arXiv subjects

Ngan Nguyen

Publications and source records attributed to Ngan Nguyen.

8 recordsLinked to original sources

arXiv2026

Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers

Modern one-step diffusion models achieve impressive quality through distribution-based timestep distillation. Yet, they rely on a critical assumption: Teacher and Student must inhabit the same latent space. This Shared-Space constraint prevents knowledge transfer from modern high-capacity Teachers (e.g., SD 3.5 and Flux) into compact, deployment-friendly Students such as SD 1.5, whose latent resolution and VAE parameterization differ from the Teacher. We formalize this overlooked regime as Cross-Space Distillation, where Teacher and Student differ in both latent resolution and VAE space. To enable distillation under this mismatch, we introduce the Bridge, a lightweight latent interface that maps Student latents into the Teacher space without modifying the Student backbone. Bridge combines a frozen Student VAE decoder as a spatial prior with a compact learnable projector, and is trained with latent reconstruction and attention fidelity objectives for stable Teacher-space alignment. Across diverse modern Teachers, Bridge enables substantial gains for compact one-step Students; for example, it improves SD 1.5 from 5.4 to 9.4 HPSv3 while preserving one-step inference, low latency, and broad ecosystem compatibility. These results show that heterogeneous large Teachers can be distilled into efficient, deployable backbones through a lightweight latent-space interface.

cs.CV↗

arXiv2026

InverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting

Recent diffusion-based models achieve photorealism in image inpainting but require many sampling steps, limiting practical use. Few-step text-to-image models offer faster generation, but naively applying them to inpainting yields poor harmonization and artifacts between the background and inpainted region. We trace this cause to random Gaussian noise initialization, which under low function evaluations causes semantic misalignment and reduced fidelity. To overcome this, we propose InverFill, a one-step inversion method tailored for inpainting that injects semantic information from the input masked image into the initial noise, enabling high-fidelity few-step inpainting. Instead of training inpainting models, InverFill leverages few-step text-to-image models in a blended sampling pipeline with semantically aligned noise as input, significantly improving vanilla blended sampling and even matching specialized inpainting models at low NFEs. Moreover, InverFill does not require real-image supervision and only adds minimal inference overhead. Extensive experiments show that InverFill consistently boosts baseline few-step models, improving image quality and text coherence without costly retraining or heavy iterative optimization.

cs.CV↗

arXiv2026

CTPD: Cross Tokenizer Preference Distillation

While knowledge distillation has seen widespread use in pre-training and instruction tuning, its application to aligning language models with human preferences remains underexplored, particularly in the more realistic cross-tokenizer setting. The incompatibility of tokenization schemes between teacher and student models has largely prevented fine-grained, white-box distillation of preference information. To address this gap, we propose Cross-Tokenizer Preference Distillation (CTPD), the first unified framework for transferring human-aligned behavior between models with heterogeneous tokenizers. CTPD introduces three key innovations: (1) Aligned Span Projection, which maps teacher and student tokens to shared character-level spans for precise supervision transfer; (2) a cross-tokenizer adaptation of Token-level Importance Sampling (TIS-DPO) for improved credit assignment; and (3) a Teacher-Anchored Reference, allowing the student to directly leverage the teacher's preferences in a DPO-style objective. Our theoretical analysis grounds CTPD in importance sampling, and experiments across multiple benchmarks confirm its effectiveness, with significant performance gains over existing methods. These results establish CTPD as a practical and general solution for preference distillation across diverse tokenization schemes, opening the door to more accessible and efficient alignment of language models.

cs.CL↗

arXiv2022

Peer Recommendation Interventions for Health-related Social Support: a Feasibility Assessment

Online health communities (OHCs) offer the promise of connecting with supportive peers. Forming these connections first requires finding relevant peers - a process that can be time-consuming. Peer recommendation systems are a computational approach to make finding peers easier during a health journey. By encouraging OHC users to alter their online social networks, peer recommendations could increase available support. But these benefits are hypothetical and based on mixed, observational evidence. To experimentally evaluate the effect of peer recommendations, we conceptualize these systems as health interventions designed to increase specific beneficial connection behaviors. In this paper, we designed a peer recommendation intervention to increase two behaviors: reading about peer experiences and interacting with peers. We conducted an initial feasibility assessment of this intervention by conducting a 12-week field study in which 79 users of CaringBridge received weekly peer recommendations via email. Our results support the usefulness and demand for peer recommendation and suggest benefits to evaluating larger peer recommendation interventions. Our contributions include practical guidance on the development and evaluation of peer recommendation interventions for OHCs.

cs.HC↗

arXiv2022

Differentiable Electron Microscopy Simulation: Methods and Applications for Visualization

We propose a new microscopy simulation system that can depict atomistic models in a micrograph visual style, similar to results of physical electron microscopy imaging. This system is scalable, able to represent simulation of electron microscopy of tens of viral particles and synthesizes the image faster than previous methods. On top of that, the simulator is differentiable, both its deterministic as well as stochastic stages that form signal and noise representations in the micrograph. This notable property has the capability for solving inverse problems by means of optimization and thus allows for generation of microscopy simulations using the parameter settings estimated from real data. We demonstrate this learning capability through two applications: (1) estimating the parameters of the modulation transfer function defining the detector properties of the simulated and real micrographs, and (2) denoising the real data based on parameters trained from the simulated examples. While current simulators do not support any parameter estimation due to their forward design, we show that the results obtained using estimated parameters are very similar to the results of real micrographs. Additionally, we evaluate the denoising capabilities of our approach and show that the results showed an improvement over state-of-the-art methods. Denoised micrographs exhibit less noise in the tilt-series tomography reconstructions, ultimately reducing the visual dominance of noise in direct volume rendering of microscopy tomograms.

q-bio.QM↗

arXiv2021

Finding Nano-\"Otzi: Semi-Supervised Volume Visualization for Cryo-Electron Tomography

Cryo-Electron Tomography (cryo-ET) is a new 3D imaging technique with unprecedented potential for resolving submicron structural detail. Existing volume visualization methods, however, cannot cope with its very low signal-to-noise ratio. In order to design more powerful transfer functions, we propose to leverage soft segmentation as an explicit component of visualization for noisy volumes. Our technical realization is based on semi-supervised learning where we combine the advantages of two segmentation algorithms. A first weak segmentation algorithm provides good results for propagating sparse user provided labels to other voxels in the same volume. This weak segmentation algorithm is used to generate dense pseudo labels. A second powerful deep-learning based segmentation algorithm can learn from these pseudo labels to generalize the segmentation to other unseen volumes, a task that the weak segmentation algorithm fails at completely. The proposed volume visualization uses the deep-learning based segmentation as a component for segmentation-aware transfer function design. Appropriate ramp parameters can be suggested automatically through histogram analysis. Finally, our visualization uses gradient-free ambient occlusion shading to further suppress visual presence of noise, and to give structural detail desired prominence. The cryo-ET data studied throughout our technical experiments is based on the highest-quality tilted series of intact SARS-CoV-2 virions. Our technique shows the high impact in target sciences for visual data analysis of very noisy volumes that cannot be visualized with existing techniques.

q-bio.QM↗

arXiv2020

Modeling in the Time of COVID-19: Statistical and Rule-based Mesoscale Models

We present a new technique for rapid modeling and construction of scientifically accurate mesoscale biological models. Resulting 3D models are based on few 2D microscopy scans and the latest knowledge about the biological entity represented as a set of geometric relationships. Our new technique is based on statistical and rule-based modeling approaches that are rapid to author, fast to construct, and easy to revise. From a few 2D microscopy scans, we learn statistical properties of various structural aspects, such as the outer membrane shape, spatial properties and distribution characteristics of the macromolecular elements on the membrane. This information is utilized in 3D model construction. Once all imaging evidence is incorporated in the model, additional information can be incorporated by interactively defining rules that spatially characterize the rest of the biological entity, such as mutual interactions among macromolecules, their distances and orientations to other structures. These rules are defined through an intuitive 3D interactive visualization and modeling feedback loop. We demonstrate the utility of our approach on a use case of the modeling procedure of the SARS-CoV-2 virus particle ultrastructure. Its first complete atomistic model, which we present here, can steer biological research to new promising directions in fighting spread of the virus.

q-bio.QM↗

arXiv2013

Comparative Assembly Hubs: Web Accessible Browsers for Comparative Genomics

We introduce a pipeline to easily generate collections of web accessible UCSC genome browsers interrelated by an alignment. Using the alignment, all annotations and the alignment itself can be efficiently viewed with reference to any genome in the collection, symmetrically. A new, intelligently scaled alignment display makes it simple to view all changes between the genomes at all levels of resolution, from substitutions to complex structural rearrangements, including duplications.

q-bio.GN↗