Search Results for author:
Found 5 papers, 1 papers with code
Rethinking the BERT-like Pretraining for DNA Sequences
To address this research gap, we first conducted a series of exploratory experiments and gained several insightful observations: 1) In the fine-tuning phase of downstream tasks, when using K-mer overlapping tokenization instead of K-mer non-overlapping tokenization, both overlapping and non-overlapping pretraining weights show consistent performance improvement. 2) During the pre-training process, using K-mer overlapping tokenization quickly produces clear K-mer embeddings and reduces the loss to a very low level, while using K-mer non-overlapping tokenization results in less distinct embeddings and continuously decreases the loss.
Improved Visual Story Generation with Adaptive Context Modeling
Diffusion models developed on top of powerful text-to-image generation models like Stable Diffusion achieve remarkable success in visual story generation.
Boosting Adversarial Transferability via Gradient Relevance Attack
Plentiful adversarial attack researches have revealed the fragility of deep neural networks (DNNs), where the imperceptible perturbations can cause drastic changes in the output.
Crossing the Gap: Domain Generalization for Image Captioning
In this paper, we introduce a new setting called Domain Generalization for Image Captioning (DGIC), where the data from the target domain is unseen in the learning process.
Generating meta-learning tasks to evolve parametric loss for classification learning
In this paper, we propose a meta-learning approach based on randomly generated meta-learning tasks to obtain a parametric loss for classification learning based on big data.
