ExtremeBERT: A Toolkit for Accelerating Pretraining of Customized BERT

extreme-bert/extreme-bert 30 Nov 2022

In this paper, we present ExtremeBERT, a toolkit for accelerating and customizing BERT pretraining.

Molecular System Prediction Sentence Classification

152
3.11 stars / hour

TorchScale: Transformers at Scale

microsoft/torchscale 23 Nov 2022

Large Transformers have achieved state-of-the-art performance across many tasks.

Language Modelling Machine Translation +1

897
1.89 stars / hour

Compressing Volumetric Radiance Fields to 1 MB

algohunt/vqrf 29 Nov 2022

Approximating radiance fields with volumetric grids is one of promising directions for improving NeRF, represented by methods like Plenoxels and DVGO, which achieve super-fast training convergence and real-time rendering.

Model Compression Neural Rendering +1

117
1.74 stars / hour

DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models

hzfinfdu/diffusion-bert 28 Nov 2022

We present DiffusionBERT, a new generative masked language model based on discrete diffusion models.

Denoising Language Modelling +1

71
1.69 stars / hour

Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation

pals-ttic/sjc 1 Dec 2022

We propose to apply chain rule on the learned gradients, and back-propagate the score of a diffusion model through the Jacobian of a differentiable renderer, which we instantiate to be a voxel radiance field.

124
1.58 stars / hour

Multiresolution Textual Inversion

giannisdaras/multires_textual_inversion 30 Nov 2022

We extend Textual Inversion to learn pseudo-words that represent a concept at different resolutions.

51
1.50 stars / hour

MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition

facebookresearch/memvit CVPR 2022

Instead of trying to process more frames at once like most existing methods, we propose to process videos in an online fashion and cache "memory" at each iteration.

Ranked #2 on Action Anticipation on EPIC-KITCHENS-100 (using extra training data)

Action Anticipation Action Classification +2

48
1.04 stars / hour

Versatile Diffusion: Text, Images and Variations All in One Diffusion Model

shi-labs/versatile-diffusion 15 Nov 2022

Through our experiments, we demonstrate that VD and its underlying framework have the following merits: a) VD handles all subtasks with competitive quality; b) VD initiates novel extensions and applications such as disentanglement of style and semantic, image-text dual-guided generation, etc.

Disentanglement Image Captioning +4

802
0.99 stars / hour

SuperFusion: Multilevel LiDAR-Camera Fusion for Long-Range HD Map Generation and Prediction

haomo-ai/superfusion 28 Nov 2022

To this end, we propose a novel network named SuperFusion, exploiting the fusion of LiDAR and camera data at multiple levels.

Autonomous Driving

89
0.98 stars / hour

DAMO-YOLO : A Report on Real-Time Object Detection Design

tinyvision/damo-yolo 23 Nov 2022

In this report, we present a fast and accurate object detection method dubbed DAMO-YOLO, which achieves higher performance than the state-of-the-art YOLO series.

Neural Architecture Search object-detection +1

234
0.90 stars / hour