Related papers: LOCO: Rethinking Objects for Network Memory

Traditional indoor scene synthesis methods often take a two-step approach: object selection and object arrangement. Current state-of-the-art object selection approaches are based on convolutional neural networks (CNNs) and can produce…

Flat combining (FC) is a synchronization paradigm in which a single thread, holding a global lock, collects requests by multiple threads for accessing a concurrent data structure and applies their combined requests to it. Although FC is…

Traditional discriminative computer vision relies predominantly on static projections, mapping input features to outputs in a single computational step. Although efficient, this paradigm lacks the iterative refinement and robustness…

Designing high-performance object detection architectures is a complex task, where traditional manual design is time-consuming and labor-intensive, and Neural Architecture Search (NAS) is computationally prohibitive. While recent approaches…

Multimodal LLM agents operating in complex game environments must continually reuse past experience to solve new tasks efficiently. In this work, we propose Echo, a transfer-oriented memory framework that enables agents to derive actionable…

Disaggregating memory from compute offers the opportunity to better utilize stranded memory in cloud data centers. It is important to cache data in the compute nodes and maintain cache coherence across multiple compute nodes. However, the…

This paper proposes a new neural architecture for collaborative ranking with implicit feedback. Our model, LRML (\textit{Latent Relational Metric Learning}) is a novel metric learning approach for recommendation. More specifically, instead…

Multi-object tracking (MOT) has profound applications in a variety of fields, including surveillance, sports analytics, self-driving, and cooperative robotics. Despite considerable advancements, existing MOT methodologies tend to falter…

Distributed Asynchronous Object Store (DAOS) is a novel software-defined object store leveraging Non-Volatile Memory (NVM) devices, designed for high performance. It provides a number of interfaces for applications to undertake I/O, ranging…

Due to the pervasive diffusion of personal mobile and IoT devices, many ``smart environments'' (e.g., smart cities and smart factories) will be, among others, generators of huge amounts of data. Currently, this is typically achieved through…

Recent advancements in Large Vision-Language Models built upon Large Language Models have established aligning visual features with LLM representations as the dominant paradigm. However, inherited LLM architectural designs introduce…

This paper is focused on code-domain non-orthogonal multiple access (CD-NOMA), which is an emerging paradigm to support massive connectivity for future machine-type wireless networks. We take a comparative approach to study two types of…

Large Language Models (LLMs) based on autoregressive, decoder-only Transformers generate text one token at a time, where a token represents a discrete unit of text. As each newly produced token is appended to the partial output sequence,…

Vision-Language Models (VLMs) have shown significant progress in open-set challenges. However, the limited availability of 3D datasets hinders their effective application in 3D scene understanding. We propose LOC, a general language-guided…

Event-based image representations are fundamentally different to traditional dense images. This poses a challenge to apply current state-of-the-art models for object detection as they are designed for dense images. In this work we evaluate…

There are numerous examples of problems in symbolic algebra in which the required storage grows far beyond the limitations even of the distributed RAM of a cluster. Often this limitation determines how large a problem one can solve in…

Recently, several Space-Time Memory based networks have shown that the object cues (e.g. video frames as well as the segmented object masks) from the past frames are useful for segmenting objects in the current frame. However, these methods…

In this paper, we aim to design an efficient real-time object detector that exceeds the YOLO series and is easily extensible for many object recognition tasks such as instance segmentation and rotated object detection. To obtain a more…

Vision-language-action (VLA) models for closed-loop robot control are typically cast under the Markov assumption, making them prone to errors on tasks requiring historical context. To incorporate memory, existing VLAs either retrieve from a…

I present Vanilla Object Orientation (VOO), a framework that composes classes from Tcl's native data structures -- lists and dictionaries -- rather than introducing additional framework infrastructure. VOO objects are plain Tcl lists with…