Trending Research
Erasing Concepts from Diffusion Models
We propose a fine-tuning method that can erase a visual concept from a pre-trained diffusion model, given only the name of the style and using negative guidance as a teacher.
LoRA: Low-Rank Adaptation of Large Language Models
We propose Low-Rank Adaptation, or LoRA, which freezes the pre-trained model weights and injects trainable rank decomposition matrices into each layer of the Transformer architecture, greatly reducing the number of trainable parameters for downstream tasks.
Prompting Large Language Models with Answer Heuristics for Knowledge-based Visual Question Answering
milvlg/prophet
•
•
Knowledge-based visual question answering (VQA) requires external knowledge beyond the image to answer the question.
Ranked #1 on
Visual Question Answering
on A-OKVQA
scenic
google-research/scenic
•
•
NeurIPS 2021
Scenic: A Jax Library for Computer Vision Research and Beyond
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
cloneofsimo/lora
•
•
Once the subject is embedded in the output domain of the model, the unique identifier can be used to synthesize novel photorealistic images of the subject contextualized in different scenes.
HFT: Lifting Perspective Representations via Hybrid Feature Transformation
jiayuzou2020/hft
•
•
In order to reap the benefits and avoid the drawbacks of CBFT and CFFT, we propose a novel framework with a Hybrid Feature Transformation module (HFT).
Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling
keyu-tian/spark
•
•
This is the first use of sparse convolution for 2D masked modeling.
Ranked #1 on
Instance Segmentation
on COCO 2017 val
Nerfstudio: A Modular Framework for Neural Radiance Field Development
nerfstudio-project/nerfstudio
•
•
Neural Radiance Fields (NeRF) are a rapidly growing area of research with wide-ranging applications in computer vision, graphics, robotics, and more.
Image as Set of Points
Context clusters (CoCs) view an image as a set of unorganized points and extract features via simplified clustering algorithm.
DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing
We thus propose a new gradient-disentangled embedding sharing method that avoids the tug-of-war dynamics, improving both training efficiency and the quality of the pre-trained model.
Ranked #1 on
Question Answering
on SWAG
Natural Language Inference
Natural Language Understanding
+2
