arXiv subjects

Dali Wang

Publications and source records attributed to Dali Wang.

15 recordsLinked to original sources

arXiv2026

Seeing Further and Wider: Joint Spatio-Temporal Enlargement for Micro-Video Popularity Prediction

Micro-video popularity prediction (MVPP) aims to forecast the future popularity of videos on online media, which is essential for applications such as content recommendation and traffic allocation. In real-world scenarios, it is critical for MVPP approaches to understand both the temporal dynamics of a given video (temporal) and its historical relevance to other videos (spatial). However, existing approaches sufer from limitations in both dimensions: temporally, they rely on sparse short-range sampling that restricts content perception; spatially, they depend on flat retrieval memory with limited capacity and low efficiency, hindering scalable knowledge utilization. To overcome these limitations, we propose a unified framework that achieves joint spatio-temporal enlargement, enabling precise perception of extremely long video sequences while supporting a scalable memory bank that can infinitely expand to incorporate all relevant historical videos. Technically, we employ a Temporal Enlargement driven by a frame scoring module that extracts highlight cues from video frames through two complementary pathways: sparse sampling and dense perception. Their outputs are adaptively fused to enable robust long-sequence content understanding. For Spatial Enlargement, we construct a Topology-Aware Memory Bank that hierarchically clusters historically relevant content based on topological relationships. Instead of directly expanding memory capacity, we update the encoder features of the corresponding clusters when incorporating new videos, enabling unbounded historical association without unbounded storage growth. Extensive experiments on three widely used MVPP benchmarks demonstrate that our method consistently outperforms 11 strong baselines across mainstream metrics, achieving robust improvements in both prediction accuracy and ranking consistency.

cs.MM↗

arXiv2025

PHASE: Physics-Integrated, Heterogeneity-Aware Surrogates for Scientific Simulations

Large-scale numerical simulations underpin modern scientific discovery but remain constrained by prohibitive computational costs. AI surrogates offer acceleration, yet adoption in mission-critical settings is limited by concerns over physical plausibility, trustworthiness, and the fusion of heterogeneous data. We introduce PHASE, a modular deep-learning framework for physics-integrated, heterogeneity-aware surrogates in scientific simulations. PHASE combines data-type-aware encoders for heterogeneous inputs with multi-level physics-based constraints that promote consistency from local dynamics to global system behavior. We validate PHASE on the biogeochemical (BGC) spin-up workflow of the U.S. Department of Energy's Energy Exascale Earth System Model (E3SM) Land Model (ELM), presenting-to our knowledge-the first scientifically validated AI-accelerated solution for this task. Using only the first 20 simulation years, PHASE infers a near-equilibrium state that otherwise requires more than 1,200 years of integration, yielding an effective reduction in required integration length by at least 60x. The framework is enabled by a pipeline for fusing heterogeneous scientific data and demonstrates strong generalization to higher spatial resolutions with minimal fine-tuning. These results indicate that PHASE captures governing physical regularities rather than surface correlations, enabling practical, physically consistent acceleration of land-surface modeling and other complex scientific workflows.

cs.LG↗

arXiv2025

Leveraging Hardware-Aware Computation in Mixed-Precision Matrix Multiply: A Tile-Centric Approach

General Matrix Multiplication (GEMM) is a critical operation underpinning a wide range of applications in high-performance computing (HPC) and artificial intelligence (AI). The emergence of hardware optimized for low-precision arithmetic necessitates a reevaluation of numerical algorithms to leverage mixed-precision computations, achieving improved performance and energy efficiency. This research introduces an adaptive mixed-precision GEMM framework that supports different precision formats at fine-grained tile/block levels. We utilize the PaRSEC runtime system to balance workloads across various architectures. The performance scales well on ARM CPU-based Fugaku supercomputer, Nvidia GPU-based A100 DGX, and AMD GPU-based Frontier supercomputer. This research aims to enhance computational efficiency and accuracy by bridging algorithmic advancements and hardware innovations, driving transformative progress in various applications.

cs.DC↗

arXiv2025

ORBIT-2: Scaling Exascale Vision Foundation Models for Weather and Climate Downscaling

Sparse observations and coarse-resolution climate models limit effective regional decision-making, underscoring the need for robust downscaling. However, existing AI methods struggle with generalization across variables and geographies and are constrained by the quadratic complexity of Vision Transformer (ViT) self-attention. We introduce ORBIT-2, a scalable foundation model for global, hyper-resolution climate downscaling. ORBIT-2 incorporates two key innovations: (1) Residual Slim ViT (Reslim), a lightweight architecture with residual learning and Bayesian regularization for efficient, robust prediction; and (2) TILES, a tile-wise sequence scaling algorithm that reduces self-attention complexity from quadratic to linear, enabling long-sequence processing and massive parallelism. ORBIT-2 scales to 10 billion parameters across 65,536 GPUs, achieving up to 4.1 exaFLOPS sustained throughput and 74--98% strong scaling efficiency. It supports downscaling to 0.9 km global resolution and processes sequences up to 4.2 billion tokens. On 7 km resolution benchmarks, ORBIT-2 achieves high accuracy with $R^2$ scores in the range of 0.98--0.99 against observational data.

cs.LG↗

arXiv2025

Kilometer-Scale E3SM Land Model Simulation over North America

The development of a kilometer-scale E3SM Land Model (km-scale ELM) is an integral part of the E3SM project, which seeks to advance energy-related Earth system science research with state-of-the-art modeling and simulation capabilities on exascale computing systems. Through the utilization of high-fidelity data products, such as atmospheric forcing and soil properties, the km-scale ELM plays a critical role in accurately modeling geographical characteristics and extreme weather occurrences. The model is vital for enhancing our comprehension and prediction of climate patterns, as well as their effects on ecosystems and human activities. This study showcases the first set of full-capability, km-scale ELM simulations over various computational domains, including simulations encompassing 21.6 million land gridcells, reflecting approximately 21.5 million square kilometers of North America at a 1 km x 1 km resolution. We present the largest km-scale ELM simulation using up to 100,800 CPU cores across 2,400 nodes. This continental-scale simulation is 300 times larger than any previous studies, and the computational resources used are about 400 times larger than those used in prior efforts. Both strong and weak scaling tests have been conducted, revealing exceptional performance efficiency and resource utilization. The km-scale ELM uses the common E3SM modeling infrastructure and a general data toolkit known as KiloCraft. Consequently, it can be readily adapted for both fully-coupled E3SM simulations and data-driven simulations over specific areas, ranging from a single gridcell to the entire North America.

cs.CE↗

arXiv2024

S3LLM: Large-Scale Scientific Software Understanding with LLMs using Source, Metadata, and Document

The understanding of large-scale scientific software poses significant challenges due to its diverse codebase, extensive code length, and target computing architectures. The emergence of generative AI, specifically large language models (LLMs), provides novel pathways for understanding such complex scientific codes. This paper presents S3LLM, an LLM-based framework designed to enable the examination of source code, code metadata, and summarized information in conjunction with textual technical reports in an interactive, conversational manner through a user-friendly interface. S3LLM leverages open-source LLaMA-2 models to enhance code analysis through the automatic transformation of natural language queries into domain-specific language (DSL) queries. Specifically, it translates these queries into Feature Query Language (FQL), enabling efficient scanning and parsing of entire code repositories. In addition, S3LLM is equipped to handle diverse metadata types, including DOT, SQL, and customized formats. Furthermore, S3LLM incorporates retrieval augmented generation (RAG) and LangChain technologies to directly query extensive documents. S3LLM demonstrates the potential of using locally deployed open-source LLMs for the rapid understanding of large-scale scientific computing software, eliminating the need for extensive coding expertise, and thereby making the process more efficient and effective. S3LLM is available at https://github.com/ResponsibleAILab/s3llm.

cs.SE↗

arXiv2021

OpenGraphGym-MG: Using Reinforcement Learning to Solve Large Graph Optimization Problems on MultiGPU Systems

Large scale graph optimization problems arise in many fields. This paper presents an extensible, high performance framework (named OpenGraphGym-MG) that uses deep reinforcement learning and graph embedding to solve large graph optimization problems with multiple GPUs. The paper uses a common RL algorithm (deep Q-learning) and a representative graph embedding (structure2vec) to demonstrate the extensibility of the framework and, most importantly, to illustrate the novel optimization techniques, such as spatial parallelism, graph-level and node-level batched processing, distributed sparse graph storage, efficient parallel RL training and inference algorithms, repeated gradient descent iterations, and adaptive multiple-node selections. This study performs a comprehensive performance analysis on parallel efficiency and memory cost that proves the parallel RL training and inference algorithms are efficient and highly scalable on a number of GPUs. This study also conducts a range of large graph experiments, with both generated graphs (over 30 million edges) and real-world graphs, using a single compute node (with six GPUs) of the Summit supercomputer. Good scalability in both RL training and inference is achieved: as the number of GPUs increases from one to six, the time of a single step of RL training and a single step of RL inference on large graphs with more than 30 million edges, is reduced from 316.4s to 54.5s, and 23.8s to 3.4s, respectively. The research results on a single node lay out a solid foundation for the future work to address graph optimization problems with a large number of GPUs across multiple nodes in the Summit.

cs.DC↗

arXiv2021

Geometrically Matched Multi-source Microscopic Image Synthesis Using Bidirectional Adversarial Networks

Microscopic images from multiple modalities can produce plentiful experimental information. In practice, biological or physical constraints under a given observation period may prevent researchers from acquiring enough microscopic scanning. Recent studies demonstrate that image synthesis is one of the popular approaches to release such constraints. Nonetheless, most existing synthesis approaches only translate images from the source domain to the target domain without solid geometric associations. To embrace this challenge, we propose an innovative model architecture, BANIS, to synthesize diversified microscopic images from multi-source domains with distinct geometric features. The experimental outcomes indicate that BANIS successfully synthesizes favorable image pairs on C. elegans microscopy embryonic images. To the best of our knowledge, BANIS is the first application to synthesize microscopic images that associate distinct spatial geometric features from multi-source domains.

eess.IV↗

arXiv2020

ElasticBroker: Combining HPC with Cloud to Provide Realtime Insights into Simulations

For large-scale scientific simulations, it is expensive to store raw simulation results to perform post-analysis. To minimize expensive I/O, "in-situ" analysis is often used, where analysis applications are tightly coupled with scientific simulations and can access and process the simulation results in memory. Increasingly, scientific domains employ Big Data approaches to analyze simulations for scientific discoveries. However, it remains a challenge to organize, transform, and transport data at scale between the two semantically different ecosystems (HPC and Cloud systems). In an effort to address these challenges, we design and implement the ElasticBroker software framework, which bridges HPC and Cloud applications to form an "in-situ" scientific workflow. Instead of writing simulation results to parallel file systems, ElasticBroker performs data filtering, aggregation, and format conversions to close the gap between an HPC ecosystem and a distinct Cloud ecosystem. To achieve this goal, ElasticBroker reorganizes simulation snapshots into continuous data streams and send them to the Cloud. In the Cloud, we deploy a distributed stream processing service to perform online data analysis. In our experiments, we use ElasticBroker to setup and execute a cross-ecosystem scientific workflow, which consists of a parallel computational fluid dynamics (CFD) simulation running on a supercomputer, and a parallel dynamic mode decomposition (DMD) analysis application running in a Cloud computing platform. Our results show that running scientific workflows consisting of decoupled HPC and Big Data jobs in their native environments with ElasticBroker, can achieve high quality of service, good scalability, and provide high-quality analytics for ongoing simulations.

cs.DC↗

arXiv2020

History-dependent percolation in two dimensions

We study the history-dependent percolation in two dimensions, which evolves in generations from standard bond-percolation configurations through iteratively removing occupied bonds. Extensive simulations are performed for various generations on periodic square lattices up to side length $L=4096$. From finite-size scaling, we find that the model undergoes a continuous phase transition, which, for any finite number of generations, falls into the universality of standard 2D percolation. At the limit of infinite generation, we determine the correlation-length exponent $1/ν=0.828(5)$ and the fractal dimension $d_{\rm f}=1.864\,4(7)$, which are not equal to $1/ν=3/4$ and $d_{\rm f}=91/48$ for 2D percolation. Hence, the transition in the infinite-generation limit falls outside the standard percolation universality and differs from the discontinuous transition of history-dependent percolation on random networks. Further, a crossover phenomenon is observed between the two universalities in infinite and finite generations.

cond-mat.stat-mech↗

arXiv2019

Investigating Channel Pruning through Structural Redundancy Reduction -- A Statistical Study

Most existing channel pruning methods formulate the pruning task from a perspective of inefficiency reduction which iteratively rank and remove the least important filters, or find the set of filters that minimizes some reconstruction errors after pruning. In this work, we investigate the channel pruning from a new perspective with statistical modeling. We hypothesize that the number of filters at a certain layer reflects the level of 'redundancy' in that layer and thus formulate the pruning problem from the aspect of redundancy reduction. Based on both theoretic analysis and empirical studies, we make an important discovery: randomly pruning filters from layers of high redundancy outperforms pruning the least important filters across all layers based on the state-of-the-art ranking criterion. These results advance our understanding of pruning and further testify to the recent findings that the structure of the pruned model plays a key role in the network efficiency as compared to inherited weights.

cs.CV↗

arXiv2019

Augmenting C. elegans Microscopic Dataset for Accelerated Pattern Recognition

The detection of cell shape changes in 3D time-lapse images of complex tissues is an important task. However, it is a challenging and tedious task to establish a comprehensive dataset to improve the performance of deep learning models. In the paper, we present a deep learning approach to augment 3D live images of the Caenorhabditis elegans embryo, so that we can further speed up the specific structural pattern recognition. We use an unsupervised training over unlabeled images to generate supplementary datasets for further pattern recognition. Technically, we used Alex-style neural networks in a generative adversarial network framework to generate new datasets that have common features of the C. elegans membrane structure. We also made the dataset available for a broad scientific community.

eess.IV↗

arXiv2019

FQL: An Extensible Feature Query Language and Toolkit on Searching Software Characteristics for HPC Applications

The amount of large-scale scientific computing software is dramatically increasing. In this work, we designed a new language, named feature query language (FQL), to collect and extract software features from a quick static code analysis. We designed and implemented an FQL toolkit to automatically detect and present the software features using an extensible query repository. Several large-scale, high performance computing (HPC) scientific codes have been used in the paper to demonstrate the HPC-related feature extraction and information collection. Although we emphasized the HPC features in the study, the toolkit can be easily extended to answer general software feature questions, such as coding pattern and hardware dependency.

cs.SE↗

arXiv2019

Speeding up convolutional networks pruning with coarse ranking

Channel-based pruning has achieved significant successes in accelerating deep convolutional neural network, whose pipeline is an iterative three-step procedure: ranking, pruning and fine-tuning. However, this iterative procedure is computationally expensive. In this study, we present a novel computationally efficient channel pruning approach based on the coarse ranking that utilizes the intermediate results during fine-tuning to rank the importance of filters, built upon state-of-the-art works with data-driven ranking criteria. The goal of this work is not to propose a single improved approach built upon a specific channel pruning method, but to introduce a new general framework that works for a series of channel pruning methods. Various benchmark image datasets (CIFAR-10, ImageNet, Birds-200, and Flowers-102) and network architectures (AlexNet and VGG-16) are utilized to evaluate the proposed approach for object classification purpose. Experimental results show that the proposed method can achieve almost identical performance with the corresponding state-of-the-art works (baseline) while our ranking time is negligibly short. In specific, with the proposed method, 75% and 54% of the total computation time for the whole pruning procedure can be reduced for AlexNet on CIFAR-10, and for VGG-16 on ImageNet, respectively. Our approach would significantly facilitate pruning practice, especially on resource-constrained platforms.

cs.CV↗

arXiv2018

Deep Reinforcement Learning of Cell Movement in the Early Stage of C. elegans Embryogenesis

Cell movement in the early phase of C. elegans development is regulated by a highly complex process in which a set of rules and connections are formulated at distinct scales. Previous efforts have shown that agent-based, multi-scale modeling systems can integrate physical and biological rules and provide new avenues to study developmental systems. However, the application of these systems to model cell movement is still challenging and requires a comprehensive understanding of regulation networks at the right scales. Recent developments in deep learning and reinforcement learning provide an unprecedented opportunity to explore cell movement using 3D time-lapse images. We present a deep reinforcement learning approach within an ABM system to characterize cell movement in C. elegans embryogenesis. Our modeling system captures the complexity of cell movement patterns in the embryo and overcomes the local optimization problem encountered by traditional rule-based, ABM that uses greedy algorithms. We tested our model with two real developmental processes: the anterior movement of the Cpaaa cell via intercalation and the rearrangement of the left-right asymmetry. In the first case, model results showed that Cpaaa's intercalation is an active directional cell movement caused by the continuous effects from a longer distance, as opposed to a passive movement caused by neighbor cell movements. This is because the learning-based simulation found that a passive movement model could not lead Cpaaa to the predefined destination. In the second case, a leader-follower mechanism well explained the collective cell movement pattern. These results showed that our approach to introduce deep reinforcement learning into ABM can test regulatory mechanisms by exploring cell migration paths in a reverse engineering perspective. This model opens new doors to explore large datasets generated by live imaging.

q-bio.QM↗