Results 11 to 20 of about 6,757,216 (293)
Prompt Learning for News Recommendation [PDF]
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]
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
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
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
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]
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
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
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
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
Accepted by CVPR ...
Yuning Lu +4 more
openaire +2 more sources

