Search Results for author:
Found 9 papers, 3 papers with code
Large Language Models in Medical Term Classification and Unexpected Misalignment Between Response and Reasoning
This study assesses the ability of state-of-the-art large language models (LLMs) including GPT-3. 5, GPT-4, Falcon, and LLaMA 2 to identify patients with mild cognitive impairment (MCI) from discharge summaries and examines instances where the models' responses were misaligned with their reasoning.
Active Prompt Learning in Vision Language Models
In response to this inquiry, we observe that (1) simply applying a conventional active learning framework to pre-trained VLMs even may degrade performance compared to random selection because of the class imbalance in labeling candidates, and (2) the knowledge of VLMs can provide hints for achieving the balance before labeling.
Fine tuning Pre trained Models for Robustness Under Noisy Labels
To tackle this issue, researchers have explored methods for Learning with Noisy Labels to identify clean samples and reduce the influence of noisy labels.
NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models
Structured pruning methods have proven effective in reducing the model size and accelerating inference speed in various network architectures such as Transformers.
CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition
To handle this restriction, several methods have been developed that increase the representations of minority samples by leveraging the features of the majority samples.
Ranked #13 on
Long-tail Learning
on CIFAR-100-LT (ρ=10)
Denoising after Entropy-based Debiasing A Robust Training Method for Dataset Bias with Noisy Labels
Furthermore, we find that running denoising algorithms before debiasing is ineffective because denoising algorithms reduce the impact of difficult-to-learn samples, including valuable bias-conflicting samples.
Mitigating Dataset Bias by Using Per-sample Gradient
In this study, we propose a debiasing algorithm, called PGD (Per-sample Gradient-based Debiasing), that comprises three steps: (1) training a model on uniform batch sampling, (2) setting the importance of each sample in proportion to the norm of the sample gradient, and (3) training the model using importance-batch sampling, whose probability is obtained in step (2).
Mitigating Dataset Bias Using Per-Sample Gradients From A Biased Classifier
The performance of deep neural networks (DNNs) primarily depends on the configuration of the training set.
Enlarging Discriminative Power by Adding an Extra Class in Unsupervised Domain Adaptation
In this paper, we propose an idea of empowering the discriminativeness: Adding a new, artificial class and training the model on the data together with the GAN-generated samples of the new class.
