Related papers: KIS-S: A GPU-Aware Kubernetes Inference Simulator …

Open-ended tasks, such as coding problems that are common in computer science education, provide detailed insights into student knowledge. However, training large language models (LLMs) to simulate and predict possible student errors in…

Deep neural network (DNN)-based policy models, such as vision-language-action (VLA) models, excel at automating complex decision-making from multi-modal inputs. However, scaling these models greatly increases computational overhead,…

Autonomous driving has a natural bi-level structure. The goal of the upper behavioural layer is to provide appropriate lane change, speeding up, and braking decisions to optimize a given driving task. However, this layer can only indirectly…

The computational and memory demands of large language models for generative inference present significant challenges for practical deployment. One promising solution targeting offline inference is offloading-based batched inference, which…

How can we reliably simulate future driving scenarios under a wide range of ego driving behaviors? Recent driving world models, developed exclusively on real-world driving data composed mainly of safe expert trajectories, struggle to follow…

The growing demand for real-time processing tasks is driving the need for multi-model inference pipelines on edge devices. However, cost-effectively deploying these pipelines while optimizing Quality of Service (QoS) and costs poses…

Future networks must meet stringent requirements while operating within tight energy and carbon constraints. Current autoscaling mechanisms remain workload-centric and infrastructure-siloed, and are largely unaware of their environmental…

Residual neural networks are widely used in computer vision tasks. They enable the construction of deeper and more accurate models by mitigating the vanishing gradient problem. Their main innovation is the residual block which allows the…

Robotic imitation learning typically requires models that capture multimodal action distributions while operating at real-time control rates and accommodating multiple sensing modalities. Although recent generative approaches such as…

Transformer-based models are becoming more and more intelligent and are revolutionizing a wide range of human tasks. To support their deployment, AI labs offer inference services that consume hundreds of GWh of energy annually and charge…

Sequential robot manipulation tasks require finding collision-free trajectories that satisfy geometric constraints across multiple object interactions in potentially high-dimensional configuration spaces. Solving these problems in real-time…

High-performance computing systems are moving towards 2.5D and 3D memory hierarchies, based on High Bandwidth Memory (HBM) and Hybrid Memory Cube (HMC) to mitigate the main memory bottlenecks. This trend is also creating new opportunities…

The modeling of high-dimensional spatio-temporal processes presents a fundamental dichotomy between the probabilistic rigor of classical geostatistics and the flexible, high-capacity representations of deep learning. While Gaussian…

The speed of deep neural networks training has become a big bottleneck of deep learning research and development. For example, training GoogleNet by ImageNet dataset on one Nvidia K20 GPU needs 21 days. To speed up the training process, the…

We study the task of learning Multi-Index Models (MIMs) with label noise under the Gaussian distribution. A $K$-MIM is any function $f$ that only depends on a $K$-dimensional subspace. We focus on well-behaved MIMs with finite ranges that…

We present a multi-GPU extension of the 3D Gaussian Splatting (3D-GS) pipeline for scientific visualization. Building on previous work that demonstrated high-fidelity isosurface reconstruction using Gaussian primitives, we incorporate a…

In this work, we propose a computationally efficient algorithm for visual policy learning that leverages differentiable simulation and first-order analytical policy gradients. Our approach decouple the rendering process from the computation…

Embodied AI research is undergoing a shift toward vision-centric perceptual paradigms. While massively parallel simulators have catalyzed breakthroughs in proprioception-based locomotion, their potential remains largely untapped for…

AI methods, such as generative models and reinforcement learning, have recently been applied to combinatorial optimization (CO) problems, especially NP-hard ones. This paper compares such GPU-based methods with classical CPU-based methods…

GPUs are widely used to accelerate many important classes of workloads today. However, we observe that several important emerging classes of workloads, including simulation engines for deep reinforcement learning and dynamic neural…