Search
Results
-
-
DeltaZip: Multi-Tenant Language Model Serving via Delta Compression
(2023)arXivFine-tuning large language models (LLMs) for downstream tasks can greatly improve model quality, however serving many different fine-tuned LLMs concurrently for users in multi-tenant environments is challenging. Dedicating GPU memory for each model is prohibitively expensive and naively swapping large model weights in and out of GPU memory is slow. Our key insight is that fine-tuned models can be quickly swapped in and out of GPU memory ...Working Paper -
PSC Impact Report. 25 years of plant science research, education and outreach
(2023)Since it was launched 25 years ago, the Zurich-Basel Plant Science Center (PSC) has contributed significantly to the field of plant sciences. By creating a highly visible platform, and through our innovative collaborations in research programmes, fellowships and educational offering, we show the profound impact that plant sciences can have. PSC facilitates interdisciplinary collaboration and bridges the gap between scientific knowledge ...Report -
SequenceLab: A Comprehensive Benchmark of Computational Methods for Comparing Genomic Sequences
(2023)arXivComputational complexity is a key limitation of genomic analyses. Thus, over the last 30 years, researchers have proposed numerous fast heuristic methods that provide computational relief. Comparing genomic sequences is one of the most fundamental computational steps in most genomic analyses. Due to its high computational complexity, new, more optimized exact and heuristic algorithms are still being developed. We find that these methods ...Working Paper -
MetaFast: Enabling Fast Metagenomic Classification via Seed Counting and Edit Distance Approximation
(2023)arXivMetagenomics, the study of genome sequences of diverse organisms cohabiting in a shared environment, has experienced significant advancements across various medical and biological fields. Metagenomic analysis is crucial, for instance, in clinical applications such as infectious disease screening and the diagnosis and early detection of diseases such as cancer. A key task in metagenomics is to determine the species present in a sample and ...Working Paper -
Dynamic Structure-Soil-Structure Interaction for Nuclear Power Plants
(2023)arXivThe paper explores the linear and nonlinear dynamic interaction between the reactor and the auxiliary buildings of a Nuclear Power Plant on a realistic layered soil profile, aiming to evaluate the effect of the auxiliary building on the seismic response of crucial components inside the reactor building. Based on realistic geometrical assumptions, highfidelity 3D finite element (FE) models of increasing sophistication are created in the ...Working Paper -
All Roads Lead to Rome? Exploring the Invariance of Transformers' Representations
(2023)arXivTransformer models bring propelling advances in various NLP tasks, thus inducing lots of interpretability research on the learned representations of the models. However, we raise a fundamental question regarding the reliability of the representations. Specifically, we investigate whether transformers learn essentially isomorphic representation spaces, or those that are sensitive to the random seeds in their pretraining process. In this ...Working Paper -
Psychologically-Inspired Causal Prompts
(2023)arXivNLP datasets are richer than just input-output pairs; rather, they carry causal relations between the input and output variables. In this work, we take sentiment classification as an example and look into the causal relations between the review (X) and sentiment (Y). As psychology studies show that language can affect emotion, different psychological processes are evoked when a person first makes a rating and then self-rationalizes their ...Working Paper -