Trending Research
ExtremeBERT: A Toolkit for Accelerating Pretraining of Customized BERT
In this paper, we present ExtremeBERT, a toolkit for accelerating and customizing BERT pretraining.
TorchScale: Transformers at Scale
Large Transformers have achieved state-of-the-art performance across many tasks.
Compressing Volumetric Radiance Fields to 1 MB
algohunt/vqrf
•
•
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.
DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models
We present DiffusionBERT, a new generative masked language model based on discrete diffusion models.
Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
pals-ttic/sjc
•
•
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.
Multiresolution Textual Inversion
giannisdaras/multires_textual_inversion
•
•
We extend Textual Inversion to learn pseudo-words that represent a concept at different resolutions.
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)
Versatile Diffusion: Text, Images and Variations All in One Diffusion Model
shi-labs/versatile-diffusion
•
•
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.
SuperFusion: Multilevel LiDAR-Camera Fusion for Long-Range HD Map Generation and Prediction
To this end, we propose a novel network named SuperFusion, exploiting the fusion of LiDAR and camera data at multiple levels.
DAMO-YOLO : A Report on Real-Time Object Detection Design
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.
Ranked #29 on
Real-Time Object Detection
on COCO
