Projekt
PRIDE – Parameter-Efficient Reduction of Identity Discrimination for Equality in LLMs
PRIDE – Parameter-Efficient Reduction of Identity Discrimination for Equality in LLMs im TechnologieAtlas.
PRIDE – Parameter-Efficient Reduction of Identity Discrimination for Equality in LLMs im TechnologieAtlas.
Weiter entdecken
Ähnliche Beiträge
Projekt
→
TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination
Large Language Models (LLMs) typically come with a fixed architecture, despite growing evidence that not all layers contribute eq… Beitrag ansehen →
Projekt
→
The Sociolinguistics of Machine Identity: LLM Personality and Ideology Propagation
Do large language models (LLMs) possess a measurable "personality," and how do the linguistic properties of training corpora shap… Beitrag ansehen →
Projekt
→
Designing Interactive Artifacts for Mental Health Education: A Game-Based Approach using AI as In-game Characters
Mental Health (MH) is fundamental to overall well-being, yet Mental Health Literacy (MHL) remains low despite growing awareness.M… Beitrag ansehen →
Projekt
→
Crop-weed classification using deep learning: a comparative study of CNNs, vision transformers, and interpretable models
Accurate discrimination between crops and weeds was considered essential for precision agriculture, as it supports targeted inter… Beitrag ansehen →
Projekt
→
Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching
Test-time finetuning (TTFT) is a rapidly evolving paradigm that adapts a language model to each prompt by retrieving related sequ… Beitrag ansehen →
Projekt
→
Advanced simulations in electrocatalysis for efficient production of C3+ by carbon dioxide reduction
The climate change has raised concerns about closing the carbon cycle by converting CO2 and renewable electricity to chemically s… Beitrag ansehen →
Passend zu diesem Beitrag
Technologien
Passend zu diesem Beitrag