Fundamental Limits of Prompt Compression: A Rate- Distortion Framework for Black-Box Language Models

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Different users find different images generated for the same prompt desirable. This gives rise to personalized image generation which involves creating images aligned with an individual’s visual preference. Current generative models are, however, tuned to ...

Generative AI technologies are increasingly being incorporated into creativity support tools. However, most generative AI tools rely on text-based prompting, requiring users to translate visual ideas into linguistic descriptions. This approach is misaligne ...

The remarkable ability of deep learning (DL) models to approximate high-dimensional functions from samples has sparked a revolution across numerous scientific and industrial domains that cannot be overemphasized. In sensitive applications, the good perform ...

Natural language processing has experienced significant improvements with the development of Transformer-based models, which employ self-attention mechanism and pre-training strategies. However, these models still present several obstacles. A notable issue ...

Models trained with counterfactually augmented data learn representations of the causal structure of tasks, enabling robust generalization. However, high-quality counterfactual data is scarce for most tasks and not easily generated at scale. When crowdsour ...

In order to provide urban residents with suitable living conditions, it is essential to keep track of the liveability of neighbourhoods. This is traditionally done through surveys and by predictive modelling. However, surveying on a large scale is expensiv ...

Semantic segmentation datasets often exhibit two types of imbalance: \textit{class imbalance}, where some classes appear more frequently than others and \textit{size imbalance}, where some objects occupy more pixels than others. This causes traditional eva ...

This paper models predictive processing of chords using a corpus of Ludwig van Beethoven’s string quartets. A recently published dataset consisting of expert harmonic analyses of all Beethoven string quartets was used to evaluate an n-gram language model a ...

Networks are commonly used to represent key processes in biology; examples include transcriptional regulatory networks, protein-protein interaction (PPI) networks, metabolic networks, etc. Databases store many such networks, as graphs, observed or inferred ...

Fundamental Limits of Prompt Compression: A Rate- Distortion Framework for Black-Box Language Models

Chattez avec Graph Search

ViPer: Visual Personalization of Generative Models via Individual Preference Learning

SketchAI: A "Sketch-First" Approach to Incorporating Generative AI into Fashion Design

Towards Trustworthy Deep Learning for Image Reconstruction

Modeling Structured Data in Attention-based Models

DISCO: Distilling Counterfactuals with Large Language Models

Predicting the liveability of Dutch cities with aerial images and semantic intermediate concepts

Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union

A Model Comparison for Chord Prediction on the Annotated Beethoven Corpus

Models and Algorithms in Biological Network Evolution with Modularity