Related papers: Just-In-Time Piecewise-Linear Semantics for ReLU-t…

To remove redundant components of large language models (LLMs) without incurring significant computational costs, this work focuses on single-shot pruning without a retraining phase. We simplify the pruning process for Transformer-based…

Many modern virtual machines, such as JVMs, .NET Framework, and V8, employ a just-in-time (JIT) compiler to achieve their high-performance. There are two major compilation strategies; trace-based compilation and method-based compilation.…

Training large language models (LLMs) requires substantial compute and energy. At the same time, renewable energy sources regularly produce more electricity than the grid can absorb, leading to curtailment, the deliberate reduction of clean…

Large language models (LLMs) have proven to be highly effective across various natural language processing tasks. However, their large number of parameters poses significant challenges for practical deployment. Pruning, a technique aimed at…

Large Language Models (LLMs) demonstrate strong abilities in common-sense reasoning and interactive decision-making, but often struggle with complex, long-horizon planning tasks. Recent techniques have sought to structure LLM outputs using…

We present a parallel variant of Pruned Landmark Labelling (PLL) that is optimised for the preprocessing of hub labels on directed acyclic graphs (DAGs). This method was developed during a seminar at the Karlsruhe Institute of Technology…

Prompt-tuning methods for Continual Learning (CL) freeze a large pre-trained model and train a few parameter vectors termed prompts. Most of these methods organize these vectors in a pool of key-value pairs and use the input image as query…

Speaker intent detection and semantic slot filling are two critical tasks in spoken language understanding (SLU) for dialogue systems. In this paper, we describe a recurrent neural network (RNN) model that jointly performs intent detection,…

For practical deep neural network design on mobile devices, it is essential to consider the constraints incurred by the computational resources and the inference latency in various applications. Among deep network acceleration related…

Transformer-based large language model (LLM) inference serving is now the backbone of many cloud services. LLM inference consists of a prefill phase and a decode phase. However, existing LLM deployment practices often overlook the distinct…

This work introduces CodeFlowLM, an incremental learning framework for Just-In-Time Software Defect Prediction (JIT-SDP) that leverages pre-trained language models (PLMs). Unlike traditional online learners, CodeFlowLM employs continual…

Linear model trees are regression trees that incorporate linear models in the leaf nodes. This preserves the intuitive interpretation of decision trees and at the same time enables them to better capture linear relationships, which is hard…

In this work new achievable rates are derived, for the uplink channel of a cellular network with joint multicell processing, where unlike previous results, the ideal backhaul network has finite capacity per-cell. Namely, the cell sites are…

Smart grid is an energy network that integrates advanced power equipment, communication technology and control technology. It can transmit two-way power and data among all components of the grid at the same time. The existing smart grid…

Split Federated Learning (SFL) offers a promising approach for distributed model training in wireless networks, combining the layer-partitioning advantages of split learning with the federated aggregation that ensures global convergence.…

We introduce a class of algebraic varieties naturally associated with ReLU neural networks, arising from the piecewise linear structure of their outputs across activation regions in input space, and the piecewise multilinear structure in…

Multi-Task Learning (MTL) networks have emerged as a promising method for transferring learned knowledge across different tasks. However, MTL must deal with challenges such as: overfitting to low resource tasks, catastrophic forgetting, and…

The deployment of large language models' (LLMs) inference at the edge can facilitate prompt service responsiveness while protecting user privacy. However, it is critically challenged by the resource constraints of a single edge node.…

We theoretically and numerically investigate the scattering behavior of a periodic parity-time (PT)-symmetric waveguide network composed of a finite number of unit cells. Specifically, we put forward rigorous and formally exact expressions…

Large language models (LLMs) have been a disruptive innovation in recent years, and they play a crucial role in our daily lives due to their ability to understand and generate human-like text. Their capabilities include natural language…