We present PixelBrax, a set of continuous control tasks with pixel observations. We combine the Brax physics engine with a pure JAX renderer, allowing reinforcement learning (RL) experiments to run end-to-end on the GPU. PixelBrax can render observations over thousands of parallel environments and can run two orders of magnitude faster than existing benchmarks that rely on CPU-based rendering. Additionally, PixelBrax supports fully reproducible experiments through its explicit handling of any stochasticity within the environments and supports color and video distractors for benchmarking generalization. We open-source PixelBrax alongside JAX implementations of several RL algorithms at github.com/trevormcinroe/pixelbrax.
In this methods article, we provide a flexible but easy-to-use implementation of Direct Coupling Analysis (DCA) based on Boltzmann machine learning, together with a tutorial on how to use it. The package \texttt{adabmDCA 2.0} is available in different programming languages (C++, Julia, Python) usable on different architectures (single-core and multi-core CPU, GPU) using a common front-end interface. In addition to several learning protocols for dense and sparse generative DCA models, it allows to directly address common downstream tasks like residue-residue contact prediction, mutational-effect prediction, scoring of sequence libraries and generation of artificial sequences for sequence design. It is readily applicable to protein and RNA sequence data.
The burgeoning field of foundation models necessitates advanced data processing mechanisms capable of harnessing vast and valuable data with various types used by these models. Nevertheless, the current landscape presents unique challenges that traditional data processing frameworks struggle to handle effectively, particularly in handling the complexity of multimodal data. In response, we present Data-Juicer 2.0, a data processing system backed by 100+ data processing operators spanning text, image, video, and audio modalities, supporting more critical tasks including data analysis, synthesis, annotation, and foundation model post-training. With seamless compatibility and dedicated optimization for popular dataset hubs like Hugging Face and computing engines like Ray, it improves upon its predecessor in terms of usability, efficiency, and programmability. It features an easily accessible user interface layer that supports decoupled Python interactions, RESTful APIs, and conversational commands. It contains a new runtime layer optimized for adaptive execution and management across varying dataset scales, processing demands, and computational environments, while hiding unnecessary system details. Extensive empirical evaluations demonstrate Data-Juicer 2.0's remarkable performance and scalability, highlighting its capability to efficiently process TB-level data with 10k+ CPU cores. The system is publicly available and has been widely adopted in diverse research fields and real-world products such as Alibaba Cloud PAI. We actively maintain it and share insights from practical feedback, with the goal of facilitating research and application of next-generation foundation models.
Mixture-of-Experts (MoE) models, though highly effective for various machine learning tasks, face significant deployment challenges on memory-constrained devices. While GPUs offer fast inference, their limited memory compared to CPUs means not all experts can be stored on the GPU simultaneously, necessitating frequent, costly data transfers from CPU memory, often negating GPU speed advantages. To address this, we present DAOP, an on-device MoE inference engine to optimize parallel GPU-CPU execution. DAOP dynamically allocates experts between CPU and GPU based on per-sequence activation patterns, and selectively pre-calculates predicted experts on CPUs to minimize transfer latency. This approach enables efficient resource utilization across various expert cache ratios while maintaining model accuracy through a novel graceful degradation mechanism. Comprehensive evaluations across various datasets show that DAOP outperforms traditional expert caching and prefetching methods by up to 8.20x and offloading techniques by 1.35x while maintaining accuracy.
The dominance of large decoder-only language models has overshadowed encoder-decoder architectures, despite their fundamental efficiency advantages in sequence processing. For small language models (SLMs) - those with 1 billion parameters or fewer - our systematic analysis across GPU, CPU, and NPU platforms reveals that encoder-decoder architectures achieve 47% lower first-token latency and 4.7x higher throughput compared to decoder-only models on edge devices. These gains may be attributed to encoder-decoder's one-time input processing and efficient separation of understanding and generation phases. We introduce a novel knowledge distillation framework that enables encoder-decoder models to leverage capabilities from large scalable decoder-only teachers while preserving their architectural advantages, achieving up to 6 average performance points improvement across diverse tasks, with significant gains in asymmetric sequence tasks where input and output distributions can benefit from different processing approaches. When combined with modern advances like Rotary Positional Embeddings (RoPE) and Vision encoders, our systematic investigation demonstrates that encoder-decoder architectures provide a more practical path toward deploying capable language models in resource-constrained environments. Our findings challenge the prevailing trend toward decoder-only scaling, showing that architectural choices become increasingly crucial as parameter budgets decrease, particularly for on-device and edge deployments where computational efficiency is paramount.
Recognizing motions of tiny targets - only few dozen pixels - in cluttered backgrounds remains a fundamental challenge when standard feature-based or deep learning methods fail under scarce visual cues. We propose STMDNet, a model-based computational framework to Recognize motions of tiny targets at variable velocities under low-sampling frequency scenarios. STMDNet designs a novel dual-dynamics-and-correlation mechanism, harnessing ipsilateral excitation to integrate target cues and leakage-enhancing-type contralateral inhibition to suppress large-object and background motion interference. Moreover, we develop the first collaborative directional encoding-decoding strategy that determines the motion direction from only one correlation per spatial location, cutting computational costs to one-eighth of prior methods. Further, simply substituting the backbone of a strong STMD model with STMDNet raises AUC by 24%, yielding an enhanced STMDNet-F. Evaluations on real-world low sampling frequency datasets show state-of-the-art results, surpassing the deep learning baseline. Across diverse speeds, STMDNet-F improves mF1 by 19%, 16%, and 8% at 240Hz, 120Hz, and 60Hz, respectively, while STMDNet achieves 87 FPS on a single CPU thread. These advances highlight STMDNet as a next-generation backbone for tiny target motion pattern recognition and underscore its broader potential to revitalize model-based visual approaches in motion detection.
We introduce Glinthawk, an architecture for offline Large Language Model (LLM) inference. By leveraging a two-tiered structure, Glinthawk optimizes the utilization of the high-end accelerators ("Tier 1") by offloading the attention mechanism to lower-end compute tier ("Tier 2"). This separation allows the memory demand of the attention, known as the key-value cache, to scale independently from the model weights, enabling larger batch sizes and more efficient accelerator usage. Prototyped with NVIDIA T4 GPUs and standard CPU VMs, Glinthawk improves throughput by $5.9\times$ and reduces cost of generation by $2.8\times$, compared to paged attention baselines. For long sequence lengths, it achieves $16.3\times$ throughput improvement at $2.4\times$ less cost. Our evaluation shows that this architecture can tolerate moderate network latency with minimal performance degradation, making it highly effective for latency-tolerant, throughput-focused applications such as batch processing. The prototype is publicly available at https://github.com/microsoft/glinthawk.
Designing efficient neural networks for embedded devices is a critical challenge, particularly in applications requiring real-time performance, such as aerial imaging with drones and UAVs for emergency responses. In this work, we introduce TakuNet, a novel light-weight architecture which employs techniques such as depth-wise convolutions and an early downsampling stem to reduce computational complexity while maintaining high accuracy. It leverages dense connections for fast convergence during training and uses 16-bit floating-point precision for optimization on embedded hardware accelerators. Experimental evaluation on two public datasets shows that TakuNet achieves near-state-of-the-art accuracy in classifying aerial images of emergency situations, despite its minimal parameter count. Real-world tests on embedded devices, namely Jetson Orin Nano and Raspberry Pi, confirm TakuNet's efficiency, achieving more than 650 fps on the 15W Jetson board, making it suitable for real-time AI processing on resource-constrained platforms and advancing the applicability of drones in emergency scenarios. The code and implementation details are publicly released.
Swarm intelligence optimization algorithms have gained significant attention due to their ability to solve complex optimization problems. However, the efficiency of optimization in large-scale problems limits the use of related methods. This paper presents a GPU-accelerated version of the Multi-Guiding Spark Fireworks Algorithm (MGFWA), which significantly improves the computational efficiency compared to its traditional CPU-based counterpart. We benchmark the GPU-MGFWA on several neural network black-box optimization problems and demonstrate its superior performance in terms of both speed and solution quality. By leveraging the parallel processing power of modern GPUs, the proposed GPU-MGFWA results in faster convergence and reduced computation time for large-scale optimization tasks. The proposed implementation offers a promising approach to accelerate swarm intelligence algorithms, making them more suitable for real-time applications and large-scale industrial problems. Source code is released at https://github.com/mxxxr/MGFWA.
Dataset deduplication plays a crucial role in enhancing data quality, ultimately improving training performance and efficiency of LLMs. A commonly used method for data deduplication is the MinHash LSH algorithm. Recently, NVIDIA introduced a GPU-based MinHash LSH deduplication method, but it remains suboptimal, leaving room for further improvement in processing efficiency. This paper proposes a GPU-accelerated deduplication framework \sys that optimizes MinHash LSH for GPU clusters and leverages computationally efficient and partially reusable non-cryptographic hash functions. \sys significantly outperforms the CPU-based deduplication tool included in SlimPajama by up to 58.3 times and the GPU-based deduplication tool included in NVIDIA NeMo Curator by up to 8.6 times when processing 1 million documents with a node of four GPUs. Deduplication of 1.2 trillion tokens is completed in just 5.1 hours in a four-node, 16-GPU environment. The related code is publicly available on GitHub (https://github.com/mcrl/FED).
Supervised machine learning techniques have shown promising results in code analysis and optimization problems. However, a learning-based solution can be brittle because minor changes in hardware or application workloads -- such as facing a new CPU architecture or code pattern -- may jeopardize decision accuracy, ultimately undermining model robustness. We introduce Prom, an open-source library to enhance the robustness and performance of predictive models against such changes during deployment. Prom achieves this by using statistical assessments to identify test samples prone to mispredictions and using feedback on these samples to improve a deployed model. We showcase Prom by applying it to 13 representative machine learning models across 5 code analysis and optimization tasks. Our extensive evaluation demonstrates that Prom can successfully identify an average of 96% (up to 100%) of mispredictions. By relabeling up to 5% of the Prom-identified samples through incremental learning, Prom can help a deployed model achieve a performance comparable to that attained during its model training phase.
In recent years, anchor and hash-based multi-view clustering methods have gained attention for their efficiency and simplicity in handling large-scale data. However, existing methods often overlook the interactions among multi-view data and higher-order cooperative relationships during projection, negatively impacting the quality of hash representation in low-dimensional spaces, clustering performance, and sensitivity to noise. To address this issue, we propose a novel approach named Tensor-Interacted Projection and Cooperative Hashing for Multi-View Clustering(TPCH). TPCH stacks multiple projection matrices into a tensor, taking into account the synergies and communications during the projection process. By capturing higher-order multi-view information through dual projection and Hamming space, TPCH employs an enhanced tensor nuclear norm to learn more compact and distinguishable hash representations, promoting communication within and between views. Experimental results demonstrate that this refined method significantly outperforms state-of-the-art methods in clustering on five large-scale multi-view datasets. Moreover, in terms of CPU time, TPCH achieves substantial acceleration compared to the most advanced current methods. The code is available at \textcolor{red}{\url{https://github.com/jankin-wang/TPCH}}.
Irreducible Cartesian tensors (ICTs) play a crucial role in the design of equivariant graph neural networks, as well as in theoretical chemistry and chemical physics. Meanwhile, the design space of available linear operations on tensors that preserve symmetry presents a significant challenge. The ICT decomposition and a basis of this equivariant space are difficult to obtain for high-rank tensors. After decades of research, Bonvicini (2024) recently achieves an explicit ICT decomposition for $n=5$ with factorial time/space complexity. In this work we, for the first time, obtains decomposition matrices for ICTs up to rank $n=9$ with reduced and affordable complexity, by constructing what we call path matrices. The path matrices are obtained via performing chain-like contractions with Clebsch-Gordan matrices following the parentage scheme. We prove and leverage that the concatenation of path matrices is an orthonormal change-of-basis matrix between the Cartesian tensor product space and the spherical direct sum spaces. Furthermore, we identify a complete orthogonal basis for the equivariant space, rather than a spanning set (Pearce-Crump, 2023), through this path matrices technique. To the best of our knowledge, this is also the first analytic, rather than numerical, method for theoretically obtaining arbitrary rank orthogonal ICT decomposition matrices and orthogonal equivariant bases. We further extend our result to the arbitrary tensor product and direct sum spaces, enabling free design between different spaces while keeping symmetry. The Python code is available at https://github.com/ShihaoShao-GH/ICT-decomposition-and-equivariant-bases, where the $n=6,\dots,9$ ICT decomposition matrices are obtained in 1s, 3s, 11s, and 4m32s on 28-cores Intel(R) Xeon(R) Gold 6330 CPU @ 2.00GHz, respectively.
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.
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.
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.