Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset.
Ranked #5 on Zero-Shot Text-to-Image Generation on COCO
Based on a simple baseline of PointNet++ (SSG version), Umbrella RepSurf surpasses the previous state-of-the-art by a large margin for classification, segmentation and detection on various benchmarks in terms of performance and efficiency.
Ranked #1 on 3D Point Cloud Classification on ScanObjectNN
Using a split/merge framework, a dynamic architecture that adapts to the changing K, and a novel loss, our proposed method outperforms existing nonparametric methods (both classical and deep ones).
Ranked #6 on Unsupervised Image Classification on ImageNet
ICL incurs substantial computational, memory, and storage costs because it involves processing all of the training examples every time a prediction is made.
Ranked #1 on Few-Shot Text Classification on RAFT
Most work on reward learning has used simulated environments, but complex information about values is often expressed in natural language, and we believe reward learning for language is a key to making RL practical and safe for real-world tasks.
PennyLane is a Python 3 software framework for optimization and machine learning of quantum and hybrid quantum-classical computations.
The Sinkhorn operator has recently experienced a surge of popularity in computer vision and related fields.
In this work we introduce RITA: a suite of autoregressive generative models for protein sequences, with up to 1. 2 billion parameters, trained on over 280 million protein sequences belonging to the UniRef-100 database.