⏩ Open MatSci ML Toolkit : A Flexible Framework for Deep Learning on the OpenCatalyst Dataset

🖥 Github: https://github.com/intellabs/matsciml

🗒 Paper: https://arxiv.org/abs/2210.17484v1

➡️ Dataset: https://paperswithcode.com/dataset/cluster

@ArtificialIntelligencedl

🖥 Dataset Distillation via Factorization

git clone https://github.com/Huage001/DatasetFactorization.git
cd DatasetFactorization
pip install -r requirements.txt

🖥 Github: https://github.com/huage001/datasetfactorization

🗒 Paper: https://arxiv.org/abs/2210.16774v1

➡️ Dataset: https://paperswithcode.com/dataset/svhn

@ArtificialIntelligencedl

💻 Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

🖥 Github: https://github.com/redwoodresearch/easy-transformer

🗒 Paper: https://arxiv.org/abs/2211.00593v1

➡️ Colab: https://colab.research.google.com/drive/1UfT8HQxHpmSKD1HjWcoUYETiYlL8_XB8?usp=sharing .

@ArtificialIntelligencedl

🌃 Big Data - действительно полезный блог для всех, кто работает с данными.

- огромный набор бесплатных датасетов
- инструменты для работы с данными
- обучающие материалы для датасаентистов
- перевод книг и статей

🔥 Смотреть

👣 Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models

🖥 Github: https://github.com/lmxyy/sige

📍 Project: https://www.cs.cmu.edu/~sige/

🗒 Paper: https://arxiv.org/abs/2211.02048v1

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

@ArtificialIntelligencedl

⭐️ Ambiguity-Aware Multi-Object Pose Optimization for Visually-Assisted Robot Manipulation

$ git clone [email protected]:rpmsnu/PrimA6D.git

🖥 Github: https://github.com/rpmsnu/prima6d

🗒 Paper: https://arxiv.org/abs/2211.00960v1

➡️ Dataset: https://paperswithcode.com/dataset/ycb-video

@ArtificialIntelligencedl

✅ Large Language Models Are Human-Level Prompt Engineers

Automatic Prompt Engineer (APE) for automatic instruction generation and selection.

pip install -e .
🖥 Github: https://github.com/keirp/automatic_prompt_engineer

👣 Colab: https://colab.research.google.com/drive/1Hrz6Q7GFdH5OVg3Dis86f5OqiGdkDfRP?usp=sharing

🖥 Project: https://sites.google.com/view/automatic-prompt-engineer

🗒 Paper: https://arxiv.org/abs/2211.01910v1

➡️ Demo: https://colab.research.google.com/drive/1oL1CcvzRybAbmeqs--2csaIvSOpjH072?usp=sharing

@ArtificialIntelligencedl

💫 Galaxy Image Deconvolution for Weak Gravitational Lensing with Physics-informed Deep Learning

git clone https://github.com/Lukeli0425/Galaxy-Deconv.git

🖥 Github: https://github.com/Lukeli0425/Galaxy-Deconv

🗒 Paper: https://arxiv.org/abs/2211.01567v1

➡️ Dataset: https://drive.google.com/drive/folders/1IwgvbetMDpLK2skRalYWmth2J1gvF-qm

@ArtificialIntelligencedl

WEBVICOB 🕸 : WEB based VIsual COrpus Builder

🖥 Github: https://github.com/clovaai/webvicob

🗒 Paper: https://arxiv.org/abs/2211.03256v1

➡️ Dataset: https://dumps.wikimedia.org/other/enterprise_html/runs

@ArtificialIntelligencedl

Robust Reflection Removal with Reflection-free Flash-only Cues (RFC)

conda env create -f environment.yml
conda activate flashrr-rfc
bash download.sh
python test.py

🖥 Github: https://github.com/ChenyangLEI/flash-reflection-removal

🗒 Paper: https://arxiv.org/abs/2211.02914v1

⭐️ Project: https://chenyanglei.github.io/flashrr_rfc/index.html

➡️ Dataset: https://hkustconnect-my.sharepoint.com/:u:/g/personal/cleiaa_connect_ust_hk/EWv1afaxrhFKlbT7iX0b8FMB8R1ZeNyUWRQM__A_SPkVGQ?e=8IbhE6

@ArtificialIntelligencedl

💬 MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation

🖥 Github: https://github.com/victorsungo/mmdialog

🗒 Paper: https://arxiv.org/abs/2211.05719v1

➡️ Dataset: https://paperswithcode.com/dataset/openvidial

@ArtificialIntelligencedl

⭐️ MACSum: Controllable Summarization with Mixed Attributes

MACSum is the first human-annotated summarization dataset for controlling mixed attributes.

🖥 Github: https://github.com/psunlpgroup/macsum

🗒 Paper: https://arxiv.org/abs/2211.05041v1

➡️ Dataset: https://paperswithcode.com/dataset/macsum

@ArtificialIntelligencedl

✔️ PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping

🖥 Github: https://github.com/mindslab-ai/phaseaug

🗒 Paper: https://arxiv.org/abs/2211.04610v1

➡️ Dataset: https://keithito.com/LJ-Speech-Dataset/

@ArtificialIntelligencedl

⭐️ Nebullvm

nebullvm is an open-source tool designed to speed up AI inference in just a few lines of code.

🖥 Github: https://github.com/nebuly-ai/nebullvm

🗒 Docs: https://nebuly.gitbook.io/nebuly/nebullvm/installation

➡️ Notebooks: https://github.com/nebuly-ai/nebullvm/tree/main/notebooks

@ArtificialIntelligencedl

⭐️ MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction

🖥 Github: https://paperswithcode.com/paper/maven-ere-a-unified-large-scale-dataset-for

🗒 Paper: https://arxiv.org/abs/2211.07342v1

➡️ Dataset: https://paperswithcode.com/dataset/maven

@ArtificialIntelligencedl

MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets

git clone https://github.com/pytorch/fairseq
cd fairseq
pip install --editable ./
git clone https://github.com/ddlBoJack/MT4SSL

🖥 Github: https://github.com/ddlbojack/mt4ssl

🗒 Paper: https://arxiv.org/abs/2211.07321v1

➡️ Dataset: https://paperswithcode.com/dataset/librispeech

@ArtificialIntelligencedl

🖥 MAGE PyTorch Implementation

git clone https://github.com/LTH14/mage.git
cd mage

🖥 Github: https://github.com/lth14/mage

🗒 Paper: https://arxiv.org/abs/2211.09117v1

➡️ Dataset: https://image-net.org/download

@ArtificialIntelligencedl

🖥 Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks

🖥 Github: https://github.com/fundamentalvision/Uni-Perceiver

🗒 Paper: https://arxiv.org/abs/2211.09808v1

➡️ Data: https://github.com/fundamentalvision/Uni-Perceiver/blob/main/data/prepare_data.md

@ArtificialIntelligencedl

VeLO: Training Versatile Learned Optimizers by Scaling Up


🖥 Github: https://github.com/google/learned_optimization/tree/main/learned_optimization/research/general_lopt

🗒 Paper: https://arxiv.org/abs/2211.09760v1

➡️ Dataset: https://paperswithcode.com/dataset/librispeech

⚡️ Colab: https://colab.research.google.com/github/google/learned_optimization/blob/main/learned_optimization/research/general_lopt/Demo_for_training_a_model_with_a_learned_optimizer.ipynb

@ArtificialIntelligencedl

⭐️UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer

🖥 Github: https://github.com/OpenGVLab/UniFormerV2

🗒 Paper: https://arxiv.org/abs/2211.09552v1

➡️ Dataset: https://paperswithcode.com/dataset/hacs
@ArtificialIntelligencedl