GLU Variants Improve Transformer

BlinkDL/RWKV-LM 12 Feb 2020

Gated Linear Units (arXiv:1612. 08083) consist of the component-wise product of two linear projections, one of which is first passed through a sigmoid function.

0.38 stars / hour

Zero-Shot Text-to-Image Generation

borisdayma/dalle-mini 24 Feb 2021

Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset.

Text to image generation Zero-Shot Text-to-Image Generation

0.38 stars / hour

Surface Representation for Point Clouds

hancyran/RepSurf 11 May 2022

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.

3D Object Detection 3D Point Cloud Classification +2

0.36 stars / hour

DeepDPM: Deep Clustering With an Unknown Number of Clusters

bgu-cs-vil/deepdpm 27 Mar 2022

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).

Deep Nonparametric Clustering Model Selection +2

0.33 stars / hour

Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning

r-three/t-few 11 May 2022

ICL incurs substantial computational, memory, and storage costs because it involves processing all of the training examples every time a prediction is made.

Few-Shot Text Classification

0.32 stars / hour

Fine-Tuning Language Models from Human Preferences

lvwerra/trl 18 Sep 2019

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.

Language Modelling

0.31 stars / hour

PennyLane: Automatic differentiation of hybrid quantum-classical computations

PennyLaneAI/pennylane 12 Nov 2018

PennyLane is a Python 3 software framework for optimization and machine learning of quantum and hybrid quantum-classical computations.

0.31 stars / hour

A Unified Framework for Implicit Sinkhorn Differentiation

marvin-eisenberger/implicit-sinkhorn 13 May 2022

The Sinkhorn operator has recently experienced a surge of popularity in computer vision and related fields.

0.29 stars / hour

CLIPasso: Semantically-Aware Object Sketching

yael-vinker/CLIPasso 11 Feb 2022

Abstraction is at the heart of sketching due to the simple and minimal nature of line drawings.

0.28 stars / hour

RITA: a Study on Scaling Up Generative Protein Sequence Models

lightonai/rita 11 May 2022

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.

0.27 stars / hour