This is your work, valued
fromage. π§ Code and models for the ICML 2023 paper "Grounding Language Models to Images for Multimodal Inputs and Outputs".
β 485gill. π Code and models for the NeurIPS 2023 paper "Generating Images with Multimodal Language Models".
β 472search-agents. Code for the paper π³ Tree Search for Language Model Agents
β 223multi-agent-computer-use. Code for the multi-agent computer use project.
β 17color-coherence-vectors. Image classification on a very limited dataset of CIFAR-10 images using color coherence vectors.
β 7hidden-markov-model. Hidden Markov model and multilayer perceptron for part-of-speech (POS) tagging.
β 4prob-stats. Dank notes and tidbits for the SUTD course, 50.034: Introduction to Probability and Statistics.
β 3lasagna. Jupyter Notebook
β 38bitALU. 8-bit ALU on an FPGA.
β 3face_verification. Face comparison and verification using dlib.
β 2densenet-stl10. This repository contains PyTorch code to train a DenseNet on the STL10 dataset.
β 2Term4_2D. Java
β 250.005ProgAssignment2. Java
β 2CRF-sentiment-analysis. Python
β 2dwm. Python
β 2gemini_vwa_debug. Python
β 1kohjingyu.github.io. HTML
β 1places365. The Places365-CNNs for Scene Classification
β 1sentiment_map. Sentiment map based on social media information in Singapore.
β 1color-conversion. Useful color conversion algorithms written in Python.
β 1LEDMatrix. LEDMatrix code for the Mojo.
β 1libdw4. A combination of the eBot API and libdw SOAR
β 1Planthing. Digital World 1D project
β 1iOSWorld. Swift
β 10multi-agent-computer-use. Code for the multi-agent computer use project.
β 18Odysseys. Python
β 9playwright-mcp. Playwright MCP server
β 35ksearch-agents. Code for the paper π³ Tree Search for Language Model Agents
β 223visualwebarena. VisualWebArena is a benchmark for multimodal agents.
β 483prm800k. 800,000 step-level correctness labels on LLM solutions to MATH problems
β 2.1kjspaint. π¨ Classic MS Paint, οΌ²οΌ₯οΌΆοΌ©οΌΆοΌ₯οΌ€ + β¨Extras
β 7.8kopen_flamingo. An open-source framework for training large multimodal models.
β 4.1kgill. π Code and models for the NeurIPS 2023 paper "Generating Images with Multimodal Language Models".
β 472mmc4. MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.
β 953clip-retrieval. Easily compute clip embeddings and build a clip retrieval system with them
β 2.8ktest. Measuring Massive Multitask Language Understanding | ICLR 2021
β 1.6kVitaminC. Contrastive Fact Verification
β 74xg2xg. by ex-googlers, for ex-googlers - a lookup table of similar tech & services
β 16kfromage. π§ Code and models for the ICML 2023 paper "Grounding Language Models to Images for Multimodal Inputs and Outputs".
β 485cramming. Cramming the training of a (BERT-type) language model into limited compute.
β 1.4knanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.
β 61kdiffusers. π€ Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
β 34kopen_clip. An open source implementation of CLIP.
β 14kmagma. MAGMA - a GPT-style multimodal model that can understand any combination of images and language. NOTE: The freely available model from this repo is only a demo. For the latest multimodal and multilingual models from Aleph Alpha check out our website https://app.aleph-alpha.com
β 489bitsandbytes. Accessible large language models via k-bit quantization for PyTorch.
β 8.3ksacrebleu. Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons
β 1.3kcoyo-dataset. COYO-700M: Large-scale Image-Text Pair Dataset
β 1.3kse3ds. This repository hosts the code for our paper, "Simple and Effective Synthesis of Indoor 3D Scenes".
β 42parti.
β 1.6krq-vae-transformer. The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)
β 1ks4. Structured state space sequence models
β 2.9kmetaseq. Repo for external large-scale work
β 6.5krestricted-boltzmann-machines. Restricted Boltzmann Machines in Python.
β 971boltzmann-machines. Boltzmann Machines in TensorFlow with examples
β 851ScienceWorld. ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.
β 364StyleNeRF. This is the open source implementation of the ICLR2022 paper "StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis"
β 950world-model-as-a-graph. Code for "World Model as a Graph: Learning Latent Landmarks for Planning" (ICML 2021 Long Presentation)
β 71SAMP. Stochastic Scene-Aware Motion Prediction https://samp.is.tue.mpg.de/
β 145MiDaS. Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"
β 5.4kimproved-diffusion. Release for Improved Denoising Diffusion Probabilistic Models
β 3.8kVideoAutoencoder. Video Autoencoder: self-supervised disentanglement of 3D structure and motion (ICCV 2021). Website: https://zlai0.github.io/VideoAutoencoder/
β 184Recurrent-VLN-BERT. Code of the CVPR 2021 Oral paper: A Recurrent Vision-and-Language BERT for Navigation
β 208mipnerf. Python
β 939learning_with_noise. Learning to See by Looking at Noise
β 115pixelsynth. [ICCV 2021] PixelSynth: Generating a 3D-Consistent Experience from a Single Image
β 116pathdreamer. Jupyter Notebook
β 163mdetr. Python
β 1.1kHVP. PyTorch implementation of our paper, "Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction."
β 21scenic. Scenic: A Jax Library for Computer Vision Research and Beyond
β 3.8khabitat-matterport-3dresearch.
β 729OASIS. Official implementation of the paper "You Only Need Adversarial Supervision for Semantic Image Synthesis" (ICLR 2021)
β 339xmcgan_image_generation. Python
β 100giraffe. This repository contains the code for the CVPR 2021 paper "GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields"
β 1.2kwebvid. Large-scale text-video dataset. 10 million captioned short videos.
β 684Replica-Dataset. The Replica Dataset v1 as published in https://arxiv.org/abs/1906.05797 .
β 1.3kflaxmodels. Pretrained deep learning models for Jax/Flax: StyleGAN2, GPT2, VGG, ResNet, etc.
β 266pangea. Panoramic Graph Environment Annotation toolkit, for collecting audio and text annotations in panoramic graph environments such as Matterport3D and StreetLearn.
β 19clean-fid. PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]
β 1.2kFourier-Discrepancies-CNN-Detection. [CVPR 2021: Oral] In this work, we show that high frequency Fourier spectrum decay discrepancies are not inherent characteristics for existing CNN-based generative models.
β 29trecs_image_generation.
β 24ml-hypersim. Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding
β 2ktensorflow-wavenet. A TensorFlow implementation of DeepMind's WaveNet paper
β 5.4kNVAE. The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)
β 1.1kvdvae. Repository for the paper "Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images"
β 453synsin. View synthesis for the public.
β 675imaginaire. NVIDIA's Deep Imagination Team's PyTorch Library
β 4.1kminGPT. A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
β 25kXLM. PyTorch original implementation of Cross-lingual Language Model Pretraining.
β 2.9kdetr. End-to-End Object Detection with Transformers
β 15khabitat-sim. A flexible, high-performance 3D simulator for Embodied AI research.
β 3.7kDSGAN. Implementation of Diversity-Sensitive Conditional Generative Adversarial Networks (ICLR 2019)
β 98Oscar. Oscar and VinVL
β 1.1khabitat-lab. A modular high-level library to train embodied AI agents across a variety of tasks and environments.
β 3.1kVLN-CE. Vision-and-Language Navigation in Continuous Environments using Habitat
β 830Matterport3DSimulator. AI Research Platform for Reinforcement Learning from Real Panoramic Images.
β 701smooth-taylor. PyTorch implementation of SmoothTaylor
β 15AttnGAN. Python
β 1.4kALAE. [CVPR2020] Adversarial Latent Autoencoders
β 3.5kmimicry. [CVPR 2020 Workshop] A PyTorch GAN library that reproduces research results for popular GANs.
β 608semantic-object-accuracy-for-generative-text-to-image-synthesis. Code for "Semantic Object Accuracy for Generative Text-to-Image Synthesis" (TPAMI 2020)
β 106localized-narratives. Localized Narratives
β 86Google_Refexp_toolbox. The toolbox for the Google Refexp dataset proposed in this paper: http://arxiv.org/abs/1511.02283
β 166Obj-GAN. Obj-GAN - Official PyTorch Implementation
β 285StackGAN-Pytorch. Python
β 494text. Making text a first-class citizen in TensorFlow.
β 1.3kneurips18_hierchical_image_manipulation. Pytorch Implementation of NeurIPS'18 paper on Generative Image Manipulation with Hierarchical Semantic Structures
β 68generative_inpainting. DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral
β 3.5kimage_completion_tf2. "Globally and Locally Consistent Image Completion" with Tensorflow2 Keras
β 31tictaitoe. Tic-Tac-Toe environment for Reinforcement learning. Written similarly to how OpenAI gym environment works
β 1pwc. This repository is no longer maintained.
β 15kpython-flickr-api. A python implementation of the Flickr API
β 374dl_landscapes_paper. Buscombe & Ritchie (2018) Landscape Classification with Deep Neural Networks. Geosciences 2018, 8(7), 244
β 22pix2pixHD. Synthesizing and manipulating 2048x1024 images with conditional GANs
β 6.9kcifar-10h. Original dataset release for CIFAR-10H
β 85SPADE-Tensorflow. Simple Tensorflow implementation of "Semantic Image Synthesis with Spatially-Adaptive Normalization" a.k.a. GauGAN, SPADE (CVPR 2019 Oral)
β 375SPADE. Semantic Image Synthesis with SPADE
β 7.7kconvnet-aig. PyTorch implementation for Convolutional Networks with Adaptive Inference Graphs
β 184land-cover. Code for training and testing deep learning based land cover models.
β 98awesome-satellite-imagery-datasets. π°οΈ List of satellite image training datasets with annotations for computer vision and deep learning
β 3.9kjax. Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
β 36kganhacks. starter from "How to Train a GAN?" at NIPS2016
β 12kDRIT. Learning diverse image-to-image translation from unpaired data
β 856Material. A UI/UX framework for creating beautiful applications.
β 12kpytorch_tiramisu. FC-DenseNet in PyTorch for Semantic Segmentation
β 303bert. TensorFlow code and pre-trained models for BERT
β 40kpydensecrf. Python wrapper to Philipp KrΓ€henbΓΌhl's dense (fully connected) CRFs with gaussian edge potentials.
β 2klatex-homework-class. A class for homework assignments written in LaTeX.
β 160places365. The Places365-CNNs for Scene Classification
β 2.1kpytorch-deeplab-resnet. DeepLab resnet v2 model in pytorch
β 602