A framework for COntextual Document Embedding Reranking

A curated list of awesome papers related to pre-trained models for information retrieval (a.k.a., pretraining for IR).

If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions

TUI for the Slurm Workload Manager

Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification

Exploring prompt tuning with pseudolabels for multiple modalities, learning settings, and training strategies.

✨✨Latest Advances on Multimodal Large Language Models

Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.

Learning to compose soft prompts for compositional zero-shot learning.

Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks

LaTeX Template for Mike Morrison's #betterposter

A system for prompted weak supervision. Alfred is a powerful tool that leverages large language models to accelerate data annotation.

Locating and editing factual associations in GPT (NeurIPS 2022)

A weak supervision framework for (partial) labeling functions

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

A modular RL library to fine-tune language models to human preferences

Case Studies for using Accera - the open source cross-platform compiler from Microsoft Research - to create high performance deep learning computations (i.e. GEMM, Convolution, etc.)

Framework for zero-shot learning with knowledge graphs.

Resources for Data Centric AI

Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy

A curated list of references for MLOps

Learn how to design, develop, deploy and iterate on production-grade ML applications.

Serve, optimize and scale PyTorch models in production

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

MERLOT: Multimodal Neural Script Knowledge Models

😎 An up-to-date & curated list of awesome semi-supervised learning papers, methods & resources.

Recognition to Cognition Networks (code for the model in "From Recognition to Cognition: Visual Commonsense Reasoning", CVPR 2019)

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering (EMNLP 2020)