arXiv subjects

Min Yu

Publications and source records attributed to Min Yu.

At least 19 recordsLinked to original sources

arXiv2026

Magnetically Self-Sealed MR Haptic Actuator With PWM-Based Excitation and High-Fidelity Torque Control

Accurate and stable torque rendering is essential for safe and perceptive human--machine interaction. Magnetorheological fluid (MRF)-based actuators offer a compact and rapidly controllable solution for haptic feedback, but their practical implementation requires reliable fluid sealing, low-hysteresis excitation, accurate torque control, and stable long-duration operation. This article presents an integrated MRF haptic system featuring a compact magnetically self-sealed rotary actuator, low-hysteresis PWM operation, high-fidelity model-based torque rendering, and stable performance during long-time operation. Magnetostatic simulation guides the arrangement of magnetic and nonmagnetic materials to focus flux in the multidisk torque and permanent-magnet sealing regions, enabling a maximum 600 N$\cdot$mm/A output. Experiments show that higher PWM frequencies reduce hysteresis and improve repeatability. At 10 kHz, the response is represented by a nonlinear model that varies with the direction and speed of torque change. The real-time controller combines feedforward, hysteresis compensation, PI feedback, and sliding-mode correction. Compared with PID, it reduces square-wave overshoot, undershoot, and steady-state RMSE by 77.4\%, 61.9\%, and 68.3\%, respectively. It tracks sinusoidal and biomechanics-model-based references, and a 1.5-h test shows only a 2.5 $^\circ$C rise near the coil with no clear tracking loss. This high-fidelity torque rendering will fundamentally transform human--robot collaboration by making interactions safer, more efficient, and more intuitive.

cs.RO↗

arXiv2026

GoGoTB: Agentic RTL Verification with Specification-Grounded Coverage Closure

Functional verification dominates integrated circuit (IC) front-end engineering effort, and a single missed bug that escapes to silicon can trigger a costly respin. Recent large language models (LLMs) offer new opportunities to automate this process, yet existing LLM-based approaches generate each component through independent single-turn calls with no shared context, leaving interface mismatches undetected and reported coverage disconnected from specification requirements. To address these challenges, we present GoGoTB, an agentic framework that achieves end-to-end verification closure through three subsystems: an agentic execution control layer, an evolvable knowledge system, and specification-grounded coverage closure. The execution control layer separates deterministic enforcement from LLM reasoning at every tool and stage boundary. The knowledge system dispatches methodology and design-specific expertise on demand. The coverage framework anchors every bin to a named specification behavior so that each residual gap has a diagnosable root cause and a targeted remedy. Tested on 8 register transfer level (RTL) designs without any human intervention, GoGoTB achieves 100\% environment generation success and averages 98.4\% line, 97.2\% branch, 97.0\% toggle, and 83.2\% functional coverage. No prior work successfully generates a complete verification environment or achieves meaningful coverage on the same benchmarks.

cs.AI↗

arXiv2026

Memory Layer: Train the In-Model Cache for Recommendation Models

Early ranking stages in recommendation systems precompute item embeddings and cache them in-model for scoring within strict latency constraints. Because this cache exists only at serving time, outside the training loop, training and serving use different item representations, a structural discrepancy that limits quality and adds operational fragility. We show that co-designing the training and serving paths removes this representation discrepancy at its source. We introduce the memory layer, an in-model key-value embedding cache co-trained with the model: the item tower writes embeddings during training and the model reads them at serving, one source of truth for item representations by construction. Always-on embeddings cover items not yet cached, so every item receives a prediction, and the design consolidates three separate trainer-to-predictor update paths into a single self-contained pipeline. Deployed in production on Instagram Reels, the memory layer raises prediction coverage from 96% to 100%, improves embedding freshness from $O(5\text{ min})$ to $O(20\text{ s})$, and narrows the training-serving Normalized Entropy (NE) gap by up to 86%, yielding over $2\times$ recall for the freshest content and a 5-6% cold start engagement lift. Because embeddings are produced during training, the system needs no separate bulk-evaluation or publish-time recomputation, cutting training-and-publish computational cost by 30% at neutral serving computational cost.

cs.IR↗

arXiv2026

Repurposing Adversarial Perturbations for Continual Learning: From Defense to Active Alignment

In dynamic environments, large language models need to keep adapting to new tasks, but continual learning often suffers from forgetting, limited transfer, and vulnerability to adversarial perturbations. To address this, we present AdvCL, which repurposes adversarial perturbations as a geometric control signal for stable continual adaptation. AdvCL combines three plug-in modules: Intra-Smooth promotes local smoothness via small adversarial perturbations; Proto-Clip uses similarity clipping to prevent excessive alignment to current task prototype; and Inter-Align applies directional alignment toward previous task prototype to reduce representational gaps. Experiments show consistent gains in both standard performance and robustness, with lower forgetting and stronger transfer. We further analyze key mechanisms by quantifying the sensitivity of Intra-Smooth to perturbation settings and the effect of Inter-Align on task similarity and geometric distance. In summary, the modules provide complementary gains when combined, and each can also be integrated individually into diverse CL paradigms, including replay, regularization, and dynamic architectures, thereby offering a geometric control mechanism for continual learning.

cs.LG↗

arXiv2025

SilverTorch: A Unified Model-based System to Democratize Large-Scale Recommendation on GPUs

Serving deep learning based recommendation models (DLRM) at scale is challenging. Existing approaches rely on dedicated ANN indexing and filtering services on CPUs, suffering from non-negligible costs and missing co-design opportunities. Such inefficiency makes them difficult to support complex model architectures, such as learned similarities and multi-task retrieval. In this paper, we present SilverTorch, a model-based serving system that brings all components into one unified model. It unifies model serving by replacing standalone indexing and filtering services with model layers. We propose a model-based GPU Bloom index for feature filtering and a fused Int8 ANN kernel for nearest neighbor search. Through co-design of the ANN search and feature filtering, we reduce GPU memory usage and eliminate computation. Benefiting from this design, we scale up retrieval by introducing an OverArch scoring layer and a multi-task retrieval with a Value Model to aggregate scores. These advancements improve the retrieval accuracy and enable future studies for serving more complex models. Our evaluation on industry-scale datasets show that SilverTorch achieves up to 23.7\times higher throughput compared to the state-of-the-art approaches. We also demonstrate that SilverTorch solution is 13.35\times more cost-efficient than CPU-based solution while improving accuracy via serving more complex models. SilverTorch is deployed at scale, serving hundreds of models online and supporting recommendation for diverse applications.

cs.IR↗

arXiv2025

An Automatic Detection Method for Hematoma Features in Placental Abruption Ultrasound Images Based on Few-Shot Learning

Placental abruption is a severe complication during pregnancy, and its early accurate diagnosis is crucial for ensuring maternal and fetal safety. Traditional ultrasound diagnostic methods heavily rely on physician experience, leading to issues such as subjective bias and diagnostic inconsistencies. This paper proposes an improved model, EH-YOLOv11n (Enhanced Hemorrhage-YOLOv11n), based on small-sample learning, aiming to achieve automatic detection of hematoma features in placental ultrasound images. The model enhances performance through multidimensional optimization: it integrates wavelet convolution and coordinate convolution to strengthen frequency and spatial feature extraction; incorporates a cascaded group attention mechanism to suppress ultrasound artifacts and occlusion interference, thereby improving bounding box localization accuracy. Experimental results demonstrate a detection accuracy of 78%, representing a 2.5% improvement over YOLOv11n and a 13.7% increase over YOLOv8. The model exhibits significant superiority in precision-recall curves, confidence scores, and occlusion scenarios. Combining high accuracy with real-time processing, this model provides a reliable solution for computer-aided diagnosis of placental abruption, holding significant clinical application value.

cs.CV↗

arXiv2025

How Auxiliary Reasoning Unleashes GUI Grounding in VLMs

Graphical user interface (GUI) grounding is a fundamental task for building GUI agents. However, general vision-language models (VLMs) struggle with this task due to a lack of specific optimization. We identify a key gap in this paper: while VLMs exhibit significant latent grounding potential, as demonstrated by their performance measured by Pointing Game, they underperform when tasked with outputting explicit coordinates. To address this discrepancy and bypass the high data and annotation costs of current fine-tuning approaches, we propose three zero-shot auxiliary reasoning methods. By providing explicit spatial cues such as axes, grids and labeled intersections as part of the input image, these methods enable VLMs to better articulate their implicit spatial understanding capabilities. We evaluate these methods on four GUI grounding benchmarks across seven open-source and proprietary VLMs. Experimental results show substantial gains from auxiliary reasoning. Mark-Grid Scaffold boosts Gemini-3.1-Pro from 11.72\% under direct inference to 95.20\% on ScreenSpot-v2, achieves state-of-the-art performance on ScreenSpot, and approaches the strongest fine-tuned methods on ScreenSpot-v2 and UI-I2E-Bench. Our code is available at https://github.com/liweim/AuxiliaryReasoning.

cs.CV↗

arXiv2025

SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection

Detection of face forgery videos remains a formidable challenge in the field of digital forensics, especially the generalization to unseen datasets and common perturbations. In this paper, we tackle this issue by leveraging the synergy between audio and visual speech elements, embarking on a novel approach through audio-visual speech representation learning. Our work is motivated by the finding that audio signals, enriched with speech content, can provide precise information effectively reflecting facial movements. To this end, we first learn precise audio-visual speech representations on real videos via a self-supervised masked prediction task, which encodes both local and global semantic information simultaneously. Then, the derived model is directly transferred to the forgery detection task. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods in terms of cross-dataset generalization and robustness, without the participation of any fake video in model training. Code is available at https://github.com/Eleven4AI/SpeechForensics.

cs.CV↗

arXiv2025

Dynamic film thickness measurement in a rolling bearing using numerical elastohydrodynamic-acoustic modelling to interpret reflected ultrasound data

The thickness of the lubricating film plays a vital role in the operational efficiency and reliability of rolling bearings. Ultrasonic reflection techniques offer a promising non-invasive approach for in situ evaluation of lubricant films.However, accurately identifying the central film thickness remains challenging due to several complex factors, including dynamic fluctuations, localized elastic deformation, cavitation effects, and variations in oil supply. This study presents a comprehensive theoretical and numerical framework to elucidate the influence of these factors on ultrasonic wave propagation in lubricated contacts. Numerical simulations considering elastohydrodynamic lubrication (EHL) regime and cavitation-induced effects are carried out to obtain the surface deformation profiles and the cavitation regions. Subsequently, high-fidelity acoustic simulations are conducted to interpret reflected ultrasound data.As main results, the EHL leads to a "double-peak with central valley" pattern in the reflection coefficient distribution. While the cavitation causes the central valley to shift toward the inlet region and increases the reflection coefficient.Accordingly, the central film thickness is extracted from the distribution of the reflection coefficient under different operating conditions. Experimental validation using both glass-oil-steel and steel-oil-steel bearing setups confirms the effectiveness of the proposed method. The high-resolution fluorescence measurement adopted in the glass-oil-steel configuration validates the simulation of the reflection coefficient distribution. Furthermore, the theoretical EHL calculations are employed with the steel-oil-steel configuration for validation of the measurement accuracy of central oil film thickness.

physics.ins-det↗

arXiv2025

Intrinsic static/dynamic triboelectric pressure sensor for continuous and event-triggered control

Conventional pressure sensors often integrate two distinct mechanisms to detect static and dynamic stimuli, hindering the development of high fidelity human-machine interfaces. Here, we present an intrinsic static/dynamic triboelectric sensor (iSD Sensor) capable of reliably perceiving both continuous static pressure and transient mechanical shocks through a DC/AC signal decoupling strategy. By pairing hydrophobic expanded polytetrafluoroethylene (ePTFE) with elastic conductive sponge, a pressure-adaptive triboelectric interface is formed, where microscale and large-scale separations enable static and dynamic pressure sensing, respectively. Furthermore, by employing a charge excitation strategy, the device delivers enhanced voltage outputs over 25X in static and 15X in dynamic modes. Combined with a 3D gradient conductive sponge structure, the sensor achieves multi-region sensitivities of 34.7 V/kPa (static) and 48.4 V/kPa (dynamic) under low pressure (less than 1.8 kPa), and a detection limit as low as 6.13 Pa. By perceiving continuous static pressure and transient shocks applied by the human hand, the iSD Sensor enables robotic arm control via proportional grasping and dynamic, trigger-based sign language communication. This work advances high-sensitivity, self-powered pressure sensors toward intelligent, closed-loop human-machine interaction.

cs.RO↗

arXiv2024

Multi-Roller Structure Triboelectric Nanogenerator for Enhanced Water Wave Energy Harvesting and Energy Management

Wave energy harvesting is critical for advancing the development and utilization of marine resources. In this study, we present a novel multi-roller structure triboelectric nanogenerator (MR-TENG) designed specifically for efficient water wave energy harvesting. The MR-TENG leverages a coupled multi-roller design to significantly enhance its energy harvesting capabilities. The triboelectric layers are composed of polytetrafluoroethylene (PTFE) film and paper, with a grid copper electrode serving as the conductive element. Through an optimized energy output strategy, a single MR-TENG is capable of generating 602.045 {\mu}J of electrical energy within 100 s. The device achieves a short-circuit current (Isc) of approximately 2.06 {\mu}A and an open-circuit voltage (Voc) of around 166 V. We further investigate the impact of different connection modes, including parallel and series configurations, on the performance of MR-TENG arrays. Notably, the electrical energy produced by the MR-TENG array is sufficient to power 40 blue commercial light-emitting diodes (LEDs). This research not only introduces a versatile optimization approach and energy management strategy for roller-structured TENGs but also contributes significantly to the advancement of ocean-based TENG technology.

physics.app-ph↗

arXiv2024

Highly robust and efficient metal-free water cup solid-liquid triboelectric generator for mechanical energy harvesting and ethanol detection

Recently, low-frequency mechanical energy harvesters based on solid-liquid contact electrification have garnered widespread attention for their unique advantages in wear resistance, high charge transfer efficiency, and novel insights into electron-ion interactions at the solid-liquid interface, particularly in material identification. Hence, we designed an robust and efficient water cup triboelectric nanogenerator (WC-TENG) that only uses ordinary drinking water and plastic water cups as primary materials, achieving high-efficiency power output while eliminating the need for metal electrodes and effectively addressing the issue of corrosion in generator components. Experimental results indicate that, at an operating frequency of 2 Hz, the WC-TENG generates an open-circuit voltage (Voc) of 249.71 V, a short-circuit current (Isc) of 4.21 uA, and a transferred charge (Qsc) of 188.85 nC. The WC-TENG demonstrates long-term stability and reliability, maintaining stable voltage output over 1500 s. Moreover, the WC-TENG maintains stable performance under high humidity conditions, and its output enhances with increasing temperature, underscoring its robustness and adaptability for diverse environmental applications. Furthermore, the introduction of ethanol disrupts the potential balance at the solid-liquid interface by impeding electron transfer and reducing the WC-TENG's electrical output, but as the ethanol volatilizes, the device gradually returns to its original potential state, demonstrating its potential as a selective ethanol sensor. This design not only advances the development of corrosion-resistant, high-performance energy harvesters but also opens up new possibilities for low-cost, sustainable, and environmentally adaptable sensing technologies.

physics.app-ph↗

arXiv2024

GLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarization

Pre-trained language models are increasingly being used in multi-document summarization tasks. However, these models need large-scale corpora for pre-training and are domain-dependent. Other non-neural unsupervised summarization approaches mostly rely on key sentence extraction, which can lead to information loss. To address these challenges, we propose a lightweight yet effective unsupervised approach called GLIMMER: a Graph and LexIcal features based unsupervised Multi-docuMEnt summaRization approach. It first constructs a sentence graph from the source documents, then automatically identifies semantic clusters by mining low-level features from raw texts, thereby improving intra-cluster correlation and the fluency of generated sentences. Finally, it summarizes clusters into natural sentences. Experiments conducted on Multi-News, Multi-XScience and DUC-2004 demonstrate that our approach outperforms existing unsupervised approaches. Furthermore, it surpasses state-of-the-art pre-trained multi-document summarization models (e.g. PEGASUS and PRIMERA) under zero-shot settings in terms of ROUGE scores. Additionally, human evaluations indicate that summaries generated by GLIMMER achieve high readability and informativeness scores. Our code is available at https://github.com/Oswald1997/GLIMMER.

cs.CL↗

arXiv2024

LMI-based robust model predictive control for a quarter car with series active variable geometry suspension

This paper proposes a robust model predictive control-based solution for the recently introduced series active variable geometry suspension (SAVGS) to improve the ride comfort and road holding of a quarter car. In order to close the gap between the nonlinear multi-body SAVGS model and its linear equivalent, a new uncertain system characterization is proposed that captures unmodeled dynamics, parameter variation, and external disturbances. Based on the newly proposed linear uncertain model for the quarter car SAVGS system, a constrained optimal control problem (OCP) is presented in the form of a linear matrix inequality (LMI) optimization. More specifically, utilizing semidefinite relaxation techniques a state-feedback robust model predictive control (RMPC) scheme is presented and integrated with the nonlinear multi-body SAVGS model, where state-feedback gain and control perturbation are computed online to optimise performance, while physical and design constraints are preserved. Numerical simulation results with different ISO-defined road events demonstrate the robustness and significant performance improvement in terms of ride comfort and road holding of the proposed approach, as compared to the conventional passive suspension, as well as, to actively controlled SAVGS by a previously developed conventional H-infinity control scheme.

eess.SY↗

arXiv2023

How to Generate Popular Post Headlines on Social Media?

Posts, as important containers of user-generated-content pieces on social media, are of tremendous social influence and commercial value. As an integral components of a post, the headline has a decisive contribution to the post's popularity. However, current mainstream method for headline generation is still manually writing, which is unstable and requires extensive human effort. This drives us to explore a novel research question: Can we automate the generation of popular headlines on social media? We collect more than 1 million posts of 42,447 celebrities from public data of Xiaohongshu, which is a well-known social media platform in China. We then conduct careful observations on the headlines of these posts. Observation results demonstrate that trends and personal styles are widespread in headlines on social medias and have significant contribution to posts's popularity. Motivated by these insights, we present MEBART, which combines Multiple preference-Extractors with Bidirectional and Auto-Regressive Transformers (BART), capturing trends and personal styles to generate popular headlines on social medias. We perform extensive experiments on real-world datasets and achieve state-of-the-art performance compared with several advanced baselines. In addition, ablation and case studies demonstrate that MEBART advances in capturing trends and personal styles.

cs.AI↗

arXiv2023

Using electrical impedance spectroscopy to identify equivalent circuit models of lubricated contacts with complex geometry: in-situ application to mini traction machine

Electrical contact resistance or capacitance as measured between a lubricated contact has been used in tribometers, partially reflecting the lubrication condition. In contrast, the electrical impedance provides rich information of magnitude and phase, which can be interpreted using equivalent circuit models, enabling more comprehensive measurements, including the variation of lubricant film thickness and the asperity (metal to metal) contact area. An accurate circuit model of the lubricated contact is critical as needed for the electrical impedance analysis. However, existing circuit models are hand derived and suited to interfaces with simple geometry, such as parallel plates, concentric and eccentric cylinders. Circuit model identification of lubricated contacts with complex geometry is challenging. This work takes the ball-on-disc lubricated contact in a Mini Traction Machine (MTM) as an example, where screws on the ball, grooves on the disc, and contact close to the disc edge make the overall interface geometry complicated. The electrical impedance spectroscopy (EIS) is used to capture its frequency response, with a group of load, speed, and temperature varied and tested separately. The results enable an identification of equivalent circuit models by fitting parallel resistor-capacitor models, the dependence on the oil film thickness is further calibrated using a high-accuracy optical interferometry, which is operated under the same lubrication condition as in the MTM. Overall, the proposed method is applicable to general lubricated interfaces for the identification of equivalent circuit models, which in turn facilitates in-situ tribo-contacts with electric impedance measurement of oil film thickness. It does not need transparent materials as optical techniques do, or structural modifications for piezoelectric sensor mounting as ultrasound techniques do.

eess.SP↗

arXiv2023

Two-photon-transition superadiabatic passage in an nitrogen-vacancy center in diamond

Reaching a given target quantum state with high fidelity and fast operation speed close to the quantum limit represents an important goal in quantum information science. Here, we experimentally demonstrate superadiabatic quantum driving to achieve population transfer in a three-level solid-state spin system. Starting from traditional stimulated Raman adiabatic passage (STIRAP), our approach implements superadiabatic corrections to the STIRAP Hamiltonians with several paradigmatic pulse shapes. It requires no need of intense microwave pulses or long transfer times and shows enhanced robustness over pulse imperfections. These results might provide a useful tool for quantum information processing and coherent manipulations of quantum systems.

quant-ph↗

arXiv2023

Accelerated quantum control in a three-level system by jumping along the geodesics

In a solid-state spin system, we experimentally demonstrate a protocol for quantum-state population transfer with an improved efficiency compared to traditional stimulated Raman adiabatic passage (STIRAP). Using the ground-state triplet of the nitrogen-vacancy center in diamond, we show that the required evolution time for high-fidelity state transfer can be reduced by almost one order of magnitude. Furthermore, we establish an improved robustness against frequency detuning caused by magnetic noise as compared to STIRAP. These results provide a powerful tool for coherent spin manipulation in the context of quantum sensing and quantum computation.

quant-ph↗