Salesforce CausalAI Library: A Fast and Scalable Framework for Causal Analysis of Time Series and Tabular Data

salesforce/causalai 25 Jan 2023

We introduce the Salesforce CausalAI Library, an open-source library for causal analysis using observational data.

Causal Discovery Causal Inference +1

109
0.32 stars / hour

Parsel: A (De-)compositional Framework for Algorithmic Reasoning with Language Models

ezelikman/parsel 20 Dec 2022

Despite recent success in large language model (LLM) reasoning, LLMs struggle with hierarchical multi-step reasoning tasks like generating complex programs.

Automated Theorem Proving Code Generation +2

135
0.32 stars / hour

Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baseline

sense-gvt/fast-bev 29 Jan 2023

Our Fast-BEV consists of five parts, We novelly propose (1) a lightweight deployment-friendly view transformation which fast transfers 2D image feature to 3D voxel space, (2) an multi-scale image encoder which leverages multi-scale information for better performance, (3) an efficient BEV encoder which is particularly designed to speed up on-vehicle inference.

Data Augmentation

136
0.31 stars / hour

Cut and Learn for Unsupervised Object Detection and Instance Segmentation

facebookresearch/cutler 26 Jan 2023

We propose Cut-and-LEaRn (CutLER), a simple approach for training unsupervised object detection and segmentation models.

Instance Segmentation object-detection +2

337
0.31 stars / hour

KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation

eleutherai/gpt-neox 20 May 2022

Relative positional embeddings (RPE) have received considerable attention since RPEs effectively model the relative distance among tokens and enable length extrapolation.

Language Modelling

3,530
0.30 stars / hour

Muse: Text-To-Image Generation via Masked Generative Transformers

lucidrains/muse-pytorch 2 Jan 2023

Compared to pixel-space diffusion models, such as Imagen and DALL-E 2, Muse is significantly more efficient due to the use of discrete tokens and requiring fewer sampling iterations; compared to autoregressive models, such as Parti, Muse is more efficient due to the use of parallel decoding.

Language Modelling Text to image generation +1

398
0.30 stars / hour

Hungry Hungry Hippos: Towards Language Modeling with State Space Models

hazyresearch/h3 28 Dec 2022

First, we use synthetic language modeling tasks to understand the gap between SSMs and attention.

Few-Shot Learning Language Modelling

260
0.29 stars / hour

How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection

hello-simpleai/chatgpt-comparison-detection 18 Jan 2023

We call the collected dataset the Human ChatGPT Comparison Corpus (HC3).

397
0.29 stars / hour

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

anthropics/hh-rlhf 23 Aug 2022

We provide our own analysis of the data and find a variety of harmful outputs, which range from offensive language to more subtly harmful non-violent unethical outputs.

Language Modelling

363
0.28 stars / hour

LAION-5B: An open large-scale dataset for training next generation image-text models

mlfoundations/open_clip NeurIPS 2022 Datasets and Benchmarks 2022

We show successful replication and fine-tuning of foundational models like CLIP, GLIDE and Stable Diffusion using the dataset, and discuss further experiments enabled with an openly available dataset of this scale.

Image Generation Zero-Shot Learning

3,160
0.27 stars / hour