arXiv subjects

Yincheng Jin

Publications and source records attributed to Yincheng Jin.

8 recordsLinked to original sources

arXiv2026

OmniCAD: A Large-Scale Benchmark for 3D Spatial Reasoning in Robotics Assemblies

Recent vision-language models (VLMs) show strong capabilities in robotic perception and spatial reasoning, yet their ability to reason about complex mechanical assemblies remains underexplored. We introduce OmniCAD, a large-scale benchmark for assembly-aware 3D spatial reasoning across diverse industrial systems, including robotic mechanisms, automotive components, aerospace structures, and agricultural machinery. OmniCAD contains 25k mechanical assemblies, with an average of 12 parts per assembly and 21 types of mate relationships. Each assembly includes a human-verified ground-truth 3D model and renderings from 20 viewpoints. The benchmark evaluates three capabilities: (1) component-level 3D spatial reasoning, requiring prediction of part positions and orientations; (2) part-to-part relational reasoning, requiring identification of mating relationships and assembly constraints; and (3) tool-augmented agentic reasoning, where models iteratively select viewpoints, inspect visual evidence, and refine predictions. Experiments show that current VLMs struggle with industrial assembly reasoning, often producing inaccurate poses, invalid mating relationships, part interpenetration, and degraded performance as assembly complexity increases. We will open-source the benchmark, evaluation code, and tool interfaces to support research on accurate, physically valid, and scalable 3D assembly reasoning.

cs.CV↗

arXiv2026

OmniMech: All-in-one Multimodal Mechanical Benchmark for 3D Reconstruction

Recent vision-language models (VLMs) can generate executable CAD programs from images, but existing methods mainly target coarse, general-purpose 3D objects and rarely address the fine-grained geometry and millimeter-level tolerances required in industrial mechanical design. We introduce OmniMech, the first million-scale benchmark for evaluating VLMs on executable CAD generation from industrial manufacturing data. OmniMech contains more than 251,000 fully dimensioned and toleranced 2D orthographic drawings, paired with native CAD models, multi-view renderings, mesh, STEP and B-rep representations, and rich semantic annotations. The benchmark includes four tasks: (1) parametric CAD program synthesis from engineering drawings; (2) diagram-to-3D reasoning for geometrically and structurally consistent reconstruction; (3) annotation-grounded reasoning over dimensions, symbols, feature callouts, and manufacturing constraints; and (4) tool-augmented agentic reasoning using visualization, measurement, CAD execution, and verification tools. Experiments show that current VLMs and CAD-specialized models still struggle with executable program synthesis, fine-grained 3D reconstruction, and reliable enforcement of dimensions and tolerances. We will release the benchmark data, evaluation code, and tool interfaces to support future research.

cs.CV↗

arXiv2026

OmniRouting: A Semantic-Coupled Multimodal Benchmark for Constraint-Aware Spatial Reasoning in PCB Routing

Recent large language models (LLMs) have demonstrated remarkable progress in constraint-aware navigation, maze reasoning, and graph reasoning. However, their ability to reason about complex routing problems under strict geometric, topological, and electrical constraints remains largely unexplored, despite routing being one of the most challenging and critical stages of electronic design automation (EDA). To bridge this gap, we introduce OmniRouting, the first large-scale benchmark designed to evaluate LLMs on printed-circuit-board (PCB) routing reasoning under real-world industrial design-rule, manufacturability, and connectivity constraints. OmniRouting contains 1,681 industrial-grade schematic-coupled PCB designs, including board geometries, routable component placements by human engineers, footprints, pad locations, netlists, stackup information, and routing constraints. The benchmark comprises four tasks: (1) geometric routing reasoning, generating physically valid copper traces, vias, and layer assignments to connect circuit nets within constrained board regions; (2) design-rule-aware routing reasoning, producing routable layouts that satisfy clearance, trace-width, via, obstacle-avoidance, and board-boundary constraints; (3) electrical functionality reasoning, preserving schematic-specified connectivity while reasoning over net names and functional roles to produce electrically correct routing; and (4) tool-augmented agentic routing, leveraging external tools for tasks (1)-(3). Our results reveal substantial limitations of current LMMs in PCB routing, including weak path-planning capabilities, poor adherence to design-rule constraints, and inconsistent preservation of electrical functionality. We will open-source all benchmark data, evaluation code, and tool interfaces to facilitate future research.

cs.CV↗

arXiv2026

OmniSch: A Multimodal PCB Schematic Benchmark For Structured Diagram Visual Reasoning

Recent large multimodal models (LMMs) have made rapid progress in visual grounding, document understanding, and diagram reasoning tasks. However, their ability to convert Printed Circuit Board (PCB) schematic diagrams into machine-readable spatially weighted netlist graphs, jointly capturing component attributes, connectivity, and geometry, remains largely underexplored, despite such graph representations are the backbone of practical electronic design automation (EDA) workflows. To bridge this gap, we introduce OmniSch, the first comprehensive benchmark designed to assess LMMs on schematic understanding and spatial netlist graph construction. OmniSch contains 1,854 real-world schematic diagrams and includes four tasks: (1) visual grounding for schematic entities, with 109.9K grounded instances aligning 423.4K diagram semantic labels to their visual regions; (2) diagram-to-graph reasoning, understanding topological relationship among diagram elements; (3) geometric reasoning, constructing layout-dependent weights for each connection; and (4) tool-augmented agentic reasoning for visual search, invoking external tools to accomplish (1)-(3). Our results reveal substantial gaps of current LMMs in interpreting schematic engineering artifacts, including unreliable fine-grained grounding, brittle layout-to-graph parsing, inconsistent global connectivity reasoning and inefficient visual exploration.

cs.CV↗

arXiv2025

IMUFace: Towards Always-On 3D Facial Reconstruction via Earphone Inertial Sensing

The potential of facial expression reconstruction technology is significant, with applications in various fields such as human-computer interaction, affective computing, and virtual reality. Recent studies have proposed using ear-worn devices for facial expression reconstruction to address the environmental limitations and privacy concerns associated with traditional camera-based methods. However, these approaches still require improvements in terms of aesthetics and power consumption. This paper introduces a system called IMUFace. It uses inertial measurement units (IMUs) embedded in wireless earphones to detect subtle ear movements caused by facial muscle activities, allowing for covert and low-power facial reconstruction. A user study involving 12 participants was conducted, and a deep learning model named IMUTwinTrans was proposed. The results show that IMUFace can accurately predict users' facial landmarks with a precision of 2.21 mm, using only five minutes of training data. The predicted landmarks can be utilized to reconstruct a three-dimensional facial model. IMUFace operates at a sampling rate of 30 Hz with a relatively low power consumption of 58 mW. The findings presented in this study demonstrate the real-world applicability of IMUFace and highlight potential directions for further research to facilitate its practical adoption.

cs.HC↗

arXiv2025

A Large Language Model Powered Integrated Circuit Footprint Geometry Understanding

Printed-Circuit-board (PCB) footprint geometry labeling of integrated circuits (IC) is essential in defining the physical interface between components and the PCB layout, requiring exceptional visual perception proficiency. However, due to the unstructured footprint drawing and abstract diagram annotations, automated parsing and accurate footprint geometry modeling remain highly challenging. Despite its importance, no methods currently exist for automated package geometry labeling directly from IC mechanical drawings. In this paper, we first investigate the visual perception performance of Large Multimodal Models (LMMs) when solving IC footprint geometry understanding. Our findings reveal that current LMMs severely suffer from inaccurate geometric perception, which hinders their performance in solving the footprint geometry labeling problem. To address these limitations, we propose LLM4-IC8K, a novel framework that treats IC mechanical drawings as images and leverages LLMs for structured geometric interpretation. To mimic the step-by-step reasoning approach used by human engineers, LLM4-IC8K addresses three sub-tasks: perceiving the number of pins, computing the center coordinates of each pin, and estimating the dimensions of individual pins. We present a two-stage framework that first trains LMMs on synthetically generated IC footprint diagrams to learn fundamental geometric reasoning and then fine-tunes them on real-world datasheet drawings to enhance robustness and accuracy in practical scenarios. To support this, we introduce ICGeo8K, a multi-modal dataset with 8,608 labeled samples, including 4138 hand-crafted IC footprint samples and 4470 synthetically generated samples. Extensive experiments demonstrate that our model outperforms state-of-the-art LMMs on the proposed benchmark.

cs.CV↗

arXiv2022

EEGLog: Lifelogging EEG Data When You Listen to Music

Self-tracking has been long discussed, which can monitor daily activities and help users to recall previous experiences. Such data-capturing technique is no longer limited to photos, text messages, or personal diaries in recent years. With the development of wearable EEG devices, we introduce a novel modality of logging EEG data while listening to music, and bring up the idea of the neural-centric way of life with the designed data analysis application named EEGLog. Four consumer-grade wearable EEG devices are explored by collecting EEG data from 24 participants. Three modules are introduced in EEGLog, including the summary module of EEG data, emotion reports, music listening activities, and memorial moments, the emotion detection module, and the music recommendation module. Feedback from interviews about using EEG devices and EEGLog were obtained and analyzed for future EEG logging development.

cs.HC↗

arXiv2022

BEAMERS: Brain-Engaged, Active Music-based Emotion Regulation System

With the increasing demands of emotion comprehension and regulation in our daily life, a customized music-based emotion regulation system is introduced by employing current EEG information and song features, which predicts users' emotion variation in the valence-arousal model before recommending music. The work shows that: (1) a novel music-based emotion regulation system with a commercial EEG device is designed without employing deterministic emotion recognition models for daily usage; (2) the system considers users' variant emotions towards the same song, and by which calculate user's emotion instability and it is in accordance with Big Five Personality Test; (3) the system supports different emotion regulation styles with users' designation of desired emotion variation, and achieves an accuracy of over $0.85$ with 2-seconds EEG data; (4) people feel easier to report their emotion variation comparing with absolute emotional states, and would accept a more delicate music recommendation system for emotion regulation according to the questionnaire.

cs.HC↗