From the 1 of 5 linked papers with an AI index.
5 papers
Wasted large language models: A life cycle thinking approach
Erik Johannes Husom, Maria Emine Nylund, Ophelia Prillard
Large Language Models (LLMs) are machine learning (ML) models that have an increasingly large carbon footprint through their development and use. Efforts to increase the energy eff…
Differentiable Clone-Structured Causal Graphs for End-to-End Cognitive Map Learning from Image Sequences
Arash Nikzad, Sasan Sarbishegi, Ali Dasmeh +8
The paper presents gradCSCG, a fully differentiable version of the Clone-Structured Causal Graph model, integrated with a vector-quantized VAE to enable end‑to‑end learning of cogn…
Overview over the first decade of LIMITS
Maria Emine Nylund, Erik Johannes Husom, Ophelia Prillard
Computing within limits is a promising field, that follows principles of a) questioning endless growth narrative, b) considering and preparing for models of scarcity and c) reducin…
The Price of Prompting: Profiling Energy Use in Large Language Models Inference
Erik Johannes Husom, Arda Goknil, Lwin Khin Shar +1
In the rapidly evolving realm of artificial intelligence, deploying large language models (LLMs) poses increasingly pressing computational and environmental challenges. This paper…
Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency
Erik Johannes Husom, Arda Goknil, Merve Astekin +5
Deploying Large Language Models (LLMs) on edge devices presents significant challenges due to computational constraints, memory limitations, inference speed, and energy consumption…