Trending Research
OCR-free Document Understanding Transformer
clovaai/donut
•
•
Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs.
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.
Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models
In RDMs, a set of nearest neighbors is retrieved from an external database during training for each training instance, and the diffusion model is conditioned on these informative samples.
GPT-NeoX-20B: An Open-Source Autoregressive Language Model
labmlai/annotated_deep_learning_paper_implementations
•
•
BigScience (ACL) 2022
We introduce GPT-NeoX-20B, a 20 billion parameter autoregressive language model trained on the Pile, whose weights will be made freely and openly available to the public through a permissive license.
Ranked #7 on
Multi-task Language Understanding
on MMLU
Elucidating the Design Space of Diffusion-Based Generative Models
We argue that the theory and practice of diffusion-based generative models are currently unnecessarily convoluted and seek to remedy the situation by presenting a design space that clearly separates the concrete design choices.
MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures
Neural Radiance Fields (NeRFs) have demonstrated amazing ability to synthesize images of 3D scenes from novel views.
Ranked #1 on
Novel View Synthesis
on Mip-NeRF 360
Learning the Beauty in Songs: Neural Singing Voice Beautifier
MoonInTheRiver/DiffSinger
•
•
ACL 2022
Furthermore, we propose a latent-mapping algorithm in the latent space to convert the amateur vocal tone to the professional one.
Patch Similarity Aware Data-Free Quantization for Vision Transformers
zkkli/psaq-vit
•
•
Vision transformers have recently gained great success on various computer vision tasks; nevertheless, their high model complexity makes it challenging to deploy on resource-constrained devices.
Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
nvidiagameworks/kaolin-wisp
•
•
Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate.
Speech Enhancement and Dereverberation with Diffusion-based Generative Models
sp-uhh/sgmse
•
•
Furthermore, we show that the proposed method achieves remarkable state-of-the-art performance in single-channel speech dereverberation.
