Searcharxiv⌕ Search

arXiv subjects

Yitong Chen

Publications and source records attributed to Yitong Chen.

At least 37 records · Page 2Linked to original sources
arXiv2026

CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization

Autoregressive (AR) language models rely on causal tokenization, but extending this paradigm to vision remains non-trivial. Current visual tokenizers either flatten 2D patches into non-causal sequences or enforce heuristic orderings that misalign with the "next-token prediction" pattern. Recent diffusion autoencoders similarly fall short: conditioning the decoder on all tokens lacks causality, while applying nested dropout mechanism introduces imbalance. To address these challenges, we present CaTok, a 1D causal image tokenizer with a MeanFlow decoder. By selecting tokens over time intervals and binding them to the MeanFlow objective, as illustrated in Fig. 1, CaTok learns causal 1D representations that support both fast one-step generation and high-fidelity multi-step sampling, while naturally capturing diverse visual concepts across token intervals. To further stabilize and accelerate training, we propose a straightforward regularization REPA-A, which aligns encoder features with Vision Foundation Models (VFMs). Experiments demonstrate that CaTok achieves state-of-the-art results on ImageNet reconstruction, reaching 0.75 FID, 22.53 PSNR and 0.674 SSIM with fewer training epochs, and the AR model attains performance comparable to leading approaches.

cs.CV↗
arXiv2026

Scalable Solar-Blind Imaging Enabled by Single-Crystalline Beta-Ga2O3 Membranes on Silicon Backplanes

Ultrawide-bandgap semiconductors are attractive for solar-blind ultraviolet (UV) detection owing to their intrinsically low noise and high spectral selectivity, yet their deployment in large-area, high-density electronic imaging systems remains limited by a fundamental trade-off between material quality, device speed, and compatibility with high-density planar silicon readout circuits. Here, we report a membrane-enabled integration platform based on transferable single-crystalline beta-Ga2O3 that overcomes these constraints at the system level. By exploiting the weak interplanar bonding of beta-Ga2O3 (100) plane, we obtain wafer-scale freestanding single-crystalline membranes that enable vertically integrated photodiodes with sub-microsecond, non-persistent photoresponse and high UV-visible rejection. Crucially, we introduce a stitching-based membrane assembly strategy that decouples array resolution from the size of the source single-crystalline substrate, allowing high-resolution photodetector arrays to be integrated onto silicon thin-film-transistor backplanes. The modular assembled active-matrix UV imaging arrays exhibit uniform solar-blind response without image lag, in stark contrast to arrays based on amorphous or polycrystalline films. Beyond beta-Ga2O3, this membrane-enabled and stitching-based modular integration strategy provides a general route toward high-speed, high-resolution electronic imaging systems using transferable single-crystalline semiconductors.

cond-mat.mtrl-sci↗
arXiv2026

Decoupling Perception and Calibration: Label-Efficient Image Quality Assessment Framework

Recent multimodal large language models (MLLMs) have demonstrated strong capabilities in image quality assessment (IQA) tasks. However, adapting such large-scale models is computationally expensive and still relies on substantial Mean Opinion Score (MOS) annotations. We argue that for MLLM-based IQA, the core bottleneck lies not in the quality perception capacity of MLLMs, but in MOS scale calibration. Therefore, we propose LEAF, a Label-Efficient Image Quality Assessment Framework that distills perceptual quality priors from an MLLM teacher into a lightweight student regressor, enabling MOS calibration with minimal human supervision. Specifically, the teacher conducts dense supervision through point-wise judgments and pair-wise preferences, with an estimate of decision reliability. Guided by these signals, the student learns the teacher's quality perception patterns through joint distillation and is calibrated on a small MOS subset to align with human annotations. Experiments on both user-generated and AI-generated IQA benchmarks demonstrate that our method significantly reduces the need for human annotations while maintaining strong MOS-aligned correlations, making lightweight IQA practical under limited annotation budgets.

cs.CV↗
arXiv2026

Burst Mode Ultrafast Laser Welding of Sapphire and Fe-36Ni Alloy with Non-optical Contact Condition

Ultrafast laser welding provides a promising approach for high precision integration of transparent and metallic materials. However, its practical application remains constrained by the precise regulation of the interfacial gap. This study investigates the interfacial response and bonding mechanism of sapphire and Fe-36Ni alloy joints under controlled non-optical contact conditions using burst mode ultrafast laser irradiation. A polymer interlayer was introduced between naturally stacked samples to establish a variable interfacial gap, allowing systematic evaluation of gap-dependent morphology, melting behavior, and elemental transport. By redistributing the pulse energy into sequential sub-pulses, the burst mode reconstructs the temporal energy-deposition process, yielding enhanced plasma-material coupling and stable thermal accumulation. Compared with single pulse irradiation, burst mode sustains continuous bonding across gaps exceeding 10 um--far beyond the failure threshold of the single pulse mode--and forms a fusion zone 82% larger. Fracture surface and cross-sectional analyses of SEM and EDS results confirm that sequential sub-pulses promote extensive sapphire melting, droplet-driven gap bridging, and enhanced Al-Fe interdiffusion at the interface. These results provide a scientific basis for high-gap-tolerance ultrafast laser welding and scalable integration of transparent-metal hybrid components in advanced optoelectronic and precision engineering applications.

physics.optics↗
arXiv2026

HCFT: Hierarchical Convolutional Fusion Transformer for EEG Decoding

Electroencephalography (EEG) decoding requires models that can effectively extract and integrate complex temporal, spectral, and spatial features from multichannel signals. To address this challenge, we propose a lightweight and generalizable decoding framework named Hierarchical Convolutional Fusion Transformer (HCFT), which combines dual-branch convolutional encoders and hierarchical Transformer blocks for multi-scale EEG representation learning. Specifically, the model first captures local temporal and spatiotemporal dynamics through time-domain and time-space convolutional branches, and then aligns these features via a cross-attention mechanism that enables interaction between branches at each stage. Subsequently, a hierarchical Transformer fusion structure is employed to encode global dependencies across all feature stages, while a customized Dynamic Tanh normalization module is introduced to replace traditional Layer Normalization in order to enhance training stability and reduce redundancy. Extensive experiments are conducted on two representative benchmark datasets, BCI Competition IV-2b and CHB-MIT, covering both event-related cross-subject classification and continuous seizure prediction tasks. Results show that HCFT achieves 80.83% average accuracy and a Cohen's kappa of 0.6165 on BCI IV-2b, as well as 99.10% sensitivity, 0.0236 false positives per hour, and 98.82% specificity on CHB-MIT, consistently outperforming over ten state-of-the-art baseline methods. Ablation studies confirm that each core component of the proposed framework contributes significantly to the overall decoding performance, demonstrating HCFT's effectiveness in capturing EEG dynamics and its potential for real-world BCI applications.

cs.HC↗
arXiv2025

Unison: A Fully Automatic, Task-Universal, and Low-Cost Framework for Unified Understanding and Generation

Unified understanding and generation is a highly appealing research direction in multimodal learning. There exist two approaches: one trains a transformer via an auto-regressive paradigm, and the other adopts a two-stage scheme connecting pre-trained understanding and generative models for alignment fine-tuning. The former demands massive data and computing resources unaffordable for ordinary researchers. Though the latter requires a lower training cost, existing works often suffer from limited task coverage or poor generation quality. Both approaches lack the ability to parse input meta-information (such as task type, image resolution, video duration, etc.) and require manual parameter configuration that is tedious and non-intelligent. In this paper, we propose Unison which adopts the two-stage scheme while preserving the capabilities of the pre-trained models well. With an extremely low training cost, we cover a variety of multimodal understanding tasks, including text, image, and video understanding, as well as diverse generation tasks, such as text-to-visual content generation, editing, controllable generation, and IP-based reference generation. We also equip our model with the ability to automatically parse user intentions, determine the target task type, and accurately extract the meta-information required for the corresponding task. This enables full automation of various multimodal tasks without human intervention. Experiments demonstrate that, under a low-cost setting of only 500k training samples and 50 GPU hours, our model can accurately and automatically identify tasks and extract relevant parameters, and achieve superior performance across a variety of understanding and generation tasks.

cs.CV↗
arXiv2025

In-depth Analysis on Caching and Pre-fetching in Mixture of Experts Offloading

In today's landscape, Mixture of Experts (MoE) is a crucial architecture that has been used by many of the most advanced models. One of the major challenges of MoE models is that they usually require much more memory than their dense counterparts due to their unique architecture, and hence are harder to deploy in environments with limited GPU memory, such as edge devices. MoE offloading is a promising technique proposed to overcome this challenge, especially if it is enhanced with caching and pre-fetching, but prior work stopped at suboptimal caching algorithm and offered limited insights. In this work, we study MoE offloading in depth and make the following contributions: 1. We analyze the expert activation and LRU caching behavior in detail and provide traces. 2. We propose LFU caching optimization based on our analysis and obtain strong improvements from LRU. 3. We implement and experiment speculative expert pre-fetching, providing detailed trace showing its huge potential . 4. In addition, our study extensively covers the behavior of the MoE architecture itself, offering information on the characteristic of the gating network and experts. This can inspire future work on the interpretation of MoE models and the development of pruning techniques for MoE architecture with minimal performance loss.

cs.LG↗
arXiv2025

ROFI: A Deep Learning-Based Ophthalmic Sign-Preserving and Reversible Patient Face Anonymizer

Patient face images provide a convenient mean for evaluating eye diseases, while also raising privacy concerns. Here, we introduce ROFI, a deep learning-based privacy protection framework for ophthalmology. Using weakly supervised learning and neural identity translation, ROFI anonymizes facial features while retaining disease features (over 98\% accuracy, $κ> 0.90$). It achieves 100\% diagnostic sensitivity and high agreement ($κ> 0.90$) across eleven eye diseases in three cohorts, anonymizing over 95\% of images. ROFI works with AI systems, maintaining original diagnoses ($κ> 0.80$), and supports secure image reversal (over 98\% similarity), enabling audits and long-term care. These results show ROFI's effectiveness of protecting patient privacy in the digital medicine era.

cs.CV↗
arXiv2025

Visual Anomaly Detection for Reliable Robotic Implantation of Flexible Microelectrode Array

Flexible microelectrode (FME) implantation into brain cortex is challenging due to the deformable fiber-like structure of FME probe and the interaction with critical bio-tissue. To ensure reliability and safety, the implantation process should be monitored carefully. This paper develops an image-based anomaly detection framework based on the microscopic cameras of the robotic FME implantation system. The unified framework is utilized at four checkpoints to check the micro-needle, FME probe, hooking result, and implantation point, respectively. Exploiting the existing object localization results, the aligned regions of interest (ROIs) are extracted from raw image and input to a pretrained vision transformer (ViT). Considering the task specifications, we propose a progressive granularity patch feature sampling method to address the sensitivity-tolerance trade-off issue at different locations. Moreover, we select a part of feature channels with higher signal-to-noise ratios from the raw general ViT features, to provide better descriptors for each specific scene. The effectiveness of the proposed methods is validated with the image datasets collected from our implantation system.

cs.CV↗
arXiv2025

Foundation Models for Cross-Domain EEG Analysis Application: A Survey

Electroencephalography (EEG) analysis stands at the forefront of neuroscience and artificial intelligence research, where foundation models are reshaping the traditional EEG analysis paradigm by leveraging their powerful representational capacity and cross-modal generalization. However, the rapid proliferation of these techniques has led to a fragmented research landscape, characterized by diverse model roles, inconsistent architectures, and a lack of systematic categorization. To bridge this gap, this study presents the first comprehensive modality-oriented taxonomy for foundation models in EEG analysis, systematically organizing research advances based on output modalities of the native EEG decoding, EEG-text, EEG-vision, EEG-audio, and broader multimodal frameworks. We rigorously analyze each category's research ideas, theoretical foundations, and architectural innovations, while highlighting open challenges such as model interpretability, cross-domain generalization, and real-world applicability in EEG-based systems. By unifying this dispersed field, our work not only provides a reference framework for future methodology development but accelerates the translation of EEG foundation models into scalable, interpretable, and online actionable solutions.

cs.HC↗
arXiv2025

Ultralow-pressure mechanical-motion switching of ferroelectric polarization

Ferroelectric polarization switching, achieved by mechanical forces, enables the storage of stress information in ferroelectrics, and holds promise for human-interfacing applications. The prevailing mechanical approach is locally induced flexoelectricity with large strain gradients. However, this approach usually requires huge mechanical pressures, which greatly impedes device applications. Here, we report an approach of using triboelectric effect to mechanically, reversibly switch ferroelectric polarization across α-In2Se3 ferroelectric memristors. Through contact electrification and electrostatic induction effects, triboelectric units are used to sensitively detect mechanical forces and generate electrical voltage pulses to trigger α-In2Se3 resistance switching. We realize multilevel resistance states under different mechanical forces, by which a neuromorphic stress system is demonstrated. Strikingly, we achieve the reversal of α-In2Se3 ferroelectric polarization with a record-low mechanical pressure of ~ 10 kPa, and even with tactile touches. Our work provides a fundamental but pragmatic strategy for creating mechanical-tactile ferroelectric memory devices.

cond-mat.mtrl-sci↗
arXiv2025

A Two-Stage Trip Inference Model of Purposes and Socio-Economic Attributes of Regular Public Transit Users

Data-driven research is becoming a new paradigm in transportation, but the natural lack of individual socio-economic attributes in transportation data makes research such as activity purpose inference and mobility pattern identification lack convincingness and verifiability. In this paper, a two-stage trip purpose and socio-economic attributes inference model is proposed based on travel resident survey and smart card data. In the first stage, the trip purpose of each trip is inferred by a combination of rule-based and XGBoost models. In the second stage, based on the trip purpose, a machine-learning model is built to inference the socio-economic attributes of individuals. A teacher-student model based on self-training is then applied on the models above to transfer them to smart card data. The impact of independent variables of socio-economic attributes inference model is also investigated. The results show that models for inferring trip purposes and socio-economic attributes have overall accuracies of 92.7% and 76.3%, respectively. Travel time, arrival time, departure time and purpose of the first two trips are most important factors on age and job status, while the land price of jobs-housing are significant to the inference of individual incomes.

stat.AP↗
arXiv2025

Wafer-scale Integration of Single-Crystalline MoS$_2$ for Flexible Electronics Enabled by Oxide Dry-transfer

Atomically thin, single-crystalline transition metal dichalcogenides (TMDCs) grown via chemical vapor deposition (CVD) on sapphire substrates exhibit exceptional mechanical and electrical properties, positioning them as excellent channel materials for flexible electronics. However, conventional wet-transfer processes for integrating these materials onto flexible substrates often introduce surface contamination, significantly degrading device performance. Here, we present a wafer-scale dry-transfer technique using a high-dielectric oxide as the transfer medium, enabling the integration of 4-inch single-crystalline MoS$_2$ onto flexible substrates. This method eliminates contact with polymers or solvents, thus preserving the intrinsic electronic properties of MoS$_2$. As a result, the fabricated flexible field-effect transistor (FET) arrays exhibit remarkable performance, with a mobility of 117 cm$^2$/Vs, a subthreshold swing of 68.8 mV dec$^{-1}$, and an ultra-high current on/off ratio of $10^{12}$-values comparable to those achieved on rigid substrates. Leveraging the outstanding electrical characteristics, we demonstrated MoS$_2$-based flexible inverters operating in the subthreshold regime, achieving both a high gain of 218 and ultra-low power consumption of 1.4 pW/$μ$m. Additionally, we integrated a flexible tactile sensing system driven by active-matrix MoS$_2$ FET arrays onto a robotic gripper, enabling real-time object identification. These findings demonstrate the simultaneous achievement of high electrical performance and flexibility, highlighting the immense potential of single-crystalline TMDC-based flexible electronics for real-world applications.

physics.app-ph↗
arXiv2025

Roadmap on Neuromorphic Photonics

This roadmap consolidates recent advances while exploring emerging applications, reflecting the remarkable diversity of hardware platforms, neuromorphic concepts, and implementation philosophies reported in the field. It emphasizes the critical role of cross-disciplinary collaboration in this rapidly evolving field.

cs.ET↗
arXiv2024

Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection

Enabling models to recognize vast open-world categories has been a longstanding pursuit in object detection. By leveraging the generalization capabilities of vision-language models, current open-world detectors can recognize a broader range of vocabularies, despite being trained on limited categories. However, when the scale of the category vocabularies during training expands to a real-world level, previous classifiers aligned with coarse class names significantly reduce the recognition performance of these detectors. In this paper, we introduce Prova, a multi-modal prototype classifier for vast-vocabulary object detection. Prova extracts comprehensive multi-modal prototypes as initialization of alignment classifiers to tackle the vast-vocabulary object recognition failure problem. On V3Det, this simple method greatly enhances the performance among one-stage, two-stage, and DETR-based detectors with only additional projection layers in both supervised and open-vocabulary settings. In particular, Prova improves Faster R-CNN, FCOS, and DINO by 3.3, 6.2, and 2.9 AP respectively in the supervised setting of V3Det. For the open-vocabulary setting, Prova achieves a new state-of-the-art performance with 32.8 base AP and 11.0 novel AP, which is of 2.6 and 4.3 gain over the previous methods.

cs.CV↗
arXiv2024

Photo-induced phase transition on black samarium monosulfide

To investigate the role of the excitons for the origin of the pressure-induced phase transition (BGT) from the black-colored insulator (BI) to the golden-yellow-colored metal (GM) of samarium monosulfide (SmS), optical reflectivity, Sm $3d$ X-ray absorption spectroscopy (XAS), and X-ray diffraction (XRD) with the creation of excitons by photoexcitation (PE) are reported. In the pump-probe reflectivity measurement, following a huge reflectivity change of about 22 %, three different relaxation times with a vibration component were observed. The fast component with the relaxation time ($τ$) of less than 1 ps is due to the excitation and relaxation of electrons into the conduction band, and the slowest one with $τ> {\rm several} 100$ ps originates from the appearance of the photo-induced (PI) state. The components with $τ\sim 10$ ps and vibration originate from the appearance of the PI state and the interference between the reflection lights at the sample surface and the boundary between the BI and PI states, suggesting that the electronic structure of the PI phase is different from that of the BI state. XAS spectra indicate that the Sm mean valence is shifted from the Sm$^{2+}$ dominant to the intermediate between Sm$^{2+}$ and Sm$^{3+}$ by PE but did not change to that of the GM phase across BGT, consistent with the reflectivity data. The XRD result after PE shows that the PI state has much less lattice contraction than the GM phase. These results suggest that the BGT cannot be achieved solely by creating excitons after PE but requires other effects, such as a lattice contraction.

cond-mat.str-el↗
arXiv2024

Dual-TSST: A Dual-Branch Temporal-Spectral-Spatial Transformer Model for EEG Decoding

The decoding of electroencephalography (EEG) signals allows access to user intentions conveniently, which plays an important role in the fields of human-machine interaction. To effectively extract sufficient characteristics of the multichannel EEG, a novel decoding architecture network with a dual-branch temporal-spectral-spatial transformer (Dual-TSST) is proposed in this study. Specifically, by utilizing convolutional neural networks (CNNs) on different branches, the proposed processing network first extracts the temporal-spatial features of the original EEG and the temporal-spectral-spatial features of time-frequency domain data converted by wavelet transformation, respectively. These perceived features are then integrated by a feature fusion block, serving as the input of the transformer to capture the global long-range dependencies entailed in the non-stationary EEG, and being classified via the global average pooling and multi-layer perceptron blocks. To evaluate the efficacy of the proposed approach, the competitive experiments are conducted on three publicly available datasets of BCI IV 2a, BCI IV 2b, and SEED, with the head-to-head comparison of more than ten other state-of-the-art methods. As a result, our proposed Dual-TSST performs superiorly in various tasks, which achieves the promising EEG classification performance of average accuracy of 80.67% in BCI IV 2a, 88.64% in BCI IV 2b, and 96.65% in SEED, respectively. Extensive ablation experiments conducted between the Dual-TSST and comparative baseline model also reveal the enhanced decoding performance with each module of our proposed method. This study provides a new approach to high-performance EEG decoding, and has great potential for future CNN-Transformer based applications.

cs.HC↗