Related papers: MapLibre Tile: A Next Generation Vector Tile Forma…

Volumetric maps are widely used in robotics due to their desirable properties in applications such as path planning, exploration, and manipulation. Constant advances in mapping technologies are needed to keep up with the improvements in…

Multi-tiered large memory systems call for rethinking of memory profiling and migration because of the unique problems unseen in the traditional memory systems with smaller capacity and fewer tiers. We develop MTM, an…

We introduce the Byte Latent Transformer (BLT), a new byte-level LLM architecture that, for the first time, matches tokenization-based LLM performance at scale with significant improvements in inference efficiency and robustness. BLT…

As an emerging field, MS-based proteomics still requires software tools for efficiently storing and accessing experimental data. In this work, we focus on the management of LC-MS data, which are typically made available in standard…

We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale…

Vision-Language Tracking (VLT) aims to localize a target in video sequences using a visual template and language description. While textual cues enhance tracking potential, current datasets typically contain much more image data than text,…

Viewport prediction is a crucial aspect of tile-based 360 video streaming system. However, existing trajectory based methods lack of robustness, also oversimplify the process of information construction and fusion between different modality…

One of the most common ways to represent and share visual designs is with vector graphics. Designers working with vector graphics often explore layout alternatives and generate them by moving and resizing elements. The motivation for this…

Spectral line observations are an indispensable tool to remotely probe the physical and chemical conditions throughout the universe. Modelling their behaviour is a computational challenge that requires dedicated software. In this paper, we…

We propose MFT -- Multi-Flow dense Tracker -- a novel method for dense, pixel-level, long-term tracking. The approach exploits optical flows estimated not only between consecutive frames, but also for pairs of frames at logarithmically…

Machine Translation (MT) has greatly advanced over the years due to the developments in deep neural networks. However, the emergence of Large Language Models (LLMs) like GPT-4 and ChatGPT is introducing a new phase in the MT domain. In this…

Video Temporal Grounding (VTG), the task of localizing video segments from text queries, struggles in open-world settings due to limited dataset scale and semantic diversity, causing performance gaps between common and rare concepts. To…

To address the challenges associated with data processing at scale, we propose Dataverse, a unified open-source Extract-Transform-Load (ETL) pipeline for large language models (LLMs) with a user-friendly design at its core. Easy addition of…

Spatial dataflow accelerators are a promising direction for next-generation computer systems because they can reduce the memory bottlenecks of traditional von Neumann machines such as CPUs and GPUs. They organize computation around…

The input tokens to Vision Transformers carry little semantic meaning as they are defined as regular equal-sized patches of the input image, regardless of its content. However, processing uniform background areas of an image should not…

We present MT-lib, an efficient message transfer library for messages gather and scatter in benchmarks like Graph500 for Supercomputers. Our library includes MST version as well as new-MST version. The MT-lib is deliberately kept…

There has been significant research interest in Procedural Level Generation via Machine Learning (PLGML), applying ML techniques to automated level generation. One recent trend is in the direction of learning representations for level…

Large Language Models (LLMs) have emerged as powerful tools for automating and executing complex data tasks. However, their integration into more complex data workflows introduces significant management challenges. In response, we present…

Modern mixed (HTAP) workloads execute fast update-transactions and long-running analytical queries on the same dataset and system. In multi-version (MVCC) systems, such workloads result in many short-lived versions and long version-chains…

Large language models (LLMs) have advanced code generation from single-function tasks to competitive-programming problems, but existing multi-agent solutions either rely on costly large-scale (>30B) models or collapse when downsized to…