🔊 Textless NLP: Generating expressive speech from raw audio

Facebook Ai: https://ai.facebook.com/blog/textless-nlp-generating-expressive-speech-from-raw-audio/

Examples: https://speechbot.github.io/pgslm/

Code: https://github.com/pytorch/fairseq/tree/master/examples/textless_nlp/gslm

Paper: https://arxiv.org/abs/2102.01192

@ai_machinelearning_big_data

✅ AliceMind: ALIbaba's Collection of Encoder-decoders from MinD (Machine IntelligeNce of Damo) Lab

Github: https://github.com/alibaba/AliceMind

Paper: https://arxiv.org/abs/2109.05687v1

Dataset: https://paperswithcode.com/dataset/glue

@ArtificialIntelligencedl

🔧 Neural Networks Block Movement Pruning

Code: https://github.com/huggingface/nn_pruning

Paper: https://arxiv.org/abs/2109.04838v1

Documentation: https://github.com/huggingface/nn_pruning/blob/main/docs/HOWTO.md

@ai_machinelearning_big_data

📖 Physics-Based Deep Learning

Book: https://www.physicsbaseddeeplearning.org/intro.html

Github: https://github.com/thunil/Physics-Based-Deep-Learning

Deep-Flow-Prediction: https://github.com/thunil/Deep-Flow-Prediction

Paper: https://arxiv.org/abs/2109.05237v1

@ai_machinelearning_big_data

✅ AliceMind: ALIbaba's Collection of Encoder-decoders from MinD (Machine IntelligeNce of Damo) Lab

Github: https://github.com/alibaba/AliceMind

Paper: https://arxiv.org/abs/2109.05687v1

Dataset: https://paperswithcode.com/dataset/glue

🗳 Image Shape Manipulation from a Single Augmented Training Sample

Github: https://github.com/eliahuhorwitz/DeepSIM

Paper: https://arxiv.org/abs/2109.06151v1

Dataset: https://paperswithcode.com/dataset/cityscapes

Project: http://www.vision.huji.ac.il/deepsim

@ai_machinelearning_big_data

DensePhrases is an extractive phrase search tool based on your natural language inputs

Github: https://github.com/princeton-nlp/DensePhrases

Paper: https://arxiv.org/abs/2109.08133v1

Dataset: https://paperswithcode.com/dataset/squad

@ai_machinelearning_big_data

☄️ Uncertainty-Aware Machine Translation Evaluation

Code: https://github.com/Unbabel/COMET

Paper: https://arxiv.org/abs/2109.06352v1

Documentation: https://unbabel.github.io/COMET/html/index.html

@ai_machinelearning_big_data

🌳 WildWood: a new Random Forest algorithm

Github: https://github.com/pyensemble/wildwood

Paper: https://arxiv.org/abs/2109.08010v1

Documentation: https://wildwood.readthedocs.io/

@ai_machinelearning_big_data

📄 Revisiting Mask-Head Architectures for Novel Class Instance Segmentation

https://ai.googleblog.com/2021/09/revisiting-mask-head-architectures-for.html

DeepMAC model: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/deepmac.md

Paper: https://arxiv.org/abs/2104.00613

@ai_machinelearning_big_data

❓ Simple Entity-Centric Questions Challenge Dense Retrievers

Github: https://github.com/princeton-nlp/entityquestions

Paper: https://arxiv.org/abs/2109.08535v1

Dataset: https://paperswithcode.com/dataset/natural-questions

@ai_machinelearning_big_data

📚 The Machine & Deep Learning Compendium Open Book

https://book.mlcompendium.com/

GitBook: https://github.com/orico/www.mlcompendium.com

@ai_machinelearning_big_data

Dynamic Slimmable Network (DS-Net)

Github: https://github.com/M3DV/AlignShift

Paper: https://arxiv.org/abs/2109.10060v1

@ArtificialIntelligencedl

Language Models are Few-shot Multilingual Learners

Github: https://github.com/gentaiscool/few-shot-lm

Paper: https://arxiv.org/abs/2109.07684v1

@ai_machinelearning_big_data

🤖 CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research

CompilerGym is a library of easy to use and performant reinforcement learning environments for compiler tasks.

Github: https://github.com/facebookresearch/CompilerGym

Documents: https://facebookresearch.github.io/CompilerGym/

Paper: https://arxiv.org/abs/2109.08267v1

@ai_machinelearning_big_data

🚀 Building AI that can generate images of things it has never seen before

Github: https://github.com/facebookresearch/ic_gan

Facebook Ai: https://ai.facebook.com/blog/instance-conditioned-gans/

Documents: https://facebookresearch.github.io/CompilerGym/

Paper: https://arxiv.org/abs/2109.05070

@ai_machinelearning_big_data

📥 Don’t be Contradicted with Anything!CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System

Github: https://github.com/yizhen20133868/ci-tod

Paper: https://arxiv.org/abs/2109.11292v1

Dataset: https://paperswithcode.com/dataset/kvret-1

@ai_machinelearning_big_data

Unseen Object Amodal Instance Segmentation (UOAIS)

Github: https://github.com/gist-ailab/uoais

Paper: https://arxiv.org/abs/2109.11103

Dataset: https://paperswithcode.com/dataset/ocid

Project: https://sites.google.com/view/uoais

@ai_machinelearning_big_data

AlphaRotate: A Rotation Detection Benchmark using TensorFlow

Github: https://github.com/yangxue0827/RotationDetection

Paper: https://arxiv.org/abs/2109.11906v1

Dataset: https://paperswithcode.com/dataset/dota

Documentation: https://rotationdetection.readthedocs.io/en/latest/

@ai_machinelearning_big_data

🧍‍♂ PASS: Pictures without humAns for Self-Supervised Pretraining

PASS is a large-scale image dataset that does not include any humans, human parts, or other personally identifiable information.

Github: https://github.com/yukimasano/PASS

Paper: https://arxiv.org/abs/2109.13228v1

Dataset: https://paperswithcode.com/dataset/pass

Documentation: https://www.robots.ox.ac.uk/~vgg/research/pass/

@ai_machinelearning_big_data

🧠 С момента выкладки библиотеки CatBoost в опенсорс прошло 100 лет! (Это если считать в двоичной системе счисления). Но главная новость в другом: библиотека обновилась до версии 1.0.0 и достигла состояния «production ready».

Более подробно обо всём этом читайте на Хабре: https://habr.com/ru/company/yandex/blog/580950/

@ai_machinelearning_big_data