arXiv subjects

Yihan Sun

Publications and source records attributed to Yihan Sun.

At least 19 recordsLinked to original sources

arXiv2026

A unified reconstruction algorithm for reduced-frame structured illumination microscopy

Reduced-frame structured illumination microscopy (SIM) is attractive for live-cell imaging because it can improve temporal throughput and reduce photobleaching, but incomplete phase sampling makes reconstruction unstable and computationally demanding. Here we present URA-SIM, a unified reduced-acquisition framework that turns fixed reduced-frame measurements into pipeline- compatible raw stacks through model-consistent phase-domain completion. Instead of solving a large object-level inverse problem or replacing established SIM reconstruction, URA-SIM estimates the missing phase content on the low-dimensional phase-harmonic manifold required by the target modality and then delegates order separation and image formation to classical reconstruction pipeline. This design combines three practical advantages: fidelity from the SIM forward structure, lightweight online computation, and direct compatibility with existing reconstruction workflows. For 2D-SIM, URA-SIM uses the first-harmonic phase structure of three-phase SIM to estimate a shared zero-order field and complete missing phase samples by direction-wise harmonic fitting. On calibration and biological 2D-SIM data, reduced-frame reconstructions preserve resolvable structures and remain competitive on COS7 mitochondria comparison data. In live-cell COS7 mitochondria imaging, URA-SIM reconstructs each time point from five acquired raw frames and resolves mitochondrial cristae across different temporal sampling regimes. Experiments on 3D-SIM and nonlinear SIM further show that the same design principle can be transferred when the phase model and reconstruction-pipeline interface are adapted to the target modality. These results support URA-SIM as a transparent, model-consistent and computationally lightweight route from fixed reduced-frame acquisition to classical SIM reconstruction workflows.

physics.optics↗

arXiv2026

ANNLib: A Development Framework for Efficient Approximate Nearest Neighbor Search

Approximate Nearest Neighbor Search (ANNS) plays a pivotal role in modern deep learning pipelines. Recently, many ANNS systems have been proposed to either provide broad functionality or reach high performance. However, it is yet difficult to achieve both with minimal programming efforts. We propose ANNLib to address the gap. ANNLib is a library that provides a programming framework for achieving high performance and flexible functionality in ANNS systems, based on popular graph-based ANNS algorithms. We carefully decouple and independently optimize both the algorithm and the data structure components of an ANNS system. In addition, we integrate state-of-the-art algorithms and data structures into ANNLib as modules, along with our new designs. Users can choose combinations of components to implement sophisticated settings with high performance, such as filter search, fully dynamic updates, and historical queries on snapshots. Our experiments show that our new solution provides a simple interface for various applications and achieves comparable or even better performance than previous work, specifically for each application.

cs.LG↗

arXiv2026

Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents

Agent benchmarks are growing fast, but no single benchmark touches more than four or five of the dimensions that deployment exposes. This paper aggregates the largest coordinated deep-dive of one MCP-based industrial-agent benchmark to date: fourteen parallel implementation studies covering new asset classes (including a multi-modal visual extension), alternative orchestrations, retrieval strategies, reasoning modes, infrastructure optimizations, and evaluation-methodology probes. Consolidating those studies with seven prior agent benchmarks, we argue that aggregate-score leaderboards systematically underspecify deployed-agent evaluation. Rankings derived from aggregate scores do not transfer to out-of-distribution settings; recent public-to-hidden competition retrospectives provide direct empirical evidence of this rank instability. We propose ranking configurations by predictive validity, the correlation between in-sample and out-of-sample rank, rather than in-sample mean, and report a twelve-tier measurement apparatus that exposes the deployment-relevant dimensions HELM and its agent-era successors collapse. The position is operationalized through three falsifiable out-of-distribution criteria with explicit thresholds; existing evidence partly supports it but is too thin to confirm. We close with a pre-registered pilot design and a field-level vision for what the next generation of agentic benchmarks should report.

cs.AI↗

arXiv2026

HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic Manipulation

World Action Models (WAMs) have emerged as a new powerful paradigm for embodied intelligence, learning action-relevant visual dynamics that significantly enhance generalization and robustness. However, existing WAMs still struggle with task-relevant memory in long-horizon robotic manipulation. To address this, we present HiMem-WAM, a Hierarchical Memory-Gated WAM that integrates motion-centric latent actions, high-level skill latents, and boundary-triggered memory updates. Specifically, we develop a hierarchical latent action framework that jointly learns low-level motion and high-level skill latents, providing structured temporal abstraction. Meanwhile, a boundary-aware memory gate writes compact task states at predicted skill transitions, enabling causal inference without test-time generation of future video or optical flow estimation. Evaluated on LIBERO, LIBERO-PLUS, RMBench and real-world tasks, HiMem-WAM shows that hierarchical latents improve robustness under deployment perturbations, and the memory module substantially benefits memory-dependent long-horizon manipulation.

cs.RO↗

arXiv2026

Parallel Metric Skip Lists and Nearest Neighbor Search

The metric skip-list is a data structure designed for efficient nearest and $k$-nearest neighbor search in metric spaces. For many real-world datasets with reasonable distributions - specifically, those with a constant expansion rate - it supports $\tilde{O}(n)$ construction time and $O(k\log n)$ query time, where $n$ is the input size and $k$ is the number of nearest neighbors in queries. Notably, unlike alternative approaches, it does not require a bounded aspect ratio, making it more flexible for input data distributions. However, the inherently sequential nature of its original construction has, to our knowledge, precluded any existing parallel algorithm. In this paper, we present highly parallel and work-efficient algorithms for constructing metric skip lists. Under the assumption of a constant expansion rate, our approach achieves an expected work of $O(n \log n)$ and a polylogarithmic span with high probability. Our design is based on novel algorithmic insights that improves the sequential procedure, enabling a divide-and-conquer strategy that facilitates parallelism while maintaining efficiency. With our algorithms, we can also support improved bounds for relevant applications using nearest neighbor as building blocks, including bichromatic closest pair (BCP), density-based clustering, and $k$-NN graph construction, among others. To our knowledge, many of these results represent the first solutions to achieve both work efficiency and polylogarithmic span, relying solely on the assumption of a constant expansion rate.

cs.DS↗

arXiv2026

STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning

Federated graph learning (FGL) enables collaborative training on graph data across multiple clients. As graph data increasingly contain multimodal node attributes such as text and images, multimodal federated graph learning (MM-FGL) has become an important yet substantially harder setting. The key challenge is that clients from different modality domains may not share a common semantic space: even for the same concept, their local encoders can produce inconsistent representations before collaboration begins. This makes direct parameter coordination unreliable and further causes two downstream problems: forcing heterogeneous client representations into a naively shared semantic space may create false semantic agreement, and graph message passing may amplify residual inconsistency across neighborhoods. To address this issue, we propose \textbf{STAGE}, a protocol-first framework for MM-FGL. Instead of relying on direct parameter averaging, STAGE builds a shared semantic space that first translates heterogeneous multimodal features into comparable representations and then regulates how these representations propagate over local graph structures. In this way, STAGE not only improves cross-client semantic calibration, but also reduces the risk of inconsistency amplification during graph learning. Extensive experiments on 8 multimodal-attributed graphs across 5 graph-centric and modality-centric tasks show that STAGE consistently achieves state-of-the-art performance while reducing per-round communication payload.

cs.LG↗

arXiv2026

EmbodiedClaw: Conversational Workflow Execution for Embodied AI Development

Embodied AI research is increasingly moving beyond single-task, single-environment policy learning toward multi-task, multi-scene, and multi-model settings. This shift substantially increases the engineering overhead and development time required for stages such as evaluation environment construction, trajectory collection, model training, and evaluation. To address this challenge, we propose a new paradigm for embodied AI development in which users express goals and constraints through conversation, and the system automatically plans and executes the development workflow. We instantiate this paradigm with EmbodiedClaw, a conversational agent that turns high-frequency, high-cost embodied research activities, including environment creation and revision, benchmark transformation, trajectory synthesis, model evaluation, and asset expansion, into executable skills. Experiments on end-to-end workflow tasks, capability-specific evaluations, human researcher studies, and ablations show that EmbodiedClaw reduces manual engineering effort while improving executability, consistency, and reproducibility. These results suggest a shift from manual toolchains to conversationally executable workflows for embodied AI development.

cs.RO↗

arXiv2026

Synthesis4AD: Synthetic Anomalies are All You Need for 3D Anomaly Detection

Industrial 3D anomaly detection performance is fundamentally constrained by the scarcity and long-tailed distribution of abnormal samples. To address this challenge, we propose Synthesis4AD, an end-to-end paradigm that leverages large-scale, high-fidelity synthetic anomalies to learn more discriminative representations for 3D anomaly detection. At the core of Synthesis4AD is 3D-DefectStudio, a software platform built upon the controllable synthesis engine MPAS, which injects geometrically realistic defects guided by higher-dimensional support primitives while simultaneously generating accurate point-wise anomaly masks. Furthermore, Synthesis4AD incorporates a multimodal large language model (MLLM) to interpret product design information and automatically translate it into executable anomaly synthesis instructions, enabling scalable and knowledge-driven anomalous data generation. To improve the robustness and generalization of the downstream detector on unstructured point clouds, Synthesis4AD further introduces a training pipeline based on spatial-distribution normalization and geometry-faithful data augmentations, which alleviates the sensitivity of Point Transformer architectures to absolute coordinates and improves feature learning under realistic data variations. Extensive experiments demonstrate state-of-the-art performance on Real3D-AD, MulSen-AD, and a real-world industrial parts dataset. The proposed synthesis method MPAS and the interactive system 3D-DefectStudio will be publicly released at https://github.com/hustCYQ/Synthesis4AD.

cs.CV↗

arXiv2026

PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools

LLM agents are beginning to invoke industrial asset-management tools through the Model Context Protocol (MCP), yet whether they can act reliably on this substrate for safety-critical \emph{Prognostics and Health Management (PHM)} is unanswered. Prior benchmarks conflate protocol fluency with reasoning, instrumentation failures with agent failures, and tool use with tool retrieval. We introduce \textbf{PHMForge}, an evaluation environment that closes each conflation. PHMForge ships 99 SME-authored scenarios across eight industrial asset classes spanning rotating equipment, aero-engines, and lithium-ion cells, on public datasets including NASA PCoE, served through 39 MCP-native tools wrapping published PHM algorithms (C-MAPSS, ISO~10816, Arrhenius capacity-fade models, time-series foundation models). Krippendorff's $\alpha \in [0.74,\,0.82]$ on a 30-scenario stratified rotating-equipment/aero-engine sample; the battery extension is single-rater. Across three agentic frameworks and six LLM backbones, the strongest configuration reaches \textbf{80.8\% pass@1}, with the residual gap concentrated in orchestration and tool-sequencing errors. Crucially, an architectural ablation shows that replacing MCP execution with text-based Retrieval-Augmented Generation (RAG) over telemetry-equivalent evidence collapses Remaining Useful Life \emph{pass-all-3} from \textbf{100\% to 20\%} (5/5 vs.\ 1/5) on the battery class, exposing the structural limits of static retrieval for prognostic computation. Trajectory decomposition shows orchestration errors dominate failures across backbones, while schema-invalid tool calls concentrate in smaller open-weight models. Frontier LLMs are stronger at calling tools than at planning when to call them. PHMForge is open-sourced with deterministic evaluators, a public leaderboard, and a datasheet.

cs.AI↗

arXiv2026

AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models

Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The execution of complex multi-step behaviors in VLA models can be improved by robust instruction grounding, a critical component for effective control. However, current paradigms predominantly rely on coarse, high-level task instructions during supervised fine-tuning. This instruction grounding gap leaves models without explicit intermediate guidance, leading to severe compounding errors in long-horizon tasks. Therefore, bridging this instruction gap and providing scalable post-training for VLA models is urgent. To tackle this problem, we propose \method, the first subtask-aware VLA framework integrated with a scalable offline post-training pipeline. Our framework leverages a large language model to decompose high-level demonstrations into fine-grained atomic subtasks. This approach utilizes a pretrained predictive world model to score candidate action chunks against subtask goals in the latent space, mitigating error accumulation while significantly improving long-horizon robustness. Furthermore, this approach enables highly efficient Group Relative Policy Optimization without the prohibitive expenses associated with online rollouts on physical robots. Extensive simulations validate that our AtomVLA maintains strong robustness under perturbations. When evaluated against fundamental baseline models, it achieves an average success rate of 97.0\% on the LIBERO benchmark and 48.0\% on the LIBERO-PRO benchmark. Finally, experiments conducted in the real world using the Galaxea R1 Lite platform confirm its broad applicability across diverse tasks, especially long-horizon tasks. All datasets, checkpoints, and code will be released to the public domain following the acceptance of this work for future research.

cs.RO↗

arXiv2026

Parallel Dynamic Spatial Indexes

Maintaining spatial data (points in two or three dimensions) is crucial and has a wide range of applications, such as graphics, GIS, and robotics. To handle spatial data, many data structures, called spatial indexes, have been proposed, e.g. kd-trees, oct/quadtrees (also called Orth-trees), R-trees, and bounding volume hierarchies (BVHs). In real-world applications, spatial datasets tend to be highly dynamic, requiring batch updates of points with low latency. This calls for efficient parallel batch updates on spatial indexes. Unfortunately, there is very little work that achieves this. In this paper, we systematically study parallel spatial indexes, with a special focus on achieving high-performance update performance for highly dynamic workloads. We select two types of spatial indexes that are considered optimized for low-latency updates: Orth-tree and R-tree/BVH. We propose two data structures: the P-Orth tree, a parallel Orth-tree, and the SPaC-tree family, a parallel R-tree/BVH. Both the P-Orth tree and the SPaC-tree deliver superior performance in batch updates compared to existing parallel kd-trees and Orth-trees, while preserving better or competitive query performance relative to their corresponding Orth-tree and R-tree counterparts. We also present comprehensive experiments comparing the performance of various parallel spatial indexes and share our findings at the end of the paper.

cs.DB↗

arXiv2025

Parallel Joinable B-Trees in the Fork-Join I/O Model

Balanced search trees are widely used in computer science to efficiently maintain dynamic ordered data. To support efficient set operations (e.g., union, intersection, difference) using trees, the join-based framework is widely studied. This framework has received particular attention in the parallel setting, and has been shown to be effective in enabling simple and theoretically efficient set operations on trees. Despite the widespread adoption of parallel join-based trees, a major drawback of previous work on such data structures is the inefficiency of their input/output (I/O) access patterns. Some recent work (e.g., C-trees and PaC-trees) focused on more I/O-friendly implementations of these algorithms. Surprisingly, however, there have been no results on bounding the I/O-costs for these algorithms. It remains open whether these algorithms can provide tight, provable guarantees in I/O-costs on trees. This paper studies efficient parallel algorithms for set operations based on search tree algorithms using a join-based framework, with a special focus on achieving I/O efficiency in these algorithms. To better capture the I/O-efficiency in these algorithms in parallel, we introduce a new computational model, Fork-Join I/O Model, to measure the I/O costs in fork-join parallelism. This model measures the total block transfers (I/O work) and their critical path (I/O span). Under this model, we propose our new solution based on B-trees. Our parallel algorithm computes the union, intersection, and difference of two B-trees with $O(m \log_B(n/m))$ I/O work and $O(\log_B m \cdot \log_2 \log_B n + \log_B n)$ I/O span, where $n$ and $m \leq n$ are the sizes of the two trees, and $B$ is the block size.

cs.DS↗

arXiv2025

Leveraging Learning Bias for Noisy Anomaly Detection

This paper addresses the challenge of fully unsupervised image anomaly detection (FUIAD), where training data may contain unlabeled anomalies. Conventional methods assume anomaly-free training data, but real-world contamination leads models to absorb anomalies as normal, degrading detection performance. To mitigate this, we propose a two-stage framework that systematically exploits inherent learning bias in models. The learning bias stems from: (1) the statistical dominance of normal samples, driving models to prioritize learning stable normal patterns over sparse anomalies, and (2) feature-space divergence, where normal data exhibit high intra-class consistency while anomalies display high diversity, leading to unstable model responses. Leveraging the learning bias, stage 1 partitions the training set into subsets, trains sub-models, and aggregates cross-model anomaly scores to filter a purified dataset. Stage 2 trains the final detector on this dataset. Experiments on the Real-IAD benchmark demonstrate superior anomaly detection and localization performance under different noise conditions. Ablation studies further validate the framework's contamination resilience, emphasizing the critical role of learning bias exploitation. The model-agnostic design ensures compatibility with diverse unsupervised backbones, offering a practical solution for real-world scenarios with imperfect training data. Code is available at https://github.com/hustzhangyuxin/LLBNAD.

cs.CV↗

arXiv2025

Multi-View Reconstruction with Global Context for 3D Anomaly Detection

3D anomaly detection is critical in industrial quality inspection. While existing methods achieve notable progress, their performance degrades in high-precision 3D anomaly detection due to insufficient global information. To address this, we propose Multi-View Reconstruction (MVR), a method that losslessly converts high-resolution point clouds into multi-view images and employs a reconstruction-based anomaly detection framework to enhance global information learning. Extensive experiments demonstrate the effectiveness of MVR, achieving 89.6\% object-wise AU-ROC and 95.7\% point-wise AU-ROC on the Real3D-AD benchmark.

cs.CV↗

arXiv2025

Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial Defects

In industrial point cloud analysis, detecting subtle anomalies demands high-resolution spatial data, yet prevailing benchmarks emphasize low-resolution inputs. To address this disparity, we propose a scalable pipeline for generating realistic and subtle 3D anomalies. Employing this pipeline, we developed MiniShift, the inaugural high-resolution 3D anomaly detection dataset, encompassing 2,577 point clouds, each with 500,000 points and anomalies occupying less than 1\% of the total. We further introduce Simple3D, an efficient framework integrating Multi-scale Neighborhood Descriptors (MSND) and Local Feature Spatial Aggregation (LFSA) to capture intricate geometric details with minimal computational overhead, achieving real-time inference exceeding 20 fps. Extensive evaluations on MiniShift and established benchmarks demonstrate that Simple3D surpasses state-of-the-art methods in both accuracy and speed, highlighting the pivotal role of high-resolution data and effective feature aggregation in advancing practical 3D anomaly detection.

cs.CV↗

arXiv2025

Parallel Point-to-Point Shortest Paths and Batch Queries

We propose Orionet, efficient parallel implementations of Point-to-Point Shortest Paths (PPSP) queries using bidirectional search (BiDS) and other heuristics, with an additional focus on batch PPSP queries. We present a framework for parallel PPSP built on existing single-source shortest paths (SSSP) frameworks by incorporating pruning conditions. As a result, we develop efficient parallel PPSP algorithms based on early termination, bidirectional search, A$^*$ search, and bidirectional A$^*$ all with simple and efficient implementations. We extend our idea to batch PPSP queries, which are widely used in real-world scenarios. We first design a simple and flexible abstraction to represent the batch so PPSP can leverage the shared information of the batch. Orionet formalizes the batch as a query graph represented by edges between queried sources and targets. In this way, we directly extended our PPSP framework to batched queries in a simple and efficient way. We evaluate Orionet on both single and batch PPSP queries using various graph types and distance percentiles of queried pairs, and compare it against two baselines, GraphIt and MBQ. Both of them support parallel single PPSP and A$^*$ using unidirectional search. On 14 graphs we tested, on average, our bidirectional search is 2.9$\times$ faster than GraphIt, and 6.8$\times$ faster than MBQ. Our bidirectional A$^*$ is 4.4$\times$ and 6.2$\times$ faster than the A$^*$ in GraphIt and MBQ, respectively. For batched PPSP queries, we also provide in-depth experimental evaluation, and show that Orionet provides strong performance compared to the plain solutions.

cs.DC↗

arXiv2025

Visual Anomaly Detection under Complex View-Illumination Interplay: A Large-Scale Benchmark

The practical deployment of Visual Anomaly Detection (VAD) systems is hindered by their sensitivity to real-world imaging variations, particularly the complex interplay between viewpoint and illumination which drastically alters defect visibility. Current benchmarks largely overlook this critical challenge. We introduce Multi-View Multi-Illumination Anomaly Detection (M2AD), a new large-scale benchmark comprising 119,880 high-resolution images designed explicitly to probe VAD robustness under such interacting conditions. By systematically capturing 999 specimens across 10 categories using 12 synchronized views and 10 illumination settings (120 configurations total), M2AD enables rigorous evaluation. We establish two evaluation protocols: M2AD-Synergy tests the ability to fuse information across diverse configurations, and M2AD-Invariant measures single-image robustness against realistic view-illumination effects. Our extensive benchmarking shows that state-of-the-art VAD methods struggle significantly on M2AD, demonstrating the profound challenge posed by view-illumination interplay. This benchmark serves as an essential tool for developing and validating VAD methods capable of overcoming real-world complexities. Our full dataset and test suite will be released at https://hustcyq.github.io/M2AD to facilitate the field.

cs.CV↗

arXiv2025

New Algorithms for Incremental Minimum Spanning Trees and Temporal Graph Applications

Processing graphs with temporal information (the temporal graphs) has become increasingly important in the real world. In this paper, we study efficient solutions to temporal graph applications using new algorithms for Incremental Minimum Spanning Trees (MST). The first contribution of this work is to formally discuss how a broad set of setting-problem combinations of temporal graph processing can be solved using incremental MST, along with their theoretical guarantees. Despite the importance of the problem, we observe a gap between theory and practice for efficient incremental MST algorithms. While many classic data structures, such as the link-cut tree, provide strong bounds for incremental MST, their performance is limited in practice. Meanwhile, existing practical solutions used in applications do not have any non-trivial theoretical guarantees. Our second and main contribution includes new algorithms for incremental MST that are efficient both in theory and in practice. Our new data structure, the AM-tree, achieves the same theoretical bound as the link-cut tree for temporal graph processing and shows strong performance in practice. In our experiments, the AM-tree has competitive or better performance than existing practical solutions due to theoretical guarantees, and can be significantly faster than the link-cut tree (7.8-11x in updates and 7.7-13.7x in queries).

cs.DS↗