arXiv subjects

Haonan Zhu

Publications and source records attributed to Haonan Zhu.

10 recordsLinked to original sources

arXiv2026

TASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Design

Text-to-image models now generate graphic design at production scale, yet their supervision still comes primarily from photo-style preference datasets with a single overall verdict per comparison. Designers evaluate designs along several distinct axes (e.g., typography, layout, color harmony) that a single preference label collapses. We release \emph{TASTE} \textit{(Typography, Aesthetics, Spatial, Tone, Etc.)}, a multi-dimensional preference dataset in which two disjoint cohorts of five professional designers each ranked outputs from four current text-to-image models across nine criteria along with per-image hallucination flags. We pair the dataset with two contributions. First, a criterion-agnostic signal-validation framework based on Kendall's $τ$, majority-vote probability, and Condorcet cycles against exact iid-uniform nulls; the analysis reveals significant but moderate designer agreement, with every TASTE criterion rejecting the random-rater null. Second, we benchmark preference models on TASTE and find that off-the-shelf VLM judges and dedicated T2I scorers fail to reach majority agreement with the designer panel, while a small MLP head trained directly on TASTE substantially narrows the gap to the single-rater ceiling, setting a baseline for future TASTE-trained preference models.

cs.CV↗

arXiv2026

Structural Evaluation Metrics for SVG Generation via Leave-One-Out Analysis

SVG generation is typically evaluated by comparing rendered outputs to reference images, which captures visual similarity but not the structural properties that make SVG editable, decomposable, and reusable. Inspired by the classical jackknife, we introduce element-level leave-one-out (LOO) analysis. The procedure renders the SVG with and without each element, which yields element-level signals for quality assessment and structural analysis. From this single mechanism, we derive (i) per-element quality scores that enable zero-shot artifact detection; (ii) element-concept attribution via LOO footprints crossed with VLM-grounded concept heatmaps; and (iii) four structural metrics: purity, coverage, compactness, and locality, which quantify SVG modularity from complementary angles. These metrics extend SVG evaluation from image similarity to code structure, enabling element-level diagnosis and comparison of how visual concepts are represented, partitioned, and organized within SVG code. Their practical relevance is validated on over 19,000 edits (5 types) across 5 generation systems and 3 complexity tiers.

cs.LG↗

arXiv2026

Graphic-Design-Bench: A Comprehensive Benchmark for Evaluating AI on Graphic Design Tasks

We introduce GraphicDesignBench (GDB), the first comprehensive benchmark suite designed specifically to evaluate AI models on the full breadth of professional graphic design tasks. Unlike existing benchmarks that focus on natural-image understanding or generic text-to-image synthesis, GDB targets the unique challenges of professional design work: translating communicative intent into structured layouts, rendering typographically faithful text, manipulating layered compositions, producing valid vector graphics, and reasoning about animation. The suite comprises 50 tasks organized along five axes: layout, typography, infographics, template & design semantics and animation, each evaluated under both understanding and generation settings, and grounded in real-world design templates drawn from the LICA layered-composition dataset. We evaluate a set of frontier closed-source models using a standardized metric taxonomy covering spatial accuracy, perceptual quality, text fidelity, semantic alignment, and structural validity. Our results reveal that current models fall short on the core challenges of professional design: spatial reasoning over complex layouts, faithful vector code generation, fine-grained typographic perception, and temporal decomposition of animations remain largely unsolved. While high-level semantic understanding is within reach, the gap widens sharply as tasks demand precision, structure, and compositional awareness. GDB provides a rigorous, reproducible testbed for tracking progress toward AI systems that can function as capable design collaborators. The full evaluation framework is publicly available.

cs.CV↗

arXiv2026

Ouroboros: Wafer-Scale SRAM CIM with Token-Grained Pipelining for Large Language Model Inference

Conventional LLM inference architectures suffer from high energy and latency due to frequent data movement across memory hierarchies. We propose Ouroboros, a wafer-scale SRAM-based Computing-in-Memory (CIM) architecture that executes all operations in situ, eliminating off-chip migration. To maximize its limited first-level capacity, we introduce three innovations: Token-Grained Pipelining: Replaces sequence-level pipelining to mitigate length variations, boosting utilization and reducing activation storage. Distributed Dynamic KV Cache Management: Decouples memory from compute to leverage fragmented SRAM for efficient KV storage. Communication-Aware Mapping: Optimizes core allocation for locality and fault tolerance across the wafer. Experimental results show Ouroboros achieves average gains of $4.1\times$ in throughput and $4.2\times$ in energy efficiency, peaking at $9.1\times$ and $17\times$ for the 13B model. (*Due to the notification of arXiv "The Abstract field cannot be longer than 1,920 characters", the appeared Abstract is shortened. For the full Abstract, please download the Article.)

cs.AR↗

arXiv2025

Hierarchical Sparse Bayesian Multitask Model with Scalable Inference for Microbiome Analysis

This paper proposes a hierarchical Bayesian multitask learning model that is applicable to the general multi-task binary classification learning problem where the model assumes a shared sparsity structure across different tasks. We derive a computationally efficient inference algorithm based on variational inference to approximate the posterior distribution. We demonstrate the potential of the new approach on various synthetic datasets and for predicting human health status based on microbiome profile. Our analysis incorporates data pooled from multiple microbiome studies, along with a comprehensive comparison with other benchmark methods. Results in synthetic datasets show that the proposed approach has superior support recovery property when the underlying regression coefficients share a common sparsity structure across different tasks. Our experiments on microbiome classification demonstrate the utility of the method in extracting informative taxa while providing well-calibrated predictions with uncertainty quantification and achieving competitive performance in terms of prediction metrics. Notably, despite the heterogeneity of the pooled datasets (e.g., different experimental objectives, laboratory setups, sequencing equipment, patient demographics), our method delivers robust results.

cs.LG↗

arXiv2025

Deep Active Learning based Experimental Design to Uncover Synergistic Genetic Interactions for Host Targeted Therapeutics

Recent technological advances have introduced new high-throughput methods for studying host-virus interactions, but testing synergistic interactions between host gene pairs during infection remains relatively slow and labor intensive. Identification of multiple gene knockdowns that effectively inhibit viral replication requires a search over the combinatorial space of all possible target gene pairs and is infeasible via brute-force experiments. Although active learning methods for sequential experimental design have shown promise, existing approaches have generally been restricted to single-gene knockdowns or small-scale double knockdown datasets. In this study, we present an integrated Deep Active Learning (DeepAL) framework that incorporates information from a biological knowledge graph (SPOKE, the Scalable Precision Medicine Open Knowledge Engine) to efficiently search the configuration space of a large dataset of all pairwise knockdowns of 356 human genes in HIV infection. Through graph representation learning, the framework is able to generate task-specific representations of genes while also balancing the exploration-exploitation trade-off to pinpoint highly effective double-knockdown pairs. We additionally present an ensemble method for uncertainty quantification and an interpretation of the gene pairs selected by our algorithm via pathway analysis. To our knowledge, this is the first work to show promising results on double-gene knockdown experimental data of appreciable scale (356 by 356 matrix).

cs.LG↗

arXiv2022

A Graphical Model for Fusing Diverse Microbiome Data

This paper develops a Bayesian graphical model for fusing disparate types of count data. The motivating application is the study of bacterial communities from diverse high dimensional features, in this case transcripts, collected from different treatments. In such datasets, there are no explicit correspondences between the communities and each correspond to different factors, making data fusion challenging. We introduce a flexible multinomial-Gaussian generative model for jointly modeling such count data. This latent variable model jointly characterizes the observed data through a common multivariate Gaussian latent space that parameterizes the set of multinomial probabilities of the transcriptome counts. The covariance matrix of the latent variables induces a covariance matrix of co-dependencies between all the transcripts, effectively fusing multiple data sources. We present a computationally scalable variational Expectation-Maximization (EM) algorithm for inferring the latent variables and the parameters of the model. The inferred latent variables provide a common dimensionality reduction for visualizing the data and the inferred parameters provide a predictive posterior distribution. In addition to simulation studies that demonstrate the variational EM procedure, we apply our model to a bacterial microbiome dataset.

stat.ME↗

arXiv2020

Feasibility of space-based measurement-device-independent quantum key distribution

The measurement-device-independent (MDI) QKD is considered to be an alternative to overcome the currently trusted satellite paradigm. However, the feasibility of the space-based MDI-QKD remains unclear in terms of the factors: the high-loss uplink between a ground station and a satellite, the limited duration when two ground stations are simultaneously visible, as well as the rigorous requirements for the two-photon interference when performing the Bell-state Measurement (BSM). In this paper, we present a feasibility assessment of space-based MDI-QKD based on the Micius satellite. Integrated with the orbital dynamics model and atmosphere channel model, a framework is presented to explore the whole parameters space including orbit height, elevation angle, apertures of transceiver and atmospheric turbulence intensity to give the considerations for improving key rates and subsequently provide a relevant parameter tradeoff for the implementation of space-based MDI-QKD. We further investigate the heart of MDI-QKD, the two-photon interference considerations such as the frequency calibration and time synchronization technology against Doppler shift, and the way of performing the intensity optimization method in the dynamic and asymmetric channels. Our work can be used as a pathfinder to support decisions involving as the selection of the future quantum communication satellite missions.

quant-ph↗

arXiv2019

A Hierarchical Bayesian Approach to Neutron Spectrum Unfolding with Organic Scintillators

We propose a hierarchical Bayesian model and state-of-art Monte Carlo sampling method to solve the unfolding problem, i.e., to estimate the spectrum of an unknown neutron source from the data detected by an organic scintillator. Inferring neutron spectra is important for several applications, including nonproliferation and nuclear security, as it allows the discrimination of fission sources in special nuclear material (SNM) from other types of neutron sources based on the differences of the emitted neutron spectra. Organic scintillators interact with neutrons mostly via elastic scattering on hydrogen nuclei and therefore partially retain neutron energy information. Consequently, the neutron spectrum can be derived through deconvolution of the measured light output spectrum and the response functions of the scintillator to monoenergetic neutrons. The proposed approach is compared to three existing methods using simulated data to enable controlled benchmarks. We consider three sets of detector responses. One set corresponds to a 2.5 MeV monoenergetic neutron source and two sets are associated with (energy-wise) continuous neutron sources ($^{252}$Cf and $^{241}$AmBe). Our results show that the proposed method has similar or better unfolding performance compared to other iterative or Tikhonov regularization-based approaches in terms of accuracy and robustness against limited detection events, while requiring less user supervision. The proposed method also provides a posteriori confidence measures, which offers additional information regarding the uncertainty of the measurements and the extracted information.

physics.ins-det↗

arXiv2019

Identifying Solar Flare Precursors Using Time Series of SDO/HMI Images and SHARP Parameters

We present several methods towards construction of precursors, which show great promise towards early predictions, of solar flare events in this paper. A data pre-processing pipeline is built to extract useful data from multiple sources, Geostationary Operational Environmental Satellites (GOES) and Solar Dynamics Observatory (SDO)/Helioseismic and Magnetic Imager (HMI), to prepare inputs for machine learning algorithms. Two classification models are presented: classification of flares from quiet times for active regions and classification of strong versus weak flare events. We adopt deep learning algorithms to capture both the spatial and temporal information from HMI magnetogram data. Effective feature extraction and feature selection with raw magnetogram data using deep learning and statistical algorithms enable us to train classification models to achieve almost as good performance as using active region parameters provided in HMI/Space-Weather HMI-Active Region Patch (SHARP) data files. Case studies show a significant increase in the prediction score around 20 hours before strong solar flare events.

astro-ph.SR↗