness and often overlook maintainability risks such as weak modularity or testability. We present Needle in the Repo (NITR), a diagnostic probe-and-oracle framework for evaluating whether behaviorally correct repository edits preserve maintainable structure. NITR distills recurring software engineering wisdom into controlled probes embedded in small, realistic multi-file codebases, each designed so that success depends primarily on one targeted maintainability dimension. Each probe is paired with a hidden evaluation harness that combines functional tests for required behavior with structural oracles that encode the targeted maintainability constraint and return interpretable diagnoses. Using NITR, we evaluate 23 coding configurations across GPT, Claude, Gemini, and Qwen families in both direct-inference and agent-based settings. Current AI coding systems remain far from robust: on average, configurations solve only 36.2% of cases, the best reaches 57.1%, and performance drops from 53.5% on micro cases to 20.6% on multi-step cases. The hardest pressures are architectural rather than local edits, especially dependency control (4.3%) and responsibility decomposition (15.2%). Moreover, 64/483 outcomes (13.3%) pass all functional tests yet fail the structural oracle. Under our harness, agent-mode configurations improve average performance from 28.2% to 45.0%, but do not eliminate these architectural failures. These results show that progress in code generation is not yet progress in maintainable code evolution, and that NITR exposes a critical failure surface missed by conventional evaluation.

cs.SE↗

arXiv2026

HALO: A Fine-Grained Resource Sharing Quantum Operating System

As quantum computing enters the cloud era, thousands of users must share access to a small number of quantum processors. Users need to wait minutes to days to start their jobs, which only takes a few seconds for execution. Current quantum cloud platforms employ a fair-share scheduler, as there is no way to multiplex a quantum computer among multiple programs at the same time, leaving many qubits idle and significantly under-utilizing the hardware. This imbalance between high user demand and scarce quantum resources has become a key barrier to scalable and cost-effective quantum computing. We present HALO, the first quantum operating system design that supports fine-grained resource-sharing. HALO introduces two complementary mechanisms. First, a hardware-aware qubit-sharing algorithm that places shared helper qubits on regions of the quantum computer that minimize routing overhead and avoid cross-talk noise between different users' processes. Second, a shot-adaptive scheduler that allocates execution windows according to each job's sampling requirements, improving throughput and reducing latency. Together, these mechanisms transform the way quantum hardware is scheduled and achieve more fine-grained parallelism. We evaluate HALO on the IBM Torino quantum computer on helper qubit intense benchmarks. Compared to state-of-the-art systems such as HyperQ, HALO improves overall hardware utilization by up to 2.44x, increasing throughput by 4.44x, and maintains fidelity loss within 33%, demonstrating the practicality of resource-sharing in quantum computing.

cs.OS↗

arXiv2026

Thinker: A vision-language foundation model for embodied intelligence

When large vision-language models are applied to the field of robotics, they encounter problems that are simple for humans yet error-prone for models. Such issues include confusion between third-person and first-person perspectives and a tendency to overlook information in video endings during temporal reasoning. To address these challenges, we propose Thinker, a large vision-language foundation model designed for embodied intelligence. We tackle the aforementioned issues from two perspectives. Firstly, we construct a large-scale dataset tailored for robotic perception and reasoning, encompassing ego-view videos, visual grounding, spatial understanding, and chain-of-thought data. Secondly, we introduce a simple yet effective approach that substantially enhances the model's capacity for video comprehension by jointly incorporating key frames and full video sequences as inputs. Our model achieves state-of-the-art results on two of the most commonly used benchmark datasets in the field of task planning.

cs.CV↗