Results 21 to 30 of about 2,403,325 (304)
Fine-Tuning LLaMA for Multi-Stage Text Retrieval [PDF]
Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2023 While large language models (LLMs) have shown impressive NLP capabilities, existing IR applications mainly focus on prompting LLMs to generate query expansions or generating permutations for listwise reranking. In this study, we leverage LLMs directly to
Xueguang Ma +4 more
semanticscholar +1 more source
Science, 2020 Targeted degradation determines whether embryonic stem cells undergo ...
Borsa, Mariana, Simon, Anna Katharina
openaire +2 more sources
DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models [PDF]
Neural Information Processing Systems, 2023 Learning from human feedback has been shown to improve text-to-image models. These techniques first learn a reward function that captures what humans care about in the task and then improve the models based on the learned reward function.
Ying Fan +9 more
semanticscholar +1 more source
Directly Fine-Tuning Diffusion Models on Differentiable Rewards [PDF]
International Conference on Learning Representations, 2023 We present Direct Reward Fine-Tuning (DRaFT), a simple and effective method for fine-tuning diffusion models to maximize differentiable reward functions, such as scores from human preference models.
Kevin Clark +3 more
semanticscholar +1 more source
Universal Language Model Fine-tuning for Text Classification
Annual Meeting of the Association for Computational Linguistics, 2018 Inductive transfer learning has greatly impacted computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch. We propose Universal Language Model Fine-tuning (ULMFiT), an effective transfer learning
Jeremy Howard, Sebastian Ruder
semanticscholar +1 more source
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning [PDF]
Neural Information Processing Systems, 2023 A compelling use case of offline reinforcement learning (RL) is to obtain a policy initialization from existing datasets followed by fast online fine-tuning with limited interaction.
Mitsuhiko Nakamoto +7 more
semanticscholar +1 more source
Dark energy without fine tuning
Journal of High Energy Physics, 2019 We present a two-field model that realises inflation and the observed density of dark energy today, whilst solving the fine-tuning problems inherent in quintessence models.
José Eliel Camargo-Molina +2 more
doaj +1 more source
Parameter-efficient fine-tuning of large-scale pre-trained language models
Nature Machine Intelligence, 2023 With the prevalence of pre-trained language models (PLMs) and the pre-training–fine-tuning paradigm, it has been continuously shown that larger models tend to yield better performance. However, as PLMs scale up, fine-tuning and storing all the parameters
Ning Ding +19 more
semanticscholar +1 more source
SVDiff: Compact Parameter Space for Diffusion Fine-Tuning [PDF]
IEEE International Conference on Computer Vision, 2023 Diffusion models have achieved remarkable success in text-to-image generation, enabling the creation of high-quality images from text prompts or other modalities.
Ligong Han +5 more
semanticscholar +1 more source
Proceedings of the AAAI Conference on Artificial Intelligence, 2019 In real-world applications, commercial off-the-shelf systems are utilized for performing automated facial analysis including face recognition, emotion recognition, and attribute prediction. However, a majority of these commercial systems act as black boxes due to the inaccessibility of the model parameters which makes it challenging to fine-tune the ...
Saheb Chhabra +3 more
openaire +3 more sources