Guodong Du, Zitao Fang, Jing Li, Junlin Li, Runhua Jiang, Shuyang Yu, Yifei Guo, Yangneng Chen, Sim Kuan Goh, Ho-Kin Tang, Daojing He, Honghai Liu, Min Zhang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Modern genomics faces challenges from “reference bias” in linear genomes, prompting the adoption of pangenomic graphs to integrate multi-allelic variations. Sequence-to-graph alignment is a fundermental procedure in many pangenomic analyses. However, the alignment in complex topologies like cyclic graphs and highly polymorphic regions remains difficult due to path branch explosion and computational complexity. In this paper, we propose GESA, a sequence-to-graph alignment framework for sequences in highly divergent genomic regions. GESA adopts a hybrid strategy integrating haplotype-guided path linearization to organize topological information, thereby reducing information loss and potential path branch explosion. It employs a Transformer-CNN contrastive learning strategy to further capture global and local genomic features, enabling the identification of genetic characteristics in complex regions across the entire genome. Finally, a hierarchical vector-space retrieval technique is used to simplify the complex graph alignment computation into linear alignments on multiple sequences through vector similarity retrieval algorithms. GESA achieves an alignment ratio of 0.79 in cyclic graphs within the complex MHC region, outperforming Minigraph and GraphAligner by$4.3 \times$and$3.3 \times$, respectively. GESA lays a foundation for the future development of deep learning model applications in the field of pangenome graph alignment. The GESA code is available at https://github.com/nudt-bioinfo/GESA.

Fine-tuning pre-trained models on targeted datasets enhances task-specific performance but often comes at the expense of generalization.Model merging techniques, which integrate multiple fine-tuned models into a single multi-task model through task arithmetic, offer a promising solution.However, task interference remains a fundamental challenge, leading to performance degradation and suboptimal merged models.Existing approaches largely overlooked the fundamental roles of neurons, their connectivity, and activation, resulting in a merging process and a merged model that does not consider how neurons relay and process information.In this work, we present the first study that relies on neuronal mechanisms for model merging.Specifically, we decomposed task-specific representations into two complementary neuronal subspaces that regulate input sensitivity and task adaptability.Leveraging this decomposition, we introduced NeuroMerging, a novel merging framework developed to mitigate task interference within neuronal subspaces, enabling training-free model fusion across diverse tasks.Through extensive experiments, we demonstrated that NeuroMerging achieved superior performance compared to existing methods on multi-task benchmarks across both natural language and vision domains.Our findings highlighted the importance of aligning neuronal mechanisms in model merging, offering new insights into mitigating task interference and improving knowledge fusion.Our project is available at https://ZzzitaoFang. github.io/projects/NeuroMerging/.

The execution of long-distance load-carrying tasks across multiple terrains remains a frequent requirement. These tasks often involve heavy loads, resulting in fatigue, decreased efficiency, and potential safety risks. To address this issue, this paper proposes a wearable centaur robot with wheel-legged transformation for human load-carrying assistance. The key feature of this robotic mechanism is the independent wheel-legged transformable structure, enabling transitions between the wheeled and legged modes. The wheeled mode ensures high load-carrying efficiency, while in the legged mode, the wheels are laid flat, transforming the ankle joint into a locked support surface that provides stable gait support. This design enables efficient and stable load carriage over complex terrains, all while preserving the natural gait of the user. Next, we develop a unified control framework for human-robot collaborative locomotion across different terrains, which includes velocity control based on an admittance model for the wheeled mode, gait control using a Bézier trajectory for the legged mode, and the transition between the two modes. The preliminary experiments include wheeled-mode, legged-mode, mode transition and obstacle crossing under human-robot collaborative locomotion, validating the proposed robot’s adaptability to different terrains while assisting with human load carriage.

BACKGROUND: The advent of Single Molecule Real-Time (SMRT) sequencing has overcome many limitations of second-generation sequencing, such as limited read lengths, PCR amplification biases. However, longer reads increase data volume exponentially and high error rates make many existing alignment tools inapplicable. Additionally, a single CPU's performance bottleneck restricts the effectiveness of alignment algorithms for SMRT sequencing. RESULTS: To address these challenges, we introduce ParaHAT, a parallel alignment algorithm for noisy long reads. ParaHAT utilizes vector-level, thread-level, process-level, and heterogeneous parallelism. We redesign the dynamic programming matrices layouts to eliminate data dependency in the base-level alignment, enabling effective vectorization. We further enhance computational speed through heterogeneous parallel technology and implement the algorithm for multi-node computing using MPI, overcoming the computational limits of a single node. CONCLUSIONS: Performance evaluations show that ParaHAT got a 10.03x speedup in base-level alignment, with a parallel acceleration ratio and weak scalability metric of 94.61 and 98.98% on 128 nodes, respectively.

Sequence alignment is the core of many bioinformatics tasks such as read mapping, genome assembly, variant detection and so on. With the advent of the third generation sequencing, classical dynamic programming-based alignment algorithms face challenges in efficiently handling these long reads. To address this issue, we present WFA-vect, a SIMD-based fast sequence alignment algorithm based on WFA. In WFA-vect, we introduce load synchronous and mask-based branch strategies to make the algorithm more suitable for vectorization. The load synchronous equalizes the load across different vector units to facilitate vectorization. The mask-based branch uses branch masking to bypass branch, avoiding pipeline hazards. To avoid binding the SIMD algorithm to specific hardware, we design a universal vectorization framework, which allows researchers to quickly port WFA-vect to other platforms without needing to understand the details of the algorithm. WFA-vect attains a peak speedup of 3.87× and 3.98× for data with error rates of 1% and 20%, respectively, compared to the scalar algorithm, while maintaining the alignment result consistent. The code and documentation of WFA-vect are publicly available at https://github.com/nudt-bioinfo/WFA-vect.

Molecular representation learning is widely used in the field of drug discovery, due to its ability to accurately capture the complex features of compounds in high-dimensional space. However, existing molecular representation learning models are prone to be influenced by spurious parts during distribution shifts (also known as out-of-distribution, or OOD), which results in models mistakenly treating these spurious parts as crucial features of molecules, thereby limiting the generalization capability of the models. To tackle this issue, a novel invariant molecular representation learning model, called Causal Invariant Hierarchical Molecular Representation Graph Neural Networks (CHiMoGNN), is proposed for OOD molecular property prediction. In CHiMoGNN, a Feature Enhancement (FE) module is designed to leverage the multi-level molecular parts to enhance the expression of invariant features, thereby enhancing the model’s capability to capture key molecular information. In addition, a Cartesian Product based Environmental Impact (EI) module is adopted to generate counterfactual samples with environmental diversity. Consequently, these samples are utilized to train a classifier that maintains consistent performance across various environments. Extensive experiments on seven real-world datasets demonstrate that CHiMoGNN outperforms 9 state-of-the-art models, achieving a 5.73% increase in average ROC-AUC, and the results also show that CHiMoGNN can effectively maintain generalization in various distribution shifts. Code and datasets are available at https://github.com/Chertuion/CHiMoGNN.

Spiking neural networks (SNNs) have gained prominence for their potential in neuromorphic computing and energy-efficient artificial intelligence, yet optimizing them remains a formidable challenge for gradient-based methods due to their discrete, spike-based computation. This paper attempts to tackle the challenges by introducing Cosine Annealing Differential Evolution (CADE), designed to modulate the mutation factor (F) and crossover rate (CR) of differential evolution (DE) for the SNN model, i.e., Spiking Element Wise (SEW) ResNet. Extensive empirical evaluations were conducted to analyze CADE. CADE showed a balance in exploring and exploiting the search space, resulting in accelerated convergence and improved accuracy compared to existing gradient-based and DE-based methods. Moreover, an initialization method based on a transfer learning setting was developed, pretraining on a source dataset (i.e., CIFAR-10) and fine-tuning the target dataset (i.e., CIFAR-100), to improve population diversity. It was found to further enhance CADE for SNN. Remarkably, CADE elevates the performance of the highest accuracy SEW model by an additional 0.52 percentage points, underscoring its effectiveness in fine-tuning and enhancing SNNs. These findings emphasize the pivotal role of a scheduler for F and CR adjustment, especially for DE-based SNN. Source Code on Github: https://github.com/Tank-Jiang/CADE4SNN.

While fine-tuning pretrained models has become common practice, these models often underperform outside their specific domains. Recently developed model merging techniques enable the direct integration of multiple models, each fine-tuned for distinct tasks, into a single model. This strategy promotes multitasking capabilities without requiring retraining on the original datasets. However, existing methods fall short in addressing potential conflicts and complex correlations between tasks, especially in parameter-level adjustments, posing a challenge in effectively balancing parameter competition across various tasks. This paper introduces an innovative technique named **PCB-Merging** (Parameter Competition Balancing), a *lightweight* and *training-free* technique that adjusts the coefficients of each parameter for effective model merging. PCB-Merging employs intra-balancing to gauge parameter significance within individual tasks and inter-balancing to assess parameter similarities across different tasks. Parameters with low importance scores are dropped, and the remaining ones are rescaled to form the final merged model. We assessed our approach in diverse merging scenarios, including cross-task, cross-domain, and cross-training configurations, as well as out-of-domain generalization. The experimental results reveal that our approach achieves substantial performance enhancements across multiple modalities, domains, model sizes, number of tasks, fine-tuning forms, and large language models, outperforming existing model merging methods.

Obtaining accurate and effective information for drug molecules is a crucial and challenging task, which relies on high-quality chemical knowledge. However, chemical knowledge has been accumulated over the past 100 years from various regions, laboratories, and experimental purposes, which contains a lot of noise and inconsistency, leading to the out-of-distribution (OOD) problem. OOD may results in weak robustness and unsatisfied performance. In order to solve OOD learning problem with noise, a novel benchmark: ADMEOOD is proposed, which is a systematic OOD dataset curator and specifically designed for drug property prediction. ADMEOOD screens 27 Absorption, Distribution, Metabolism and Excretion (ADME) drug properties from Chembl and relevant literature. This paper explicitly make distinctions between two kinds of OOD data shifts: Noise Shift and Concept Conflict Drift (CCD). Overall, ADME contains 6 domain annotations combined with noise, CCD and no shifts, resulting in 18 different splits in total. ADMEOOD provides performance results on a variety of SOTA OOD models. The results demonstrate a significant difference performance between in-distribution and OOD data. Moreover, Empirical Risk Minimization and other models exhibit distinct trends in different domains and measurement types. The ADMEOOD benchmark can be accessed via https://github.com/qweasdzxc-wsy/ADMEOOD/.

The high-quality pathological microscopic images are essential for physicians or pathologists to make a correct diagnosis. Image quality assessment (IQA) can quantify the visual distortion degree of images and guide the imaging system to improve image quality, thus raising the quality of pathological microscopic images. Current IQA methods are not ideal for pathological microscopy images due to their specificity. In this paper, we present deep learning-based blind image quality assessment model with saliency block and patch block for pathological microscopic images. The saliency block and patch block can handle the local and global distortions, respectively. To better capture the area of interest of pathologists when viewing pathological images, the saliency block is fine-tuned by eye movement data of pathologists. The patch block can capture lots of global information strongly related to image quality via the interaction between different image patches from different positions. The performance of the developed model is validated by the home-made Pathological Microscopic Image Quality Database under Screen and Immersion Scenarios (PMIQD-SIS) and cross-validated by the five public datasets. The results of ablation experiments demonstrate the contribution of the added blocks. The dataset and the corresponding code are publicly available at: https://github.com/mikugyf/PMIQD-SIS.

This paper presents a double-stage voltage control method based on model predictive control to address the voltage regulation in distribution network with high penetration of distributed generation. In the first stage, the operation times of transformer with on-load tap changer and switchable capacitor banks are minimized in hourly timescale. In the second stage, the controller minimizes the distributed generation curtailment while guaranteeing bus voltages within allowed limits with a control period of 1 min. In this paper, an analytical method is applied to calculate the voltage sensitivities with respect to power injections and tap changes. Numerical simulations of a modified IEEE-33 bus system are performed to validate the proposed method.