Search Results for author:
Found 8 papers, 8 papers with code
Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction
Our experimental findings demonstrate that our approach accelerates the training of vision-language models by a factor of 5 without a noticeable impact on overall performance.
Bootstrapping Vision-Language Learning with Decoupled Language Pre-training
We present a novel methodology aimed at optimizing the application of frozen large language models (LLMs) for resource-intensive vision-language (VL) pre-training.
Knowledge from Large-Scale Protein Contact Prediction Models Can Be Transferred to the Data-Scarce RNA Contact Prediction Task
Our findings indicate that the learned structural patterns of proteins can be transferred to RNAs, opening up potential new avenues for research.
Non-Linguistic Supervision for Contrastive Learning of Sentence Embeddings
This indicates that Transformer models are able to generalize better by doing a similar task (i. e., clustering) with unpaired examples from different modalities in a multi-task fashion.
Contrastive Learning for Prompt-Based Few-Shot Language Learners
Following this line of work, we present a contrastive learning framework that clusters inputs from the same class for better generality of models trained with only limited examples.
Embedding Hallucination for Few-Shot Language Fine-tuning
Few-shot language learners adapt knowledge from a pre-trained model to recognize novel classes from a few-labeled sentences.
Label Hallucination for Few-Shot Classification
At the same time, training a simple linear classifier on top of "frozen" features learned from the large labeled dataset fails to adapt the model to the properties of the novel classes, effectively inducing underfitting.
MetaPix: Domain Transfer for Semantic Segmentation by Meta Pixel Weighting
Previous work has shown that the performance of a semantic segmentation model can be improved by training jointly with real and synthetic examples with a proper weighting on the synthetic data.
