Results 11 to 20 of about 6,757,216 (293)

Prompt Learning for News Recommendation [PDF]

open access: yesProceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2023
11 pages, 7 figures, 3 tables, SIGIR2023 ...
Zizhuo Zhang, Bang Wang 0001
openaire   +4 more sources

Quantifying Privacy Risks of Prompts in Visual Prompt Learning [PDF]

open access: yesCoRR, 2023
To appear in the 33rd USENIX Security Symposium, August 14-16 ...
Yixin Wu 0001   +6 more
core   +8 more sources

Discrete Prompt Compression With Reinforcement Learning

open access: yesIEEE Access
Compressed prompts aid instruction-tuned language models (LMs) in overcoming context window limitations and reducing computational costs. Existing methods, which are primarily based on training embeddings, face various challenges associated with ...
Hoyoun Jung, Kyung-Joong Kim
doaj   +4 more sources

Prompt Diffusion Robustifies Any-Modality Prompt Learning

open access: yesCoRR
Foundation models enable prompt-based classifiers for zero-shot and few-shot learning. Nonetheless, the conventional method of employing fixed prompts suffers from distributional shifts that negatively impact generalizability to unseen samples. This paper introduces prompt diffusion, which uses a diffusion model to gradually refine the prompts to ...
Yingjun Du   +5 more
openaire   +4 more sources

Plum: Prompt Learning using Metaheuristics

open access: yesFindings of the Association for Computational Linguistics ACL 2024
Since the emergence of large language models, prompt learning has become a popular method for optimizing and customizing these models. Special prompts, such as Chain-of-Thought, have even revealed previously unknown reasoning capabilities within these models.
Rui Pan 0002   +8 more
openaire   +4 more sources

Bayesian Prompt Learning for Image-Language Model Generalization [PDF]

open access: yes, 2023
Foundational image-language models have generated considerable interest due to their efficient adaptation to downstream tasks by prompt learning. Prompt learning treats part of the language model input as trainable while freezing the rest, and optimizes ...
Sanchez, E   +7 more
core   +6 more sources

POP: Prompt Of Prompts for Continual Learning

open access: yesCoRR, 2023
Continual learning (CL) has attracted increasing attention in the recent past. It aims to mimic the human ability to learn new concepts without catastrophic forgetting. While existing CL methods accomplish this to some extent, they are still prone to semantic drift of the learned feature space. Foundation models, which are endowed with a robust feature
Zhiyuan Hu   +3 more
openaire   +3 more sources

Prompt Backdoors in Visual Prompt Learning

open access: yesCoRR, 2023
Fine-tuning large pre-trained computer vision models is infeasible for resource-limited users. Visual prompt learning (VPL) has thus emerged to provide an efficient and flexible alternative to model fine-tuning through Visual Prompt as a Service (VPPTaaS).
Hai Huang 0014   +4 more
openaire   +3 more sources

Learning to Prompt for Continual Learning

open access: yes2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge. Typical methods rely on a rehearsal buffer or known task identity at test time to retrieve learned knowledge and address forgetting, while this work presents a new ...
Zifeng Wang 0002   +9 more
openaire   +3 more sources

Prompt Distribution Learning

open access: yes2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Accepted by CVPR ...
Yuning Lu   +4 more
openaire   +2 more sources

Home - About - Disclaimer - Privacy