Related papers: Active Switching: Packet Steering Flow Annotations
Transformers have achieved remarkable success across diverse domains, but their monolithic architecture presents challenges in interpretability, adaptability, and scalability. This paper introduces a novel modular Transformer architecture…
Most state-of-the-art instance segmentation methods rely on large amounts of pixel-precise ground-truth annotations for training, which are expensive to create. Interactive segmentation networks help generate such annotations based on an…
This paper presents a unified framework for analyzing the input-output behavior of discrete time complex networks viewed as open systems. Importantly, we focus on systems that are inherently modeled in discrete time-such as opinion…
State-of-the-art computer vision approaches rely on huge amounts of annotated data. The collection of such data is a time consuming process since it is mainly performed by humans. The literature shows that semi-automatic annotation…
High-quality system-level message flow specifications can lead to comprehensive validation of system-on-chip (SoC) designs. We propose a disruptive method that utilizes an attention mechanism to produce accurate flow specifications from SoC…
Network latency severely impacts the performance of applications running on supercomputers. Adaptive routing algorithms route packets over different available paths to reduce latency and improve network utilization. However, if a switch…
Feature interaction is a core ingredient in ranking models for large-scale recommender systems, yet making it both expressive and efficiently scalable remains challenging. Exhaustive pairwise interaction is powerful but incurs quadratic…
Multi-agent systems built on large language models (LLMs) require many coordination choices that are difficult to fix a priori: which skill protocol to invoke, which agent role should perform a subtask, which model to bind to each role, how…
We introduce GateSkip, a simple residual-stream gating mechanism that enables token-wise layer skipping in decoder-only LMs. Each Attention/MLP branch is equipped with a sigmoid-linear gate that condenses the branch's output before it…
Unsupervised and open-vocabulary 3D object detection has recently gained attention, particularly in autonomous driving, where reducing annotation costs and recognizing unseen objects are critical for both safety and scalability. However,…
Annotating instance masks is time-consuming and labor-intensive. A promising solution is to predict contours using a deep learning model and then allow users to refine them. However, most existing methods focus on in-domain scenarios,…
The next generation Internet is deemed to be heterogeneous in nature and mobile devices connected to the Internet are expected to be equipped with different wireless network interfaces. As seamless mobility is important in such networks,…
Distributed storage systems typically maintain strong consistency between data nodes and metadata nodes by adopting ordered writes: 1) first installing data; 2) then updating metadata to make data visible.We propose SwitchDelta to…
Next to scaling considerations, architectural design choices profoundly shape the solution space of transformers. In this work, we analyze the solutions simple transformer blocks implement when tackling the histogram task: counting items in…
Modern warehouse automation systems rely on fleets of intelligent robots that generate vast amounts of data -- most of which remains unannotated. This paper develops a self-supervised domain adaptation pipeline that leverages real-world,…
We establish mean-field limits for large-scale random-access networks with buffer dynamics and arbitrary interference graphs. While saturated-buffer scenarios have been widely investigated and yield useful throughput estimates for…
Networking data analytics is increasingly used for enhanced network visibility and controllability. We draw the similarities between the Software Defined Networking (SDN) architecture and the MapReduce programming model. Inspired by the…
The digitisation campaigns carried out by libraries and archives in recent years have facilitated access to documents in their collections. However, exploring and exploiting these documents remain difficult tasks due to the sheer quantity…
Recent advances in interpretability suggest we can project weights and hidden states of transformer-based language models (LMs) to their vocabulary, a transformation that makes them more human interpretable. In this paper, we investigate LM…
In the online packet buffering problem (also known as the unweighted FIFO variant of buffer management), we focus on a single network packet switching device with several input ports and one output port. This device forwards unit-size,…