The conventional virtual-to-physical address mapping scheme enables a virtual address to flexibly map to any physical address. This flexibility necessitates large data structures to store virtual-to-physical mappings, which incurs significantly high address translation latency and translation-induced interference in the memory hierarchy, especially in data-intensive workloads. Restricting the address mapping so that a virtual address can map to only a specific set of physical addresses can significantly reduce the overheads associated with the conventional address translation by making use of compact and more efficient translation structures. However, restricting the address mapping flexibility across the entire main memory severely limits data sharing across different processes and increases memory under-utilization. In this work, we propose Utopia, a new hybrid virtual-to-physical address mapping scheme that allows both flexible and restrictive hash-based address mapping schemes to co-exist in a system. The key idea of Utopia is to manage the physical memory using two types of physical memory segments: restrictive segments and flexible segments. A restrictive segment uses a restrictive, hash-based address mapping scheme to map the virtual addresses to only a specific set of physical addresses and enable faster address translation using compact and efficient translation structures. A flexible segment is similar to the conventional address mapping scheme and provides full virtual-to-physical address mapping flexibility. By mapping data to a restrictive segment, Utopia enables faster address translation with lower translation-induced interference whenever a flexible address mapping is not necessary. Our evaluation using 11 data-intensive workloads shows that Utopia improves performance by 24% on average in single-core workloads over the baseline four-level radix-tree page table design.
相關內容
Optical flow provides information on relative motion that is an important component in many computer vision pipelines. Neural networks provide high accuracy optical flow, yet their complexity is often prohibitive for application at the edge or in robots, where efficiency and latency play crucial role. To address this challenge, we build on the latest developments in event-based vision and spiking neural networks. We propose a new network architecture, inspired by Timelens, that improves the state-of-the-art self-supervised optical flow accuracy when operated both in spiking and non-spiking mode. To implement a real-time pipeline with a physical event camera, we propose a methodology for principled model simplification based on activity and latency analysis. We demonstrate high speed optical flow prediction with almost two orders of magnitude reduced complexity while maintaining the accuracy, opening the path for real-time deployments.
Recently, the performance of neural image compression (NIC) has steadily improved thanks to the last line of study, reaching or outperforming state-of-the-art conventional codecs. Despite significant progress, current NIC methods still rely on ConvNet-based entropy coding, limited in modeling long-range dependencies due to their local connectivity and the increasing number of architectural biases and priors, resulting in complex underperforming models with high decoding latency. Motivated by the efficiency investigation of the Tranformer-based transform coding framework, namely SwinT-ChARM, we propose to enhance the latter, as first, with a more straightforward yet effective Tranformer-based channel-wise auto-regressive prior model, resulting in an absolute image compression transformer (ICT). Through the proposed ICT, we can capture both global and local contexts from the latent representations and better parameterize the distribution of the quantized latents. Further, we leverage a learnable scaling module with a sandwich ConvNeXt-based pre-/post-processor to accurately extract more compact latent codes while reconstructing higher-quality images. Extensive experimental results on benchmark datasets showed that the proposed framework significantly improves the trade-off between coding efficiency and decoder complexity over the versatile video coding (VVC) reference encoder (VTM-18.0) and the neural codec SwinT-ChARM. Moreover, we provide model scaling studies to verify the computational efficiency of our approach and conduct several objective and subjective analyses to bring to the fore the performance gap between the adaptive image compression transformer (AICT) and the neural codec SwinT-ChARM.
The growing spread of robots for service and industrial purposes calls for versatile, intuitive and portable interaction approaches. In particular, in industrial environments, operators should be able to interact with robots in a fast, effective, and possibly effortless manner. To this end, reality enhancement techniques have been used to achieve efficient management and simplify interactions, in particular in manufacturing and logistics processes. Building upon this, in this paper we propose a system based on mixed reality that allows a ubiquitous interface for heterogeneous robotic systems in dynamic scenarios, where users are involved in different tasks and need to interact with different robots. By means of mixed reality, users can interact with a robot through manipulation of its virtual replica, which is always colocated with the user and is extracted when interaction is needed. The system has been tested in a simulated intralogistics setting, where different robots are present and require sporadic intervention by human operators, who are involved in other tasks. In our setting we consider the presence of drones and AGVs with different levels of autonomy, calling for different user interventions. The proposed approach has been validated in virtual reality, considering quantitative and qualitative assessment of performance and user's feedback.
Storing tabular data in a way that balances storage and query efficiencies is a long standing research question in the database community. While there are several lossless compression techniques in the literature, in this work we argue and show that a novel Deep Learned Data Mapping (or DeepMapping) abstraction, which relies on the impressive memorization capabilities of deep neural networks, can provide better storage cost, better latency, and better run-time memory footprint, all at the same time. Our proposed DeepMapping abstraction transforms a data set into multiple key-value mappings and constructs a multi-tasking neural network model that outputs the corresponding values for a given input key. In order to deal with the memorization errors, DeepMapping couples the learned neural network with a light-weight auxiliary data structure capable of correcting errors. The auxiliary structure further enables DeepMapping to efficiently deal with insertions, deletions, and updates, without having to re-train the mapping. Since the shape of the network has a significant impact on the overall size of the DeepMapping structure, we further propose a multi-task hybrid architecture search strategy to identify DeepMapping architectures that strike a desirable balance among memorization capacity, size, and efficiency. Extensive experiments with synthetic and benchmark datasets, including TPC-H and TPC-DS, demonstrated that the proposed DeepMapping approach can significantly reduce the latency of the key-based queries, while simultaneously improving both offline and run-time storage requirements against several cutting-edge competitors.
Temporal Conditioning Spiking Latent Variable Models of the Neural Response to Natural Visual Scenes
Developing computational models of neural response is crucial for understanding sensory processing and neural computations. Current state-of-the-art neural network methods use temporal filters to handle temporal dependencies, resulting in an unrealistic and inflexible processing flow. Meanwhile, these methods target trial-averaged firing rates and fail to capture important features in spike trains. This work presents the temporal conditioning spiking latent variable models (TeCoS-LVM) to simulate the neural response to natural visual stimuli. We use spiking neurons to produce spike outputs that directly match the recorded trains. This approach helps to avoid losing information embedded in the original spike trains. We exclude the temporal dimension from the model parameter space and introduce a temporal conditioning operation to allow the model to adaptively explore and exploit temporal dependencies in stimuli sequences in a natural paradigm. We show that TeCoS-LVM models can produce more realistic spike activities and accurately fit spike statistics than powerful alternatives. Additionally, learned TeCoS-LVM models can generalize well to longer time scales. Overall, while remaining computationally tractable, our model effectively captures key features of neural coding systems. It thus provides a useful tool for building accurate predictive computational accounts for various sensory perception circuits.
Rendering photorealistic and dynamically moving human heads is crucial for ensuring a pleasant and immersive experience in AR/VR and video conferencing applications. However, existing methods often struggle to model challenging facial regions (e.g., mouth interior, eyes, hair/beard), resulting in unrealistic and blurry results. In this paper, we propose {\fullname} ({\name}), a method that adopts the neural point representation as well as the neural volume rendering process and discards the predefined connectivity and hard correspondence imposed by mesh-based approaches. Specifically, the neural points are strategically constrained around the surface of the target expression via a high-resolution UV displacement map, achieving increased modeling capacity and more accurate control. We introduce three technical innovations to improve the rendering and training efficiency: a patch-wise depth-guided (shading point) sampling strategy, a lightweight radiance decoding process, and a Grid-Error-Patch (GEP) ray sampling strategy during training. By design, our {\name} is better equipped to handle topologically changing regions and thin structures while also ensuring accurate expression control when animating avatars. Experiments conducted on three subjects from the Multiface dataset demonstrate the effectiveness of our designs, outperforming previous state-of-the-art methods, especially in handling challenging facial regions.
A new control paradigm using angular momentum and foot placement as state variables in the linear inverted pendulum model has expanded the realm of possibilities for the control of bipedal robots. This new paradigm, known as the ALIP model, has shown effectiveness in cases where a robot's center of mass height can be assumed to be constant or near constant as well as in cases where there are no non-kinematic restrictions on foot placement. Walking up and down stairs violates both of these assumptions, where center of mass height varies significantly within a step and the geometry of the stairs restrict the effectiveness of foot placement. In this paper, we explore a variation of the ALIP model that allows the length of the virtual pendulum formed by the robot's stance foot and center of mass to follow smooth trajectories during a step. We couple this model with a control strategy constructed from a novel combination of virtual constraint-based control and a model predictive control algorithm to stabilize a stair climbing gait that does not soley rely on foot placement. Simulations on a 20-degree of freedom model of the Cassie biped in the SimMechanics simulation environment show that the controller is able to achieve periodic gait.
A long-lasting goal of robotics research is to operate robots safely, while achieving high performance which often involves fast motions. Traditional motor-driven systems frequently struggle to balance these competing demands. Addressing this trade-off is crucial for advancing fields such as manufacturing and healthcare, where seamless collaboration between robots and humans is essential. We introduce a four degree-of-freedom (DoF) tendon-driven robot arm, powered by pneumatic artificial muscles (PAMs), to tackle this challenge. Our new design features low friction, passive compliance, and inherent impact resilience, enabling rapid, precise, high-force, and safe interactions during dynamic tasks. In addition to fostering safer human-robot collaboration, the inherent safety properties are particularly beneficial for reinforcement learning, where the robot's ability to explore dynamic motions without causing self-damage is crucial. We validate our robotic arm through various experiments, including long-term dynamic motions, impact resilience tests, and assessments of its ease of control. On a challenging dynamic table tennis task, we further demonstrate our robot's capabilities in rapid and precise movements. By showcasing our new design's potential, we aim to inspire further research on robotic systems that balance high performance and safety in diverse tasks. Our open-source hardware design, software, and a large dataset of diverse robot motions can be found at //webdav.tuebingen.mpg.de/pamy2/.
The rising demand for electric vehicles (EVs) worldwide necessitates the development of robust and accessible charging infrastructure, particularly in developing countries where electricity disruptions pose a significant challenge. Earlier charging infrastructure optimization studies do not rigorously address such service disruption characteristics, resulting in suboptimal infrastructure designs. To address this issue, we propose an efficient simulation-based optimization model that estimates candidate stations' service reliability and incorporates it into the objective function and constraints. We employ the control variates (CV) variance reduction technique to enhance simulation efficiency. Our model provides a highly robust solution that buffers against uncertain electricity disruptions, even when candidate station service reliability is subject to underestimation or overestimation. Using a dataset from Surabaya, Indonesia, our numerical experiment demonstrates that the proposed model achieves a 13% higher average objective value compared to the non-robust solution. Furthermore, the CV technique successfully reduces the simulation sample size up to 10 times compared to Monte Carlo, allowing the model to solve efficiently using a standard MIP solver. Our study provides a robust and efficient solution for designing EV charging infrastructure that can thrive even in developing countries with uncertain electricity disruptions.
Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference. We study the impact of model size in this setting, focusing on Transformer models for NLP tasks that are limited by compute: self-supervised pretraining and high-resource machine translation. We first show that even though smaller Transformer models execute faster per iteration, wider and deeper models converge in significantly fewer steps. Moreover, this acceleration in convergence typically outpaces the additional computational overhead of using larger models. Therefore, the most compute-efficient training strategy is to counterintuitively train extremely large models but stop after a small number of iterations. This leads to an apparent trade-off between the training efficiency of large Transformer models and the inference efficiency of small Transformer models. However, we show that large models are more robust to compression techniques such as quantization and pruning than small models. Consequently, one can get the best of both worlds: heavily compressed, large models achieve higher accuracy than lightly compressed, small models.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191