Related papers: LiZIP: An Auto-Regressive Compression Framework fo…
Highly distributed training of Deep Neural Networks (DNNs) on future compute platforms (offering 100 of TeraOps/s of computational capacity) is expected to be severely communication constrained. To overcome this limitation, new gradient…
Recent deep learning-based methods for lossy image compression achieve competitive rate-distortion performance through extensive end-to-end training and advanced architectures. However, emerging applications increasingly prioritize semantic…
Masked Autoregressive (MAR) models have emerged as a promising approach in image generation, expected to surpass traditional autoregressive models in computational efficiency by leveraging the capability of parallel decoding. However, their…
With the ever-increasing execution scale of high performance computing (HPC) applications, vast amounts of data are being produced by scientific research every day. Error-bounded lossy compression has been considered a very promising…
With the rapid adoption of machine learning (ML), a number of domains now use the approach of fine tuning models which were pre-trained on a large corpus of data. However, our experiments show that even fine-tuning on models like BERT can…
LiDAR Upsampling is a challenging task for the perception systems of robots and autonomous vehicles, due to the sparse and irregular structure of large-scale scene contexts. Recent works propose to solve this problem by converting LiDAR…
Protein inverse folding aims to identify viable amino acid sequences that can fold into given protein structures, enabling the design of novel proteins with desired functions for applications in drug discovery, enzyme engineering, and…
End-to-end perception and trajectory prediction from raw sensor data is one of the key capabilities for autonomous driving. Modular pipelines restrict information flow and can amplify upstream errors. Recent query-based, fully…
To realize low-latency spatial transmission system for immersive telepresence, there are two major problems: capturing dynamic 3D scene densely and processing them in real time. LiDAR sensors capture 3D in real time, but produce sparce…
Sparse LiDAR point clouds cause severe loss of detail of static structures and reduce the density of static points available for navigation. Reduced density can be detrimental to navigation under several scenarios. We observe that despite…
As high-performance computing architectures evolve, more scientific computing workflows are being deployed on advanced computing platforms such as GPUs. These workflows can produce raw data at extremely high throughputs, requiring urgent…
Recent advancements in multi-modal large language models have propelled the development of joint probabilistic models capable of both image understanding and generation. However, we have identified that recent methods suffer from loss of…
3D LiDAR sensors are essential for autonomous navigation, environmental monitoring, and precision mapping in remote sensing applications. To efficiently process the massive point clouds generated by these sensors, LiDAR data is often…
Machine-learning interatomic potentials (MLIPs) have become a mainstay in computationally-guided materials science, surpassing traditional force fields due to their flexible functional form and superior accuracy in reproducing physical…
Diffusion MRI is a modern neuroimaging modality with a unique ability to acquire microstructural information by measuring water self-diffusion at the voxel level. However, it generates huge amounts of data, resulting from a large number of…
We tackle the challenge of LiDAR-based place recognition, which traditionally depends on costly and time-consuming prior 3D maps. To overcome this, we first construct LiRSI-XA dataset, which encompasses approximately $110,000$ remote…
LiDAR point cloud compression is vital for autonomous systems to handle massive data from high-resolution sensors. While learned entropy modeling built upon octree structures yields high compression gains, it faces two critical bottlenecks:…
Recent models for learned image compression are based on autoencoders, learning approximately invertible mappings from pixels to a quantized latent representation. These are combined with an entropy model, a prior on the latent…
With the ability of providing direct and accurate enough range measurements, light detection and ranging (LiDAR) is playing an essential role in localization and detection for autonomous vehicles. Since single LiDAR suffers from hardware…
Atomistic simulation methods have evolved through successive computational levels, each building upon more fundamental approaches: from quantum mechanics to density functional theory (DFT), and subsequently, to machine learning interatomic…