arXiv subjects

Juheon Lee

Publications and source records attributed to Juheon Lee.

At least 19 recordsLinked to original sources

arXiv2026

SlimPer: Make Personalization Model Slim and Smart

Transformer-style architectures are increasingly adopted for industrial recommendation systems, yet they inherit a design premise misaligned with the task: generative models rely on per-token autoregressive prediction, which justifies maintaining large intermediate tensors that scale with sequence length. In contrast, recommendation systems produce a single set of relevance scores for each pair without token-level supervision. Leveraging this observation, we propose SlimPer, which reformulates personalized ranking as iterative refinement of a compact, unified knowledge base. At each layer, the model selectively queries raw multi-modal user-side tokens, computes explicit relevance matching scores, and refines the knowledge base, all in O(N) per-layer cost with a fixed-size intermediate representation. As a result, model depth is decoupled from user history length, enabling deeper relevance understanding without proportional growth in compute or memory; request-only optimization further trims memory by sharing a single copy of user-side tokens across all candidate items. SlimPer unifies sparse, dense, and sequence features within a single backbone and provides inherent interpretability through its attention mechanism. Deployed on Instagram Reels and Feed, SlimPer yields measurable improvements in user engagement while streamlining the overall system and enabling effective modeling of 10k+ fine-grained user history events.

cs.IR↗

arXiv2026

RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching

While flow-matching text-to-speech (TTS) achieves strong zero-shot speaker similarity and naturalness, it remains susceptible to content fidelity issues, particularly skip and repeat errors from imperfect alignment. We propose RobustSpeechFlow, a training strategy that improves alignment robustness by extending contrastive flow matching with length-preserving repeat and skip latent augmentations. Requiring no external aligners or preference data, our method directly penalizes realistic failure modes and readily integrates into existing pipelines. On Seed-TTS-eval, it reduces the word error rate (WER) from 1.44 to 1.38 using only 0.06B parameters. On our ZERO500 benchmark, it delivers consistent intelligibility improvements across diverse speaker and prosody conditions; at NFE=24, it reduces English character error rate (CER) from 0.48\% to 0.35\% and Korean CER from 0.81\% to 0.57\%. Audio samples: https://robustspeechflow.github.io/

cs.SD↗

arXiv2025

Robust TTS Training via Self-Purifying Flow Matching for the WildSpoof 2026 TTS Track

This paper presents a lightweight text-to-speech (TTS) system developed for the WildSpoof Challenge TTS Track. Our approach fine-tunes the recently released open-weight TTS model, \textit{Supertonic}\footnote{\url{https://github.com/supertone-inc/supertonic}}, with Self-Purifying Flow Matching (SPFM) to enable robust adaptation to in-the-wild speech. SPFM mitigates label noise by comparing conditional and unconditional flow matching losses on each sample, routing suspicious text--speech pairs to unconditional training while still leveraging their acoustic information. The resulting model achieves the lowest Word Error Rate (WER) among all participating teams, while ranking second in perceptual metrics such as UTMOS and DNSMOS. These findings demonstrate that efficient, open-weight architectures like Supertonic can be effectively adapted to diverse real-world speech conditions when combined with explicit noise-handling mechanisms such as SPFM.

cs.SD↗

arXiv2025

Incoherent dielectric tensor tomography for quantitative 3D measurement of biaxial anisotropy

Biaxial anisotropy, arising from distinct optical responses along three principal directions, underlies the complex structure of many crystalline, polymeric, and biological materials. However, existing techniques such as X-ray diffraction and electron microscopy require specialized facilities or destructive preparation and cannot provide full three-dimensional (3D) information. Here we introduce incoherent dielectric tensor tomography (iDTT), a non-interferometric optical imaging method that quantitatively reconstructs the 3D dielectric tensor under incoherent, polarization-diverse illumination. By combining polarization diversity and angular-spectrum modulation, iDTT achieves speckle-free and vibration-robust mapping of biaxial birefringence with submicron resolution. Simulations and experiments on uniaxial and biaxial samples validate its quantitative accuracy. Applied to mixed and polycrystalline materials, iDTT distinguishes crystal types by their birefringent properties and reveals 3D grain orientations and boundaries. This approach establishes iDTT as a practical and accessible tool for quantitative, label-free characterization of biaxial anisotropy in diverse materials.

physics.optics↗

arXiv2025

Training Flow Matching Models with Reliable Labels via Self-Purification

Training datasets are inherently imperfect, often containing mislabeled samples due to human annotation errors, limitations of tagging models, and other sources of noise. Such label contamination can significantly degrade the performance of a trained model. In this work, we introduce Self-Purifying Flow Matching (SPFM), a principled approach to filtering unreliable data within the flow-matching framework. SPFM identifies suspicious data using the model itself during the training process, bypassing the need for pretrained models or additional modules. Our experiments demonstrate that models trained with SPFM generate samples that accurately adhere to the specified conditioning, even when trained on noisy labels. Furthermore, we validate the robustness of SPFM on the TITW dataset, which consists of in-the-wild speech data, achieving performance that surpasses existing baselines.

eess.AS↗

arXiv2025

Improving Test-Time Performance of RVQ-based Neural Codecs

The residual vector quantization (RVQ) technique plays a central role in recent advances in neural audio codecs. These models effectively synthesize high-fidelity audio from a limited number of codes due to the hierarchical structure among quantization levels. In this paper, we propose an encoding algorithm to further enhance the synthesis quality of RVQ-based neural codecs at test-time. Firstly, we point out the suboptimal nature of quantized vectors generated by conventional methods. We demonstrate that quantization error can be mitigated by selecting a different set of codes. Subsequently, we present our encoding algorithm, designed to identify a set of discrete codes that achieve a lower quantization error. We then apply the proposed method to pre-trained models and evaluate its efficacy using diverse metrics. Our experimental findings validate that our method not only reduces quantization errors, but also improves synthesis quality.

eess.AS↗

arXiv2025

Length-Aware Rotary Position Embedding for Text-Speech Alignment

Many recent text-to-speech (TTS) systems are built on transformer architectures and employ cross-attention mechanisms for text-speech alignment. Within these systems, rotary position embedding (RoPE) is commonly used to encode positional information in text and speech representations. In this work, we introduce length-aware RoPE (LARoPE), a simple yet effective extension of RoPE that improves text-speech alignment. Unlike RoPE, which relies on absolute indices, LARoPE computes relative distances between query and key positions using length-normalized indices. Experimental results show that LARoPE consistently outperforms RoPE, offering faster loss convergence, more accurate text-speech alignment, and higher overall TTS quality. Furthermore, LARoPE demonstrates greater resilience to variations in utterance duration and maintains stable performance in extended speech generation up to 30 seconds, whereas RoPE suffers from notable degradation. Notably, our method achieves a state-of-the-art word error rate on a standard zero-shot TTS benchmark.

eess.AS↗

arXiv2025

Few-step Adversarial Schr\"{o}dinger Bridge for Generative Speech Enhancement

Deep generative models have recently been employed for speech enhancement to generate perceptually valid clean speech on large-scale datasets. Several diffusion models have been proposed, and more recently, a tractable Schr\"odinger Bridge has been introduced to transport between the clean and noisy speech distributions. However, these models often suffer from an iterative reverse process and require a large number of sampling steps -- more than 50. Our investigation reveals that the performance of baseline models significantly degrades when the number of sampling steps is reduced, particularly under low-SNR conditions. We propose integrating Schr\"odinger Bridge with GANs to effectively mitigate this issue, achieving high-quality outputs on full-band datasets while substantially reducing the required sampling steps. Experimental results demonstrate that our proposed model outperforms existing baselines, even with a single inference step, in both denoising and dereverberation tasks.

cs.SD↗

arXiv2025

SupertonicTTS: Towards Highly Efficient and Streamlined Text-to-Speech System

We introduce SupertonicTTS, a novel text-to-speech (TTS) system designed for efficient and streamlined speech synthesis. SupertonicTTS comprises three components: a speech autoencoder for continuous latent representation, a text-to-latent module leveraging flow-matching for text-to-latent mapping, and an utterance-level duration predictor. To enable a lightweight architecture, we employ a low-dimensional latent space, temporal compression of latents, and ConvNeXt blocks. The TTS pipeline is further simplified by operating directly on raw character-level text and employing cross-attention for text-speech alignment, thus eliminating the need for grapheme-to-phoneme (G2P) modules and external aligners. In addition, we propose context-sharing batch expansion that accelerates loss convergence and stabilizes text-speech alignment with minimal memory and I/O overhead. Experimental results demonstrate that SupertonicTTS delivers performance comparable to contemporary zero-shot TTS models with only 44M parameters, while significantly reducing architectural complexity and computational cost. Audio samples are available at: https://supertonictts.github.io/.

eess.AS↗

arXiv2025

Compression benchmarking of holotomography data using the OME-Zarr storage format

Holotomography (HT) is a label-free, three-dimensional imaging technique that captures refractive index distributions of biological samples at sub-micron resolution. As modern HT systems enable high-throughput and large-scale acquisition, they produce terabyte-scale datasets that require efficient data management. This study presents a systematic benchmarking of data compression strategies for HT data stored in the OME-Zarr format, a cloud-compatible, chunked data structure suitable for scalable imaging workflows. Using representative datasets-including embryo, tissue, and birefringent tissue volumes-we evaluated combinations of preprocessing filters and 25 compression configurations across multiple compression levels. Performance was assessed in terms of compression ratio, bandwidth, and decompression speed. A throughput-based evaluation metric was introduced to simulate real-world conditions under varying network constraints, supporting optimal compressor selection based on system bandwidth. The results offer practical guidance for storage and transmission of large HT datasets and serve as a reference for implementing scalable, FAIR-aligned imaging workflows in cloud and high-performance computing environments.

physics.optics↗

arXiv2025

GraphCompNet: A Position-Aware Model for Predicting and Compensating Shape Deviations in 3D Printing

Shape deviation modeling and compensation in additive manufacturing are pivotal for achieving high geometric accuracy and enabling industrial-scale production. Critical challenges persist, including generalizability across complex geometries and adaptability to position-dependent variations in batch production. Traditional methods of controlling geometric deviations often rely on complex parameterized models and repetitive metrology, which can be time-consuming yet not applicable for batch production. In this paper, we present a novel, process-agnostic approach to address the challenge of ensuring geometric precision and accuracy in position-dependent AM production. The proposed GraphCompNet presents a novel computational framework integrating graph-based neural networks with a GAN inspired training paradigm. The framework leverages point cloud representations and dynamic graph convolutional neural networks (DGCNNs) to model intricate geometries while incorporating position-specific thermal and mechanical variations. A two-stage adversarial training process iteratively refines compensated designs using a compensator-predictor architecture, enabling real-time feedback and optimization. Experimental validation across various shapes and positions demonstrates the framework's ability to predict deviations in freeform geometries and adapt to position-dependent batch production conditions, significantly improving compensation accuracy (35 to 65 percent) across the entire printing space, addressing position-dependent variabilities within the print chamber. The proposed method advances the development of a Digital Twin for AM, offering scalable, real-time monitoring and compensation capabilities.

cs.CV↗

arXiv2024

DualSpeech: Enhancing Speaker-Fidelity and Text-Intelligibility Through Dual Classifier-Free Guidance

Text-to-Speech (TTS) models have advanced significantly, aiming to accurately replicate human speech's diversity, including unique speaker identities and linguistic nuances. Despite these advancements, achieving an optimal balance between speaker-fidelity and text-intelligibility remains a challenge, particularly when diverse control demands are considered. Addressing this, we introduce DualSpeech, a TTS model that integrates phoneme-level latent diffusion with dual classifier-free guidance. This approach enables exceptional control over speaker-fidelity and text-intelligibility. Experimental results demonstrate that by utilizing the sophisticated control, DualSpeech surpasses existing state-of-the-art TTS models in performance. Demos are available at https://bit.ly/48Ewoib.

eess.AS↗

arXiv2024

Revisiting Cross-Domain Problem for LiDAR-based 3D Object Detection

Deep learning models such as convolutional neural networks and transformers have been widely applied to solve 3D object detection problems in the domain of autonomous driving. While existing models have achieved outstanding performance on most open benchmarks, the generalization ability of these deep networks is still in doubt. To adapt models to other domains including different cities, countries, and weather, retraining with the target domain data is currently necessary, which hinders the wide application of autonomous driving. In this paper, we deeply analyze the cross-domain performance of the state-of-the-art models. We observe that most models will overfit the training domains and it is challenging to adapt them to other domains directly. Existing domain adaptation methods for 3D object detection problems are actually shifting the models' knowledge domain instead of improving their generalization ability. We then propose additional evaluation metrics -- the side-view and front-view AP -- to better analyze the core issues of the methods' heavy drops in accuracy levels. By using the proposed metrics and further evaluating the cross-domain performance in each dimension, we conclude that the overfitting problem happens more obviously on the front-view surface and the width dimension which usually faces the sensor and has more 3D points surrounding it. Meanwhile, our experiments indicate that the density of the point cloud data also significantly influences the models' cross-domain performance.

cs.CV↗

arXiv2024

Detect Closer Surfaces that can be Seen: New Modeling and Evaluation in Cross-domain 3D Object Detection

The performance of domain adaptation technologies has not yet reached an ideal level in the current 3D object detection field for autonomous driving, which is mainly due to significant differences in the size of vehicles, as well as the environments they operate in when applied across domains. These factors together hinder the effective transfer and application of knowledge learned from specific datasets. Since the existing evaluation metrics are initially designed for evaluation on a single domain by calculating the 2D or 3D overlap between the prediction and ground-truth bounding boxes, they often suffer from the overfitting problem caused by the size differences among datasets. This raises a fundamental question related to the evaluation of the 3D object detection models' cross-domain performance: Do we really need models to maintain excellent performance in their original 3D bounding boxes after being applied across domains? From a practical application perspective, one of our main focuses is actually on preventing collisions between vehicles and other obstacles, especially in cross-domain scenarios where correctly predicting the size of vehicles is much more difficult. In other words, as long as a model can accurately identify the closest surfaces to the ego vehicle, it is sufficient to effectively avoid obstacles. In this paper, we propose two metrics to measure 3D object detection models' ability of detecting the closer surfaces to the sensor on the ego vehicle, which can be used to evaluate their cross-domain performance more comprehensively and reasonably. Furthermore, we propose a refinement head, named EdgeHead, to guide models to focus more on the learnable closer surfaces, which can greatly improve the cross-domain performance of existing models not only under our new metrics, but even also under the original BEV/3D metrics.

cs.CV↗

arXiv2024

Neural varifolds: an aggregate representation for quantifying the geometry of point clouds

Point clouds are popular 3D representations for real-life objects (such as in LiDAR and Kinect) due to their detailed and compact representation of surface-based geometry. Recent approaches characterise the geometry of point clouds by bringing deep learning based techniques together with geometric fidelity metrics such as optimal transportation costs (e.g., Chamfer and Wasserstein metrics). In this paper, we propose a new surface geometry characterisation within this realm, namely a neural varifold representation of point clouds. Here the surface is represented as a measure/distribution over both point positions and tangent spaces of point clouds. The varifold representation quantifies not only the surface geometry of point clouds through the manifold-based discrimination, but also subtle geometric consistencies on the surface due to the combined product space. This study proposes neural varifold algorithms to compute the varifold norm between two point clouds using neural networks on point clouds and their neural tangent kernel representations. The proposed neural varifold is evaluated on three different sought-after tasks -- shape matching, few-shot shape classification and shape reconstruction. Detailed evaluation and comparison to the state-of-the-art methods demonstrate that the proposed versatile neural varifold is superior in shape matching and few-shot shape classification, and is competitive for shape reconstruction.

cs.CV↗

arXiv2024

Rytov Approximation of Vectorial Waves by Modifying Scattering Matrixes: Precise Reconstruction of Dielectric Tensor Tomography

Analyzing 3D anisotropic materials presents significant challenges, especially when assessing 3D orientations, material distributions, and anisotropies through scattered light, due to the inherently vectorial nature of light-matter interactions. In this study, we formulate a scattering theory based on the Rytov approximation, commonly employed in scalar wave tomography, tailored to accommodate vector waves by modifying the scattering matrix. Using this formulation, we investigate the intricate 3D structure of liquid crystals with multiple topological defects exploiting dielectric tensor tomography. By leveraging dielectric tensor tomography, we successfully visualize these topological defects in three dimensions, a task that conventional 2D imaging techniques fail to achieve.

physics.optics↗

arXiv2024

Virtual Foundry Graphnet for Metal Sintering Deformation Prediction

Metal Sintering is a necessary step for Metal Injection Molded parts and binder jet such as HP's metal 3D printer. The metal sintering process introduces large deformation varying from 25 to 50% depending on the green part porosity. In this paper, we use a graph-based deep learning approach to predict the part deformation, which can speed up the deformation simulation substantially at the voxel level. Running a well-trained Metal Sintering inferencing engine only takes a range of seconds to obtain the final sintering deformation value. The tested accuracy on example complex geometry achieves 0.7um mean deviation for a 63mm testing part.

cs.LG↗

arXiv2024

High-precision and low-noise dielectric tensor tomography using a micro-electromechanical system mirror

Dielectric tensor tomography is an imaging technique for mapping three-dimensional distributions of dielectric properties in transparent materials. This work introduces an enhanced illumination strategy employing a micro-electromechanical system mirror to achieve high precision and reduced noise in imaging. This illumination approach allows for precise manipulation of light, significantly improving the accuracy of angle control and minimizing diffraction noise compared to traditional beam steering approaches. Our experiments have successfully reconstructed the dielectric properties of liquid crystal droplets, which are known for their anisotropic structures, while demonstrating a notable reduction in background noise of the imag-es. Additionally, the technique has been applied to more complex samples, revealing its capability to achieve a high signal-to-noise ratio. This development represents a significant step forward in the field of birefringence imaging, offering a powerful tool for detailed study of materials with anisotropic properties.

physics.optics↗