Related papers: BASEL (Buffering Architecture SpEcification Langua…
End-to-end multilingual ASR has become more appealing because of several reasons such as simplifying the training and deployment process and positive performance transfer from high-resource to low-resource languages. However, scaling up the…
Living systems are often described utilizing informational analogies. An important open question is whether information is merely a useful conceptual metaphor, or intrinsic to the operation of biological systems. To address this question,…
Current benchmarks for evaluating neural code models focus on only a small subset of programming languages, excluding many popular languages such as Go or Rust. To ameliorate this issue, we present the BabelCode framework for…
With the increasing popularity of recommendation systems (RecSys), the demand for compute resources in datacenters has surged. However, the model-wise resource allocation employed in current RecSys model serving architectures falls short in…
The research in hierarchical planning has made considerable progress in the last few years. Many recent systems do not rely on hand-tailored advice anymore to find solutions, but are supposed to be domain-independent systems that come with…
Backbone architectures of most binary networks are well-known floating point architectures such as the ResNet family. Questioning that the architectures designed for floating point networks would not be the best for binary networks, we…
Tokenization imposes a fixed granularity on the input text, freezing how a language model operates on data and how far in the future it predicts. Byte Pair Encoding (BPE) and similar schemes split text once, build a static vocabulary, and…
Bilevel optimization is characterized by a two-level optimization structure, where the upper-level problem is constrained by optimal lower-level solutions, and such structures are prevalent in real-world problems. The constraint by optimal…
A peer-to-peer application architecture is proposed that has the potential to eliminate the back-end servers for hosting services on the Internet. The proposed application architecture has been modeled as a distributed system for delivering…
Decision-making is a core engineering design activity that conveys the engineer's knowledge and translates it into courses of action. Capturing this form of knowledge can reap potential benefits for the engineering teams and enhance…
The design phase plays a vital role than all other phases in the software development. Software Architecture has to meet both the functional and non-functional quality requirements. The Evaluation of Architecture has to be performed, so…
Evaluating competing systems in a comparable way, i.e., benchmarking them, is an undeniable pillar of the scientific method. However, system performance is often summarized via a small number of metrics. The analysis of the evaluation…
Neural network architecture design mostly focuses on the new convolutional operator or special topological structure of network block, little attention is drawn to the configuration of stacking each block, called Block Stacking Style (BSS).…
Profiling techniques are used extensively at different parts of the computing stack to achieve many goals. One major goal is to make a piece of software execute more efficiently on a specific hardware platform, where efficiency spans…
There is a recent surge of interest in designing deep architectures based on the update steps in traditional algorithms, or learning neural networks to improve and replace traditional algorithms. While traditional algorithms have certain…
Driven by the goal of eradicating language barriers on a global scale, machine translation has solidified itself as a key focus of artificial intelligence research today. However, such efforts have coalesced around a small subset of…
State-of-the-art saliency prediction methods develop upon model architectures or loss functions; while training to generate one target saliency map. However, publicly available saliency prediction datasets can be utilized to create more…
Interpreting RNA-sequencing data requires identifying coordinated gene expression patterns that correspond to biological pathways. Standard factor models provide useful dimension reduction but typically ignore existing pathway knowledge or…
Understanding how data moves, transforms, and persists, known as data flow, is fundamental to reasoning in procedural tasks. Despite their fluency in natural and programming languages, large language models (LLMs), although increasingly…
Physical spaces are increasingly dense with networked devices, promising seamless coordination and ambient intelligence. Yet today, cloud-first architectures force all communication through wide-area networks regardless of physical…