Bias-Aware Low-Rank Adaptation: Mitigating Catastrophic Inheritance of Large Language Models
Large language models (LLMs) have exhibited remarkable proficiency across a diverse
array of natural language processing (NLP) tasks. However, adapting LLMs to downstream …
array of natural language processing (NLP) tasks. However, adapting LLMs to downstream …
[HTML][HTML] Future Shock: Generative AI and the international AI policy and governance crisis
D Leslie, AM Perini - 2024 - hdsr.mitpress.mit.edu
On March 29, 2023, the Future of Life Institute (FLI) published an open letter calling on “all AI
labs to immediately pause for at least 6 months the training of AI systems more powerful than …
labs to immediately pause for at least 6 months the training of AI systems more powerful than …
As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?
Foundation models pre-trained on web-scale vision-language data, such as CLIP, are
widely used as cornerstones of powerful machine learning systems. While pre-training offers …
widely used as cornerstones of powerful machine learning systems. While pre-training offers …
Slight Corruption in Pre-training Data Makes Better Diffusion Models
Diffusion models (DMs) have shown remarkable capabilities in generating realistic high-
quality images, audios, and videos. They benefit significantly from extensive pre-training on …
quality images, audios, and videos. They benefit significantly from extensive pre-training on …
ControlVAR: Exploring Controllable Visual Autoregressive Modeling
Conditional visual generation has witnessed remarkable progress with the advent of
diffusion models (DMs), especially in tasks like control-to-image generation. However …
diffusion models (DMs), especially in tasks like control-to-image generation. However …
Open-Set Video-based Facial Expression Recognition with Human Expression-sensitive Prompting
Y Liu, Y Huang, S Liu, Y Zhan, Z Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
In Video-based Facial Expression Recognition (V-FER), models are typically trained on
closed-set datasets with a fixed number of known classes. However, these V-FER models …
closed-set datasets with a fixed number of known classes. However, these V-FER models …
Comparative evaluation of commercial large language models on promptbench: An english and chinese perspective
S Wang, Q Ouyang, B Wang - 2024 - researchsquare.com
This study embarks on an exploration of the performance disparities observed between
English and Chinese in large language models (LLMs), motivated by the growing need for …
English and Chinese in large language models (LLMs), motivated by the growing need for …