Trending Research
Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality
implus/um-mae
•
•
Masked AutoEncoder (MAE) has recently led the trends of visual self-supervision area by an elegant asymmetric encoder-decoder design, which significantly optimizes both the pre-training efficiency and fine-tuning accuracy.
Ranked #16 on
Object Detection
on COCO minival
Conformer: Convolution-augmented Transformer for Speech Recognition
Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs).
Ranked #9 on
Speech Recognition
on LibriSpeech test-clean
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.
PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit
PaddleSpeech is an open-source all-in-one speech toolkit.
Automatic Speech Recognition
Environmental Sound Classification
+8
MuJoCo: A physics engine for model-based control
To facilitate optimal control applications and in particular sampling and finite differencing, the dynamics can be evaluated for different states and controls in parallel.
Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors
hsouri/bayesiantransferlearning
•
•
Deep learning is increasingly moving towards a transfer learning paradigm whereby large foundation models are fine-tuned on downstream tasks, starting from an initialization learned on the source task.
BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving
Specifically, BEVerse first performs shared feature extraction and lifting to generate 4D BEV representations from multi-timestamp and multi-view images.
FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis
Also, FastDiff enables a sampling speed of 58x faster than real-time on a V100 GPU, making diffusion models practically applicable to speech synthesis deployment for the first time.
Ranked #6 on
Text-To-Speech Synthesis
on LJSpeech
Automated Crossword Solving
albertkx/berkeley-crossword-solver
•
•
ACL 2022
We present the Berkeley Crossword Solver, a state-of-the-art approach for automatically solving crossword puzzles.
Extracting Triangular 3D Models, Materials, and Lighting From Images
NVlabs/nvdiffrec
•
•
We present an efficient method for joint optimization of topology, materials and lighting from multi-view image observations.
