Trending Research
Vision Transformer Adapter for Dense Predictions
When fine-tuning on downstream tasks, a modality-specific adapter is used to introduce the data and tasks' prior information into the model, making it suitable for these tasks.
Ranked #1 on
Semantic Segmentation
on ADE20K val
Neo: Generalizing Confusion Matrix Visualization to Hierarchical and Multi-Output Labels
The confusion matrix, a ubiquitous visualization for helping people evaluate machine learning models, is a tabular layout that compares predicted class labels against actual class labels over all data instances.
PennyLane: Automatic differentiation of hybrid quantum-classical computations
PennyLane is a Python 3 software framework for optimization and machine learning of quantum and hybrid quantum-classical computations.
RankGen: Improving Text Generation with Large Ranking Models
martiansideofthemoon/rankgen
•
•
Given an input sequence (or prefix), modern language models often assign high probabilities to output sequences that are repetitive, incoherent, or irrelevant to the prefix; as such, model-generated text also contains such artifacts.
Thin-Plate Spline Motion Model for Image Animation
yoyo-nb/thin-plate-spline-motion-model
•
•
Firstly, we propose thin-plate spline motion estimation to produce a more flexible optical flow, which warps the feature maps of the source image to the feature domain of the driving image.
GLU Variants Improve Transformer
BlinkDL/RWKV-LM
•
•
Gated Linear Units (arXiv:1612. 08083) consist of the component-wise product of two linear projections, one of which is first passed through a sigmoid function.
A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation
Despite its simplicity, benchmark results show our system's note estimation to be substantially better than a comparable baseline, and its frame-level accuracy to be only marginally below those of specialized state-of-the-art AMT systems.
Ivy: Templated Deep Learning for Inter-Framework Portability
ivy-dl/ivy
•
•
We introduce Ivy, a templated Deep Learning (DL) framework which abstracts existing DL frameworks.
OPT: Open Pre-trained Transformer Language Models
Large language models, which are often trained for hundreds of thousands of compute days, have shown remarkable capabilities for zero- and few-shot learning.
Ranked #1 on
Stereotypical Bias Analysis
on CrowS-Pairs
ConvMAE: Masked Convolution Meets Masked Autoencoders
alpha-vl/convmae
•
•
Masked auto-encoding for feature pretraining and multi-scale hybrid convolution-transformer architectures can further unleash the potentials of ViT, leading to state-of-the-art performances on image classification, detection and semantic segmentation.
