The increasing deployment of AI models in critical applications has exposed them to significant risks from adversarial attacks. While adversarial vulnerabilities in 2D vision models have been extensively studied, the threat landscape for 3D generative models, such as Neural Radiance Fields (NeRF), remains underexplored. This work introduces \textit{AdvIRL}, a novel framework for crafting adversarial NeRF models using Instant Neural Graphics Primitives (Instant-NGP) and Reinforcement Learning. Unlike prior methods, \textit{AdvIRL} generates adversarial noise that remains robust under diverse 3D transformations, including rotations and scaling, enabling effective black-box attacks in real-world scenarios. Our approach is validated across a wide range of scenes, from small objects (e.g., bananas) to large environments (e.g., lighthouses). Notably, targeted attacks achieved high-confidence misclassifications, such as labeling a banana as a slug and a truck as a cannon, demonstrating the practical risks posed by adversarial NeRFs. Beyond attacking, \textit{AdvIRL}-generated adversarial models can serve as adversarial training data to enhance the robustness of vision systems. The implementation of \textit{AdvIRL} is publicly available at \url{https://github.com/Tommy-Nguyen-cpu/AdvIRL/tree/MultiView-Clean}, ensuring reproducibility and facilitating future research.
The rise of Artificial Intelligence and Large Language Models is driving increased GPU usage in data centers for complex training and inference tasks, impacting operational costs, energy demands, and the environmental footprint of large-scale computing infrastructures. This work addresses the online scheduling problem in GPU datacenters, which involves scheduling tasks without knowledge of their future arrivals. We focus on two objectives: minimizing GPU fragmentation and reducing power consumption. GPU fragmentation occurs when partial GPU allocations hinder the efficient use of remaining resources, especially as the datacenter nears full capacity. A recent scheduling policy, Fragmentation Gradient Descent (FGD), leverages a fragmentation metric to address this issue. Reducing power consumption is also crucial due to the significant power demands of GPUs. To this end, we propose PWR, a novel scheduling policy to minimize power usage by selecting power-efficient GPU and CPU combinations. This involves a simplified model for measuring power consumption integrated into a Kubernetes score plugin. Through an extensive experimental evaluation in a simulated cluster, we show how PWR, when combined with FGD, achieves a balanced trade-off between reducing power consumption and minimizing GPU fragmentation.
An evolving solution to address hallucination and enhance accuracy in large language models (LLMs) is Retrieval-Augmented Generation (RAG), which involves augmenting LLMs with information retrieved from an external knowledge source, such as the web. This paper profiles several RAG execution pipelines and demystifies the complex interplay between their retrieval and generation phases. We demonstrate that while exact retrieval schemes are expensive, they can reduce inference time compared to approximate retrieval variants because an exact retrieval model can send a smaller but more accurate list of documents to the generative model while maintaining the same end-to-end accuracy. This observation motivates the acceleration of the exact nearest neighbor search for RAG. In this work, we design Intelligent Knowledge Store (IKS), a type-2 CXL device that implements a scale-out near-memory acceleration architecture with a novel cache-coherent interface between the host CPU and near-memory accelerators. IKS offers 13.4-27.9x faster exact nearest neighbor search over a 512GB vector database compared with executing the search on Intel Sapphire Rapids CPUs. This higher search performance translates to 1.7-26.3x lower end-to-end inference time for representative RAG applications. IKS is inherently a memory expander; its internal DRAM can be disaggregated and used for other applications running on the server to prevent DRAM, which is the most expensive component in today's servers, from being stranded.
Background. The rapid growth of Language Models (LMs), particularly in code generation, requires substantial computational resources, raising concerns about energy consumption and environmental impact. Optimizing LMs inference for energy efficiency is crucial, and Small Language Models (SLMs) offer a promising solution to reduce resource demands. Aim. Our goal is to analyze the impact of deep learning runtime engines and execution providers on energy consumption, execution time, and computing-resource utilization from the point of view of software engineers conducting inference in the context of code SLMs. Method. We conducted a technology-oriented, multi-stage experimental pipeline using twelve code generation SLMs to investigate energy consumption, execution time, and computing-resource utilization across the configurations. Results. Significant differences emerged across configurations. CUDA execution provider configurations outperformed CPU execution provider configurations in both energy consumption and execution time. Among the configurations, TORCH paired with CUDA demonstrated the greatest energy efficiency, achieving energy savings from 37.99% up to 89.16% compared to other serving configurations. Similarly, optimized runtime engines like ONNX with the CPU execution provider achieved from 8.98% up to 72.04% energy savings within CPU-based configurations. Also, TORCH paired with CUDA exhibited efficient computing-resource utilization. Conclusions. Serving configuration choice significantly impacts energy efficiency. While further research is needed, we recommend the above configurations best suited to software engineers' requirements for enhancing serving efficiency in energy and performance.
Advancements in large language models (LLMs) have unlocked remarkable capabilities. While deploying these models typically requires server-grade GPUs and cloud-based inference, the recent emergence of smaller open-source models and increasingly powerful consumer devices have made on-device deployment practical. The web browser as a platform for on-device deployment is universally accessible, provides a natural agentic environment, and conveniently abstracts out the different backends from diverse device vendors. To address this opportunity, we introduce WebLLM, an open-source JavaScript framework that enables high-performance LLM inference entirely within web browsers. WebLLM provides an OpenAI-style API for seamless integration into web applications, and leverages WebGPU for efficient local GPU acceleration and WebAssembly for performant CPU computation. With machine learning compilers MLC-LLM and Apache TVM, WebLLM leverages optimized WebGPU kernels, overcoming the absence of performant WebGPU kernel libraries. Evaluations show that WebLLM can retain up to 80% native performance on the same device, with room to further close the gap. WebLLM paves the way for universally accessible, privacy-preserving, personalized, and locally powered LLM applications in web browsers. The code is available at: https://github.com/mlc-ai/web-llm.
Although Answer Set Programming (ASP) allows constraining neural-symbolic (NeSy) systems, its employment is hindered by the prohibitive costs of computing stable models and the CPU-bound nature of state-of-the-art solvers. To this end, we propose Answer Set Networks (ASN), a NeSy solver. Based on Graph Neural Networks (GNN), ASNs are a scalable approach to ASP-based Deep Probabilistic Logic Programming (DPPL). Specifically, we show how to translate ASPs into ASNs and demonstrate how ASNs can efficiently solve the encoded problem by leveraging GPU's batching and parallelization capabilities. Our experimental evaluations demonstrate that ASNs outperform state-of-the-art CPU-bound NeSy systems on multiple tasks. Simultaneously, we make the following two contributions based on the strengths of ASNs. Namely, we are the first to show the finetuning of Large Language Models (LLM) with DPPLs, employing ASNs to guide the training with logic. Further, we show the "constitutional navigation" of drones, i.e., encoding public aviation laws in an ASN for routing Unmanned Aerial Vehicles in uncertain environments.
SocialED is a comprehensive, open-source Python library designed to support social event detection (SED) tasks, integrating 19 detection algorithms and 14 diverse datasets. It provides a unified API with detailed documentation, offering researchers and practitioners a complete solution for event detection in social media. The library is designed with modularity in mind, allowing users to easily adapt and extend components for various use cases. SocialED supports a wide range of preprocessing techniques, such as graph construction and tokenization, and includes standardized interfaces for training models and making predictions. By integrating popular deep learning frameworks, SocialED ensures high efficiency and scalability across both CPU and GPU environments. The library is built adhering to high code quality standards, including unit testing, continuous integration, and code coverage, ensuring that SocialED delivers robust, maintainable software. SocialED is publicly available at \url{https://github.com/RingBDStack/SocialED} and can be installed via PyPI.
This paper presents a comprehensive evaluation of state-of-the-art object detection models, including YOLOv9, YOLOv10, and RT-DETR, for the task of weed detection in smart-spraying applications focusing on three classes: Sugarbeet, Monocot, and Dicot. The performance of these models is compared based on mean Average Precision (mAP) scores and inference times on different GPU and CPU devices. We consider various model variations, such as nano, small, medium, large alongside different image resolutions (320px, 480px, 640px, 800px, 960px). The results highlight the trade-offs between inference time and detection accuracy, providing valuable insights for selecting the most suitable model for real-time weed detection. This study aims to guide the development of efficient and effective smart spraying systems, enhancing agricultural productivity through precise weed management.
Strongly lensed quasars provide valuable insights into the rate of cosmic expansion, the distribution of dark matter in foreground deflectors, and the characteristics of quasar hosts. However, detecting them in astronomical images is difficult due to the prevalence of non-lensing objects. To address this challenge, we developed a generative deep learning model called VariLens, built upon a physics-informed variational autoencoder. This model seamlessly integrates three essential modules: image reconstruction, object classification, and lens modeling, offering a fast and comprehensive approach to strong lens analysis. VariLens is capable of rapidly determining both (1) the probability that an object is a lens system and (2) key parameters of a singular isothermal ellipsoid (SIE) mass model -- including the Einstein radius ($\theta_\mathrm{E}$), lens center, and ellipticity -- in just milliseconds using a single CPU. A direct comparison of VariLens estimates with traditional lens modeling for 20 known lensed quasars within the Subaru Hyper Suprime-Cam (HSC) footprint shows good agreement, with both results consistent within $2\sigma$ for systems with $\theta_\mathrm{E}<3$ arcsecs. To identify new lensed quasar candidates, we begin with an initial sample of approximately 80 million sources, combining HSC data with multiwavelength information from various surveys. After applying a photometric preselection aimed at locating $z>1.5$ sources, the number of candidates was reduced to 710,966. Subsequently, VariLens highlights 13,831 sources, each showing a high likelihood of being a lens. A visual assessment of these objects results in 42 promising candidates that await spectroscopic confirmation. These results underscore the potential of automated deep learning pipelines to efficiently detect and model strong lenses in large datasets.
Compressing integer keys is a fundamental operation among multiple communities, such as database management (DB), information retrieval (IR), and high-performance computing (HPC). Recent advances in \emph{learned indexes} have inspired the development of \emph{learned compressors}, which leverage simple yet compact machine learning (ML) models to compress large-scale sorted keys. The core idea behind learned compressors is to \emph{losslessly} encode sorted keys by approximating them with \emph{error-bounded} ML models (e.g., piecewise linear functions) and using a \emph{residual array} to guarantee accurate key reconstruction. While the concept of learned compressors remains in its early stages of exploration, our benchmark results demonstrate that an SIMD-optimized learned compressor can significantly outperform state-of-the-art CPU-based compressors. Drawing on our preliminary experiments, this vision paper explores the potential of learned data compression to enhance critical areas in DBMS and related domains. Furthermore, we outline the key technical challenges that existing systems must address when integrating this emerging methodology.
Large Language Models (LLMs) have become essential tools in natural language processing, finding large usage in chatbots such as ChatGPT and Gemini, and are a central area of research. A particular area of interest includes designing hardware specialized for these AI applications, with one such example being the neural processing unit (NPU). In 2023, Intel released the Intel Core Ultra processor with codename Meteor Lake, featuring a CPU, GPU, and NPU system-on-chip. However, official software support for the NPU through Intel's OpenVINO framework is limited to static model inference. The dynamic nature of autoregressive token generation in LLMs is therefore not supported out of the box. To address this shortcoming, we present NITRO (NPU Inference for Transformers Optimization), a Python-based framework built on top of OpenVINO to support text and chat generation on NPUs. In this paper, we discuss in detail the key modifications made to the transformer architecture to enable inference, some performance benchmarks, and future steps towards improving the package. The code repository for NITRO can be found here: https://github.com/abdelfattah-lab/nitro.
Personalized generative diffusion models, capable of synthesizing highly realistic images based on a few reference portraits, may pose substantial social, ethical, and legal risks via identity replication. Existing defense mechanisms rely on computationally intensive adversarial perturbations tailored to individual images, rendering them impractical for real-world deployment. This study introduces the Real-time Identity Defender (RID), a neural network designed to generate adversarial perturbations through a single forward pass, bypassing the need for image-specific optimization. RID achieves unprecedented efficiency, with defense times as low as 0.12 seconds on a single NVIDIA A100 80G GPU (4,400 times faster than leading methods) and 1.1 seconds per image on a standard Intel i9 CPU, making it suitable for edge devices such as smartphones. Despite its efficiency, RID achieves promising protection performance across visual and quantitative benchmarks, effectively mitigating identity replication risks. Our analysis reveals that RID's perturbations mimic the efficacy of traditional defenses while exhibiting properties distinct from natural noise, such as Gaussian perturbations. To enhance robustness, we extend RID into an ensemble framework that integrates multiple pre-trained text-to-image diffusion models, ensuring resilience against black-box attacks and post-processing techniques, including image compression and purification. Our model is envisioned to play a crucial role in safeguarding portrait rights, thereby preventing illegal and unethical uses.
With the rapid acceleration of ML/AI research in the last couple of years, the energy consumption of the Information and Communication Technology (ICT) domain has rapidly increased. As a major part of this energy consumption is due to users' workloads, it is evident that users need to be aware of the energy footprint of their applications. Compute Energy and Emissions Monitoring Stack (CEEMS) has been designed to address this issue. CEEMS can report energy consumption and equivalent emissions of user workloads in real time for HPC and cloud platforms alike. Besides CPU energy usage, it supports reporting energy usage of workloads on NVIDIA and AMD GPU accelerators. CEEMS has been built around the prominent open-source tools in the observability eco-system like Prometheus and Grafana. CEEMS has been designed to be extensible and it allows the Data Center (DC) operators to easily define the energy estimation rules of user workloads based on the underlying hardware. This paper explains the architectural overview of CEEMS, data sources that are used to measure energy usage and estimate equivalent emissions and potential use cases of CEEMS from operator and user perspectives. Finally, the paper will conclude by describing how CEEMS deployment on the Jean-Zay supercomputing platform is capable of monitoring more than 1400 nodes that have a daily job churn rate of around 20k jobs.
We applied machine learning to the entire data history of ESO's High Accuracy Radial Velocity Planet Searcher (HARPS) instrument. Our primary goal was to recover the physical properties of the observed objects, with a secondary emphasis on simulating spectra. We systematically investigated the impact of various factors on the accuracy and fidelity of the results, including the use of simulated data, the effect of varying amounts of real training data, network architectures, and learning paradigms. Our approach integrates supervised and unsupervised learning techniques within autoencoder frameworks. Our methodology leverages an existing simulation model that utilizes a library of existing stellar spectra in which the emerging flux is computed from first principles rooted in physics and a HARPS instrument model to generate simulated spectra comparable to observational data. We trained standard and variational autoencoders on HARPS data to predict spectral parameters and generate spectra. Our models excel at predicting spectral parameters and compressing real spectra, and they achieved a mean prediction error of approximately 50 K for effective temperatures, making them relevant for most astrophysical applications. Furthermore, the models predict metallicity ([M/H]) and surface gravity (log g) with an accuracy of approximately 0.03 dex and 0.04 dex, respectively, underscoring their broad applicability in astrophysical research. The models' computational efficiency, with processing times of 779.6 ms on CPU and 3.97 ms on GPU, makes them valuable for high-throughput applications like massive spectroscopic surveys and large archival studies. By achieving accuracy comparable to classical methods with significantly reduced computation time, our methodology enhances the scope and efficiency of spectroscopic analysis.
A collaboration between dataset owners and model owners is needed to facilitate effective machine learning (ML) training. During this collaboration, however, dataset owners and model owners want to protect the confidentiality of their respective assets (i.e., datasets, models and training code), with the dataset owners also caring about the privacy of individual users whose data is in their datasets. Existing solutions either provide limited confidentiality for models and training code, or suffer from privacy issues due to collusion. We present Citadel++, a collaborative ML training system designed to simultaneously protect the confidentiality of datasets, models and training code as well as the privacy of individual users. Citadel++ enhances differential privacy mechanisms to safeguard the privacy of individual user data while maintaining model utility. By employing Virtual Machine-level Trusted Execution Environments (TEEs) as well as the improved sandboxing and integrity mechanisms through OS-level techniques, Citadel++ effectively preserves the confidentiality of datasets, models and training code, and enforces our privacy mechanisms even when the models and training code have been maliciously designed. Our experiments show that Citadel++ provides model utility and performance while adhering to the confidentiality and privacy requirements of dataset owners and model owners, outperforming the state-of-the-art privacy-preserving training systems by up to 543x on CPU and 113x on GPU TEEs.
We present a novel machine learning (ML) method to accelerate conservative-to-primitive inversion, focusing on hybrid piecewise polytropic and tabulated equations of state. Traditional root-finding techniques are computationally expensive, particularly for large-scale relativistic hydrodynamics simulations. To address this, we employ feedforward neural networks (NNC2PS and NNC2PL), trained in PyTorch and optimized for GPU inference using NVIDIA TensorRT, achieving significant speedups with minimal accuracy loss. The NNC2PS model achieves $ L_1 $ and $ L_\infty $ errors of $ 4.54 \times 10^{-7} $ and $ 3.44 \times 10^{-6} $, respectively, while the NNC2PL model exhibits even lower error values. TensorRT optimization with mixed-precision deployment substantially accelerates performance compared to traditional root-finding methods. Specifically, the mixed-precision TensorRT engine for NNC2PS achieves inference speeds approximately 400 times faster than a traditional single-threaded CPU implementation for a dataset size of 1,000,000 points. Ideal parallelization across an entire compute node in the Delta supercomputer (Dual AMD 64 core 2.45 GHz Milan processors; and 8 NVIDIA A100 GPUs with 40 GB HBM2 RAM and NVLink) predicts a 25-fold speedup for TensorRT over an optimally-parallelized numerical method when processing 8 million data points. Moreover, the ML method exhibits sub-linear scaling with increasing dataset sizes. We release the scientific software developed, enabling further validation and extension of our findings. This work underscores the potential of ML, combined with GPU optimization and model quantization, to accelerate conservative-to-primitive inversion in relativistic hydrodynamics simulations.
Recent advances have extended the context window of frontier LLMs dramatically, from a few thousand tokens up to millions, enabling entire books and codebases to fit into context. However, the compute costs of inferencing long-context LLMs are massive and often prohibitive in practice. RAG offers an efficient and effective alternative: retrieve and process only the subset of the context most important for the current task. Although promising, recent work applying RAG to long-context tasks has two core limitations: 1) there has been little focus on making the RAG pipeline compute efficient, and 2) such works only test on simple QA tasks, and their performance on more challenging tasks is unclear. To address this, we develop an algorithm based on PageRank, a graph-based retrieval algorithm, which we call mixture-of-PageRanks (MixPR). MixPR uses a mixture of PageRank-based graph-retrieval algorithms implemented using sparse matrices for efficent, cheap retrieval that can deal with a variety of complex tasks. Our MixPR retriever achieves state-of-the-art results across a wide range of long-context benchmark tasks, outperforming both existing RAG methods, specialized retrieval architectures, and long-context LLMs despite being far more compute efficient. Due to using sparse embeddings, our retriever is extremely compute efficient, capable of embedding and retrieving millions of tokens within a few seconds and runs entirely on CPU.
With the approach of the High Luminosity Large Hadron Collider (HL-LHC) era set to begin particle collisions by the end of this decade, it is evident that the computational demands of traditional collision simulation methods are becoming increasingly unsustainable. Existing approaches, which rely heavily on first-principles Monte Carlo simulations for modeling event showers in calorimeters, are projected to require millions of CPU-years annually -- far exceeding current computational capacities. This bottleneck presents an exciting opportunity for advancements in computational physics by integrating deep generative models with quantum simulations. We propose a quantum-assisted hierarchical deep generative surrogate founded on a variational autoencoder (VAE) in combination with an energy conditioned restricted Boltzmann machine (RBM) embedded in the model's latent space as a prior. By mapping the topology of D-Wave's Zephyr quantum annealer (QA) into the nodes and couplings of a 4-partite RBM, we leverage quantum simulation to accelerate our shower generation times significantly. To evaluate our framework, we use Dataset 2 of the CaloChallenge 2022. Through the integration of classical computation and quantum simulation, this hybrid framework paves way for utilizing large-scale quantum simulations as priors in deep generative models.
The k-means algorithm can simplify large-scale spatial vectors, such as 2D geo-locations and 3D point clouds, to support fast analytics and learning. However, when processing large-scale datasets, existing k-means algorithms have been developed to achieve high performance with significant computational resources, such as memory and CPU usage time. These algorithms, though effective, are not well-suited for resource-constrained devices. In this paper, we propose a fast, memory-efficient, and cost-predictable k-means called Dask-means. We first accelerate k-means by designing a memory-efficient accelerator, which utilizes an optimized nearest neighbor search over a memory-tunable index to assign spatial vectors to clusters in batches. We then design a lightweight cost estimator to predict the memory cost and runtime of the k-means task, allowing it to request appropriate memory from devices or adjust the accelerator's required space to meet memory constraints, and ensure sufficient CPU time for running k-means. Experiments show that when simplifying datasets with scale such as $10^6$, Dask-means uses less than $30$MB of memory, achieves over $168$ times speedup compared to the widely-used Lloyd's algorithm. We also validate Dask-means on mobile devices, where it demonstrates significant speedup and low memory cost compared to other state-of-the-art (SOTA) k-means algorithms. Our cost estimator estimates the memory cost with a difference of less than $3\%$ from the actual ones and predicts runtime with an MSE up to $33.3\%$ lower than SOTA methods.
Constructing datasets representative of the target domain is essential for training effective machine learning models. Active learning (AL) is a promising method that iteratively extends training data to enhance model performance while minimizing data acquisition costs. However, current AL workflows often require human intervention and lack parallelism, leading to inefficiencies and underutilization of modern computational resources. In this work, we introduce PAL, an automated, modular, and parallel active learning library that integrates AL tasks and manages their execution and communication on shared- and distributed-memory systems using the Message Passing Interface (MPI). PAL provides users with the flexibility to design and customize all components of their active learning scenarios, including machine learning models with uncertainty estimation, oracles for ground truth labeling, and strategies for exploring the target space. We demonstrate that PAL significantly reduces computational overhead and improves scalability, achieving substantial speed-ups through asynchronous parallelization on CPU and GPU hardware. Applications of PAL to several real-world scenarios - including ground-state reactions in biomolecular systems, excited-state dynamics of molecules, simulations of inorganic clusters, and thermo-fluid dynamics - illustrate its effectiveness in accelerating the development of machine learning models. Our results show that PAL enables efficient utilization of high-performance computing resources in active learning workflows, fostering advancements in scientific research and engineering applications.