Trending Research
GLU Variants Improve Transformer
BlinkDL/RWKV-LM
•
•
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.
Zero-Shot Text-to-Image Generation
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
Surface Representation for Point Clouds
hancyran/RepSurf
•
•
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
DeepDPM: Deep Clustering With an Unknown Number of Clusters
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
Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
r-three/t-few
•
•
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
Fine-Tuning Language Models from Human Preferences
lvwerra/trl
•
•
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: Automatic differentiation of hybrid quantum-classical computations
PennyLane is a Python 3 software framework for optimization and machine learning of quantum and hybrid quantum-classical computations.
A Unified Framework for Implicit Sinkhorn Differentiation
marvin-eisenberger/implicit-sinkhorn
•
•
The Sinkhorn operator has recently experienced a surge of popularity in computer vision and related fields.
CLIPasso: Semantically-Aware Object Sketching
Abstraction is at the heart of sketching due to the simple and minimal nature of line drawings.
RITA: a Study on Scaling Up Generative Protein Sequence Models
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.
