arXiv subjects

Yumin Zhang

Publications and source records attributed to Yumin Zhang.

At least 19 recordsLinked to original sources

arXiv2026

VERDICT: Agreement Beats Pixel-Space Verification in Real-Document OCSR

Optical Chemical Structure Recognition (OCSR) converts 2D molecular depictions in the published literature into SMILES, and is increasingly important for constructing large-scale chemical training datasets. Automation at that scale requires identifying unreliable predictions in the absence of ground truth. Three families of label-free signals were compared on $263$ ACS journal depictions with verified ground truth: model confidence, re-rendering similarity, and agreement among recognizers. Pixel-space re-rendering performed little better than chance (AUROC $0.547$, $95\%$ CI $[0.465,0.629]$), and an oracle-tuned threshold on it reduced correct labels per image from $0.745$ to $0.205$. Agreement among four architecturally distinct recognizers instead reached an AUROC of $0.916$ ($[0.880,0.952]$). The two-of-four rule accepted $81.7\%$ of images at $88.8\%$ precision, the three-of-four rule $52.1\%$ at $98.5\%$. The same pattern held on CLEF-IP, UOB, and USPTO. This distinction is obscured on synthetic benchmarks, where re-rendered predictions naturally resemble their inputs. A substance filter removed $2{,}193$ false agreements on wildcards and R-group fragments, after which the three-of-four rule rejected all $68$ generic depictions. VERDICT was then applied to PMC Open Access, producing $6{,}146$ structure labels for $4{,}833$ molecules; chemist adjudication of $400$ released labels in two independent samples yielded precisions of $0.995$ for the three-of-four tier and $0.958$ for the two-of-four tier. VERDICT therefore enables validated labels for multimodal molecular databases linking structure images, machine-readable representations, and source-publication information. In SES AI's Molecular Universe platform, VERDICT further serves as an image-based interface for searching and retrieving molecular records.

cs.CV↗

arXiv2026

Real Data Closes Synthetic-to-Real Gap in Optical Chemical Structure Recognition

Millions of chemical structures appear in patents and papers only as drawings, and using that information at scale requires reading the drawings. OCSR appears nearly solved on synthetic images yet remains difficult on real documents: the starting recognizer, Qwen2.5-VL-7B, exceeds 91% accuracy on synthetic renders but falls below 16% on three real-world benchmarks (ACS, CLEF-IP, USPTO). To identify the main source of improvement, 21 recognizers were fine-tuned on mixtures of synthetically rendered structures and labeled real depictions from patents, journal figures, and hand-drawn collections, varying the vision language model (VLM) base, the fraction of real training data, and the vision-tower adaptation strategy. Labeled real training images make the largest difference. For Qwen2.5-VL, ACS exact match rises from 0.15 with no real data to 0.37 at 9.5% and 0.46 at 50.2%; a controlled experiment across three base models reproduces the trend. A vision-tower LoRA, in contrast, does nothing for Qwen (+0.00, paired p=1.00), substantially helps InternVL3-8B (+22.8 to +34.6 pt), and modestly helps GLM-4.1V-9B (+1.0 to +9.6 pt), so its value depends on the base model. The best configuration reaches 0.96 exact match on clean renders and 0.49, 0.65, 0.84, and 0.76 on ACS, CLEF-IP, UOB, and USPTO, respectively. Gaps between base models are largest without real data (0.21), shrink to 0.06 at 70% real data, and reorder the ranking; base model and real-data mixture must therefore be selected together. Small-scale experiments on handwritten image-to-LaTeX recognition and chart-to-table conversion show that base-model rankings also vary beyond chemistry. More generally, model and adaptation choices for visual structure recognition should be evaluated on the target task.

cs.LG↗

arXiv2026

Predictive Simulation of Interphases on Li Metal Surface

Interphases remain the least understood components in advanced batteries. Although their properties dictate whether a new battery chemistry could perform as designed, there has never been a reliable way to predict what an interphase could arise from a new electrolyte system due to the absence of atomistic level knowledge about interphasial formation process. In this work, we attempt to develop a simulation method that can universally predict interphasial chemistries formed on Li metal surface, so that the electrolyte engineering would no longer need lengthy Edisonian approaches. By combining a transferable universal polarizable force field and a universal machine learning force field, we simulate interphasial chemistry across chemically diverse electrolyte formulations, and successfully replicate the experimental observation that fluorinated solvents promote the formation of LiF-rich interphases, whereas interphases of more organic origin arise from conventional carbonate-based electrolytes. By directly capturing these spontaneous interfacial reactions behind these interphasial chemistries, our simulations establish molecular-level relationships between electrolyte chemistry, salt concentration, decomposition pathways, and SEI properties, and opens a route toward universal and high-throughput predictive simulation of interphases that is the foundation for AI-driven electrolyte discoveries.

cond-mat.mtrl-sci↗

arXiv2026

TeachPro: Multi-Label Qualitative Teaching Evaluation via Cross-View Graph Synergy and Semantic Anchored Evidence Encoding

Standardized Student Evaluation of Teaching often suffer from low reliability, restricted response options, and response distortion. Existing machine learning methods that mine open-ended comments usually reduce feedback to binary sentiment, which overlooks concrete concerns such as content clarity, feedback timeliness, and instructor demeanor, and provides limited guidance for instructional improvement.We propose TeachPro, a multi-label learning framework that systematically assesses five key teaching dimensions: professional expertise, instructional behavior, pedagogical efficacy, classroom experience, and other performance metrics. We first propose a Dimension-Anchored Evidence Encoder, which integrates three core components: (i) a pre-trained text encoder that transforms qualitative feedback annotations into contextualized embeddings; (ii) a prompt module that represents five teaching dimensions as learnable semantic anchors; and (iii) a cross-attention mechanism that aligns evidence with pedagogical dimensions within a structured semantic space. We then propose a Cross-View Graph Synergy Network to represent student comments. This network comprises two components: (i) a Syntactic Branch that extracts explicit grammatical dependencies from parse trees, and (ii) a Semantic Branch that models latent conceptual relations derived from BERT-based similarity graphs. BiAffine fusion module aligns syntactic and semantic units, while a differential regularizer disentangles embeddings to encourage complementary representations. Finally, a cross-attention mechanism bridges the dimension-anchored evidence with the multi-view comment representations. We also contribute a novel benchmark dataset featuring expert qualitative annotations and multi-label scores. Extensive experiments demonstrate that TeachPro offers superior diagnostic granularity and robustness across diverse evaluation settings.

cs.CL↗

arXiv2025

Bayesian Variable Selection on Small Sample Trial Data via Adaptive Posterior-Informed Shrinkage Prior

Identifying variables associated with clinical endpoints is of much interest in clinical trials. With the rapid growth of cell and gene therapy (CGT) and therapeutics for ultra-rare diseases, there is an urgent need for statistical methods that can detect meaningful associations under severe sample-size constraints. Motivated by data-borrowing strategies for historical controls, we propose the Adaptive Posterior-Informed Shrinkage Prior (APSP), a Bayesian approach that adaptively borrows information from external sources to improve variable-selection efficiency while preserving robustness across plausible scenarios. APSP builds upon existing Bayesian data borrowing frameworks, incorporating data-driven adaptive information selection, structure of mixture shrinkage informative priors and decision making with empirical null to enhance variable selection performances under small sample size. Extensive simulations show that APSP attains better efficiency relative to traditional and popular data-borrowing and Bayesian variable-selection methods while maintaining robustness under linear relationships. We further applied APSP to identify variables associated with peak C-peptide at Day 75 from the Clinical Islet Transplantation (CIT) Consortium study CIT06 by borrowing information from the study CIT07.

stat.ME↗

arXiv2025

A Visual-Inertial Motion Prior SLAM for Dynamic Environments

The Visual-Inertial Simultaneous Localization and Mapping (VI-SLAM) algorithms which are mostly based on static assumption are widely used in fields such as robotics, UAVs, VR, and autonomous driving. To overcome the localization risks caused by dynamic landmarks in most VI-SLAM systems, a robust visual-inertial motion prior SLAM system, named IDY-VINS, is proposed in this paper which effectively handles dynamic landmarks using inertial motion prior for dynamic environments to varying degrees. Specifically, potential dynamic landmarks are preprocessed during the feature tracking phase by the probabilistic model of landmarks' minimum projection errors which are obtained from inertial motion prior and epipolar constraint. Subsequently, a robust and self-adaptive bundle adjustment residual is proposed considering the minimum projection error prior for dynamic candidate landmarks. This residual is integrated into a sliding window based nonlinear optimization process to estimate camera poses, IMU states and landmark positions while minimizing the impact of dynamic candidate landmarks that deviate from the motion prior. Finally, a clean point cloud map without `ghosting effect' is obtained that contains only static landmarks. Experimental results demonstrate that our proposed system outperforms state-of-the-art methods in terms of localization accuracy and time cost by robustly mitigating the influence of dynamic landmarks.

cs.RO↗

arXiv2025

FedSCA: Federated Tuning with Similarity-guided Collaborative Aggregation for Heterogeneous Medical Image Segmentation

Transformer-based foundation models (FMs) have recently demonstrated remarkable performance in medical image segmentation. However, scaling these models is challenging due to the limited size of medical image datasets within isolated hospitals, where data centralization is restricted due to privacy concerns. These constraints, combined with the data-intensive nature of FMs, hinder their broader application. Integrating federated learning (FL) with foundation models (FLFM) fine-tuning offers a potential solution to these challenges by enabling collaborative model training without data sharing, thus allowing FMs to take advantage of a diverse pool of sensitive medical image data across hospitals/clients. However, non-independent and identically distributed (non-IID) data among clients, paired with computational and communication constraints in federated environments, presents an additional challenge that limits further performance improvements and remains inadequately addressed in existing studies. In this work, we propose a novel FLFM fine-tuning framework, \underline{\textbf{Fed}}erated tuning with \underline{\textbf{S}}imilarity-guided \underline{\textbf{C}}ollaborative \underline{\textbf{A}}ggregation (FedSCA), encompassing all phases of the FL process. This includes (1) specially designed parameter-efficient fine-tuning (PEFT) for local client training to enhance computational efficiency; (2) partial low-level adapter transmission for communication efficiency; and (3) similarity-guided collaborative aggregation (SGCA) on the server side to address non-IID issues. Extensive experiments on three FL benchmarks for medical image segmentation demonstrate the effectiveness of our proposed FedSCA, establishing new SOTA performance.

eess.IV↗

arXiv2024

Exemplar-condensed Federated Class-incremental Learning

We propose Exemplar-Condensed federated class-incremental learning (ECoral) to distil the training characteristics of real images from streaming data into informative rehearsal exemplars. The proposed method eliminates the limitations of exemplar selection in replay-based approaches for mitigating catastrophic forgetting in federated continual learning (FCL). The limitations particularly related to the heterogeneity of information density of each summarized data. Our approach maintains the consistency of training gradients and the relationship to past tasks for the summarized exemplars to represent the streaming data compared to the original images effectively. Additionally, our approach reduces the information-level heterogeneity of the summarized data by inter-client sharing of the disentanglement generative model. Extensive experiments show that our ECoral outperforms several state-of-the-art methods and can be seamlessly integrated with many existing approaches to enhance performance.

cs.LG↗

arXiv2024

Alternative sum rules and waterbed effects of Lorentz resonator system for sound absorption and transmission in a unidimensional waveguide

We investigate fundamental constraints on passive linear time-invariant acoustic systems through the developing alternative linear sum rules for sound absorption and transmission. Our approach, based on the Herglotz function method, yields integral identities without non-linear logarithmic terms or frequency weightings, providing clearer physical insights into system performance limits. The study focuses on unidimensional waveguides with Lorentz resonators, encompassing various practical acoustic structures. The developed sum rules are found to be particularly effective in predicting constraints on the average sound absorption coefficient for broadband absorbers operating in deep-subwavelength structures. Based on these rules, we demonstrate the waterbed effect in such systems, highlighting the inherent compromises between absorption efficiency, bandwidth, and device thickness. Through case studies of resonator arrays and membranes, we illustrate the practical implications of these new sum rules for designing optimal sound absorbers and isolators. The work concludes with a discussion on the challenges and future prospects in passive noise control, suggesting potential pathways to surpass current performance boundaries.

physics.class-ph↗

arXiv2024

Prototype Correlation Matching and Class-Relation Reasoning for Few-Shot Medical Image Segmentation

Few-shot medical image segmentation has achieved great progress in improving accuracy and efficiency of medical analysis in the biomedical imaging field. However, most existing methods cannot explore inter-class relations among base and novel medical classes to reason unseen novel classes. Moreover, the same kind of medical class has large intra-class variations brought by diverse appearances, shapes and scales, thus causing ambiguous visual characterization to degrade generalization performance of these existing methods on unseen novel classes. To address the above challenges, in this paper, we propose a \underline{\textbf{P}}rototype correlation \underline{\textbf{M}}atching and \underline{\textbf{C}}lass-relation \underline{\textbf{R}}easoning (i.e., \textbf{PMCR}) model. The proposed model can effectively mitigate false pixel correlation matches caused by large intra-class variations while reasoning inter-class relations among different medical classes. Specifically, in order to address false pixel correlation match brought by large intra-class variations, we propose a prototype correlation matching module to mine representative prototypes that can characterize diverse visual information of different appearances well. We aim to explore prototype-level rather than pixel-level correlation matching between support and query features via optimal transport algorithm to tackle false matches caused by intra-class variations. Meanwhile, in order to explore inter-class relations, we design a class-relation reasoning module to segment unseen novel medical objects via reasoning inter-class relations between base and novel classes. Such inter-class relations can be well propagated to semantic encoding of local query features to improve few-shot segmentation performance. Quantitative comparisons illustrates the large performance improvement of our model over other baseline methods.

cs.CV↗

arXiv2024

ExactDreamer: High-Fidelity Text-to-3D Content Creation via Exact Score Matching

Text-to-3D content creation is a rapidly evolving research area. Given the scarcity of 3D data, current approaches often adapt pre-trained 2D diffusion models for 3D synthesis. Among these approaches, Score Distillation Sampling (SDS) has been widely adopted. However, the issue of over-smoothing poses a significant limitation on the high-fidelity generation of 3D models. To address this challenge, LucidDreamer replaces the Denoising Diffusion Probabilistic Model (DDPM) in SDS with the Denoising Diffusion Implicit Model (DDIM) to construct Interval Score Matching (ISM). However, ISM inevitably inherits inconsistencies from DDIM, causing reconstruction errors during the DDIM inversion process. This results in poor performance in the detailed generation of 3D objects and loss of content. To alleviate these problems, we propose a novel method named Exact Score Matching (ESM). Specifically, ESM leverages auxiliary variables to mathematically guarantee exact recovery in the DDIM reverse process. Furthermore, to effectively capture the dynamic changes of the original and auxiliary variables, the LoRA of a pre-trained diffusion model implements these exact paths. Extensive experiments demonstrate the effectiveness of ESM in text-to-3D generation, particularly highlighting its superiority in detailed generation.

cs.CV↗

arXiv2024

From Sora What We Can See: A Survey of Text-to-Video Generation

With impressive achievements made, artificial intelligence is on the path forward to artificial general intelligence. Sora, developed by OpenAI, which is capable of minute-level world-simulative abilities can be considered as a milestone on this developmental path. However, despite its notable successes, Sora still encounters various obstacles that need to be resolved. In this survey, we embark from the perspective of disassembling Sora in text-to-video generation, and conducting a comprehensive review of literature, trying to answer the question, \textit{From Sora What We Can See}. Specifically, after basic preliminaries regarding the general algorithms are introduced, the literature is categorized from three mutually perpendicular dimensions: evolutionary generators, excellent pursuit, and realistic panorama. Subsequently, the widely used datasets and metrics are organized in detail. Last but more importantly, we identify several challenges and open problems in this domain and propose potential future directions for research and development.

cs.CV↗

arXiv2024

Enhancing GPU-acceleration in the Python-based Simulations of Chemistry Framework

We describe our contribution as industrial stakeholders to the existing open-source GPU4PySCF project (https: //github.com/pyscf/gpu4pyscf), a GPU-accelerated Python quantum chemistry package. We have integrated GPU acceleration into other PySCF functionality including Density Functional Theory (DFT), geometry optimization, frequency analysis, solvent models, and density fitting technique. Through these contributions, GPU4PySCF v1.0 can now be regarded as a fully functional and industrially relevant platform which we demonstrate in this work through a range of tests. When performing DFT calculations on modern GPU platforms, GPU4PySCF delivers 30 times speedup over a 32-core CPU node, resulting in approximately 90% cost savings for most DFT tasks. The performance advantages and productivity improvements have been found in multiple industrial applications, such as generating potential energy surfaces, analyzing molecular properties, calculating solvation free energy, identifying chemical reactions in lithium-ion batteries, and accelerating neural-network methods. With the improved design that makes it easy to integrate with the Python and PySCF ecosystem, GPU4PySCF is natural choice that we can now recommend for many industrial quantum chemistry applications.

physics.comp-ph↗

arXiv2024

A predictive machine learning force field framework for liquid electrolyte development

Despite the widespread applications of machine learning force fields (MLFF) in solids and small molecules, there is a notable gap in applying MLFF to simulate liquid electrolyte, a critical component of the current commercial lithium-ion battery. In this work, we introduce BAMBOO (\textbf{B}yteDance \textbf{A}I \textbf{M}olecular Simulation \textbf{Boo}ster), a predictive framework for molecular dynamics (MD) simulations, with a demonstration of its capability in the context of liquid electrolyte for lithium batteries. We design a physics-inspired graph equivariant transformer architecture as the backbone of BAMBOO to learn from quantum mechanical simulations. Additionally, we introduce an ensemble knowledge distillation approach and apply it to MLFFs to reduce the fluctuation of observations from MD simulations. Finally, we propose a density alignment algorithm to align BAMBOO with experimental measurements. BAMBOO demonstrates state-of-the-art accuracy in predicting key electrolyte properties such as density, viscosity, and ionic conductivity across various solvents and salt combinations. The current model, trained on more than 15 chemical species, achieves the average density error of 0.01 g/cm$^3$ on various compositions compared with experiment.

cond-mat.mtrl-sci↗

arXiv2023

Crucial Semantic Classifier-based Adversarial Learning for Unsupervised Domain Adaptation

Unsupervised Domain Adaptation (UDA), which aims to explore the transferrable features from a well-labeled source domain to a related unlabeled target domain, has been widely progressed. Nevertheless, as one of the mainstream, existing adversarial-based methods neglect to filter the irrelevant semantic knowledge, hindering adaptation performance improvement. Besides, they require an additional domain discriminator that strives extractor to generate confused representations, but discrete designing may cause model collapse. To tackle the above issues, we propose Crucial Semantic Classifier-based Adversarial Learning (CSCAL), which pays more attention to crucial semantic knowledge transferring and leverages the classifier to implicitly play the role of domain discriminator without extra network designing. Specifically, in intra-class-wise alignment, a Paired-Level Discrepancy (PLD) is designed to transfer crucial semantic knowledge. Additionally, based on classifier predictions, a Nuclear Norm-based Discrepancy (NND) is formed that considers inter-class-wise information and improves the adaptation performance. Moreover, CSCAL can be effortlessly merged into different UDA methods as a regularizer and dramatically promote their performance.

cs.CV↗

arXiv2022

Consecutive Knowledge Meta-Adaptation Learning for Unsupervised Medical Diagnosis

Deep learning-based Computer-Aided Diagnosis (CAD) has attracted appealing attention in academic researches and clinical applications. Nevertheless, the Convolutional Neural Networks (CNNs) diagnosis system heavily relies on the well-labeled lesion dataset, and the sensitivity to the variation of data distribution also restricts the potential application of CNNs in CAD. Unsupervised Domain Adaptation (UDA) methods are developed to solve the expensive annotation and domain gaps problem and have achieved remarkable success in medical image analysis. Yet existing UDA approaches only adapt knowledge learned from the source lesion domain to a single target lesion domain, which is against the clinical scenario: the new unlabeled target domains to be diagnosed always arrive in an online and continual manner. Moreover, the performance of existing approaches degrades dramatically on previously learned target lesion domains, due to the newly learned knowledge overwriting the previously learned knowledge (i.e., catastrophic forgetting). To deal with the above issues, we develop a meta-adaptation framework named Consecutive Lesion Knowledge Meta-Adaptation (CLKM), which mainly consists of Semantic Adaptation Phase (SAP) and Representation Adaptation Phase (RAP) to learn the diagnosis model in an online and continual manner. In the SAP, the semantic knowledge learned from the source lesion domain is transferred to consecutive target lesion domains. In the RAP, the feature-extractor is optimized to align the transferable representation knowledge across the source and multiple target lesion domains.

eess.IV↗

arXiv2022

BugListener: Identifying and Synthesizing Bug Reports from Collaborative Live Chats

In community-based software development, developers frequently rely on live-chatting to discuss emergent bugs/errors they encounter in daily development tasks. However, it remains a challenging task to accurately record such knowledge due to the noisy nature of interleaved dialogs in live chat data. In this paper, we first formulate the task of identifying and synthesizing bug reports from community live chats, and propose a novel approach, named BugListener, to address the challenges. Specifically, BugListener automates three sub-tasks: 1) Disentangle the dialogs from massive chat logs by using a Feed-Forward neural network; 2) Identify the bug-report dialogs from separated dialogs by modeling the original dialog to the graph-structured dialog and leveraging the graph neural network to learn the contextual information; 3) Synthesize the bug reports by utilizing the TextCNN model and Transfer Learning network to classify the sentences into three groups: observed behaviors (OB), expected behaviors (EB), and steps to reproduce the bug (SR). BugListener is evaluated on six open source projects. The results show that: for bug report identification, BugListener achieves the average F1 of 74.21%, improving the best baseline by 10.37%; and for bug report synthesis task, BugListener could classify the OB, EB, and SR sentences with the F1 of 67.37%, 87.14%, and 65.03%, improving the best baselines by 7.21%, 7.38%, 5.30%, respectively. A human evaluation also confirms the effectiveness of BugListener in generating relevant and accurate bug reports. These demonstrate the significant potential of applying BugListener in community-based software development, for promoting bug discovery and quality improvement.

cs.SE↗

arXiv2022

Distributed Design for Causal Inferences on Big Observational Data

A fundamental issue in causal inference for Big Observational Data is confounding due to covariate imbalances between treatment groups. This can be addressed by designing the data prior to analysis. Existing design methods, developed for traditional observational studies with single designers, can yield unsatisfactory designs with suboptimum covariate balance for Big Observational Data due to their inability to accommodate the massive dimensionality, heterogeneity, and volume of the Big Data. We propose a new framework for the distributed design of Big Observational Data amongst collaborative designers. Our framework first assigns subsets of the high-dimensional and heterogeneous covariates to multiple designers. The designers then summarize their covariates into lower-dimensional quantities, share their summaries with the others, and design the study in parallel based on their assigned covariates and the summaries they receive. The final design is selected by comparing balance measures for all covariates across the candidates. We perform simulation studies and analyze datasets from the 2016 Atlantic Causal Inference Conference Data Challenge to demonstrate the flexibility and power of our framework for constructing designs with good covariate balance from Big Observational Data.

stat.ME↗