Bias-Aware Low-Rank Adaptation: Mitigating Catastrophic Inheritance of Large Language Models

Y Chang, Y Chang, Y Wu - arXiv preprint arXiv:2408.04556, 2024 - arxiv.org
Large language models (LLMs) have exhibited remarkable proficiency across a diverse
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 …

As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?

A Hu, J Gu, F Pinto, K Kamnitsas, P Torr - arXiv preprint arXiv:2403.12693, 2024 - arxiv.org
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 …

Slight Corruption in Pre-training Data Makes Better Diffusion Models

H Chen, Y Han, D Misra, X Li, K Hu, D Zou… - arXiv preprint arXiv …, 2024 - arxiv.org
Diffusion models (DMs) have shown remarkable capabilities in generating realistic high-
quality images, audios, and videos. They benefit significantly from extensive pre-training on …

ControlVAR: Exploring Controllable Visual Autoregressive Modeling

X Li, K Qiu, H Chen, J Kuen, Z Lin, R Singh… - arXiv preprint arXiv …, 2024 - arxiv.org
Conditional visual generation has witnessed remarkable progress with the advent of
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 …

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 …