Home

PwC

Default view
Name
Code Link
Description
Retrieved
Stars
https://github.com/MTLab/MorphMLP
With such multi-dimension and multi-scale factorization, our MorphMLP block can achieve a great accuracy-computation balance. Code: https://github.com/MTLab/MorphMLP
2023/01/30
92
/salesforce/ ProGen2: Exploring the Boundaries of Protein Language Models
Open
https://github.com/salesforce/progen
Attention-based models trained on protein sequences have demonstrated incredible success at classification and generation tasks relevant for artificial intelligence-driven protein design. Code: https://github.com/salesforce/progen
2023/01/30
170
/salesforce/ Salesforce CausalAI Library: A Fast and Scalable Framework for Causal Analysis of Time Series and Tabular Data
Open
https://github.com/salesforce/causalai
We introduce the Salesforce CausalAI Library, an open-source library for causal analysis using observational data. Code: https://github.com/salesforce/causalai
2023/01/28
21
/microsoft/ BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining
Open
https://github.com/microsoft/biogpt
Pre-trained language models have attracted increasing attention in the biomedical domain, inspired by their great success in the general natural language domain. Code: https://github.com/microsoft/biogpt
2023/01/28
158
/zhongcl-thu/ SNAKE: Shape-aware Neural 3D Keypoint Field
Open
https://github.com/zhongcl-thu/snake
Detecting 3D keypoints from point clouds is important for shape reconstruction, while this work investigates the dual question: can shape reconstruction benefit 3D keypoint detection? Code: https://github.com/zhongcl-thu/snake
2023/01/28
187
/air-discover/ VIBUS: Data-efficient 3D Scene Parsing with VIewpoint Bottleneck and Uncertainty-Spectrum Modeling
Open
https://github.com/air-discover/vibus
In the first stage, we perform self-supervised representation learning on unlabeled points with the proposed Viewpoint Bottleneck loss function. Code: https://github.com/air-discover/vibus
2023/01/28
156
/serycjon/ Planar Object Tracking via Weighted Optical Flow
Open
https://github.com/serycjon/WOFT
We propose WOFT -- a novel method for planar object tracking that estimates a full 8 degrees-of-freedom pose, i. e. the homography w. r. t. Code: https://github.com/serycjon/WOFT
2023/01/27
32
/sjvasquez/ Generating Sequences With Recurrent Neural Networks
Open
https://github.com/sjvasquez/handwriting-synthesis
This paper shows how Long Short-term Memory recurrent neural networks can be used to generate complex sequences with long-range structure, simply by predicting one data point at a time. Code: https://github.com/sjvasquez/handwriting-synthesis
2023/01/27
1923
/facebookresearch/ Cut and Learn for Unsupervised Object Detection and Instance Segmentation
Open
https://github.com/facebookresearch/cutler
We propose Cut-and-LEaRn (CutLER), a simple approach for training unsupervised object detection and segmentation models. Code: https://github.com/facebookresearch/cutler
2023/01/27
76
/hustvl/ A Simple Adaptive Unfolding Network for Hyperspectral Image Reconstruction
Open
https://github.com/hustvl/saunet
We present a simple, efficient, and scalable unfolding network, SAUNet, to simplify the network design with an adaptive alternate optimization framework for hyperspectral image (HSI) reconstruction. Code: https://github.com/hustvl/saunet
2023/01/27
16
/microsoft/ TorchGeo: Deep Learning With Geospatial Data
Open
https://github.com/microsoft/torchgeo
Deep learning methods are particularly promising for modeling many remote sensing tasks given the success of deep neural networks in similar computer vision tasks and the sheer volume of remotely sensed imagery available. Code: https://github.com/microsoft/torchgeo
2023/01/27
1391
/chaitjo/ On the Expressive Power of Geometric Graph Neural Networks
Open
https://github.com/chaitjo/geometric-gnn-dojo
The expressive power of Graph Neural Networks (GNNs) has been studied extensively through the Weisfeiler-Leman (WL) graph isomorphism test. Code: https://github.com/chaitjo/geometric-gnn-dojo
2023/01/26
30
/sarafridov/ K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
Open
https://github.com/sarafridov/k-planes
We introduce k-planes, a white-box model for radiance fields in arbitrary dimensions. Code: https://github.com/sarafridov/k-planes
2023/01/26
67
/stanfordnlp/ Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP
Open
https://github.com/stanfordnlp/dsp
Retrieval-augmented in-context learning has emerged as a powerful approach for addressing knowledge-intensive tasks using frozen language models (LM) and retrieval models (RM). Code: https://github.com/stanfordnlp/dsp
2023/01/26
140
/wxjiao/ Is ChatGPT A Good Translator? A Preliminary Study
Open
https://github.com/wxjiao/is-chatgpt-a-good-translator
This report provides a preliminary evaluation of ChatGPT for machine translation, including translation prompt, multilingual translation, and translation robustness. Code: https://github.com/wxjiao/is-chatgpt-a-good-translator
2023/01/25
33
/hazyresearch/ Hungry Hungry Hippos: Towards Language Modeling with State Space Models
Open
https://github.com/hazyresearch/h3
First, we use synthetic language modeling tasks to understand the gap between SSMs and attention. Code: https://github.com/hazyresearch/h3
2023/01/25
109
/autonomousvision/ StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis
Open
https://github.com/autonomousvision/stylegan-t
Text-to-image synthesis has recently seen significant progress thanks to large pretrained language models, large-scale training data, and the introduction of scalable model families such as diffusion and autoregressive models. Code: https://github.com/autonomousvision/stylegan-t
2023/01/25
197
/showlab/ Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
Open
https://github.com/showlab/Tune-A-Video
To reproduce the success of text-to-image (T2I) generation, recent works in text-to-video (T2V) generation employ large-scale text-video dataset for fine-tuning. Code: https://github.com/showlab/Tune-A-Video
2023/01/22
113
/facebookresearch/ Learning-Rate-Free Learning by D-Adaptation
Open
https://github.com/facebookresearch/dadaptation
In this work, we describe a single-loop method, with no back-tracking or line searches, which does not require knowledge of $D$ yet asymptotically achieves the optimal rate of convergence for the complexity class of convex Lipschitz functions. Code: https://github.com/facebookresearch/dadaptation
2023/01/22
61
/gallilmaimon/ Speaking Style Conversion With Discrete Self-Supervised Units
Open
https://github.com/gallilmaimon/DISSC
We introduce a suite of quantitative and qualitative evaluation metrics for this setup, and empirically demonstrate the proposed approach is significantly superior to the evaluated baselines. Code: https://github.com/gallilmaimon/DISSC
2023/01/22
40
/facebookresearch/ Multiview Compressive Coding for 3D Reconstruction
Open
https://github.com/facebookresearch/mcc
We introduce a simple framework that operates on 3D points of single objects or whole scenes coupled with category-agnostic large-scale training from diverse RGB-D videos. Code: https://github.com/facebookresearch/mcc
2023/01/21
79
/BlinkDL/ GLU Variants Improve Transformer
Open
https://github.com/BlinkDL/RWKV-LM
Gated Linear Units (arXiv:1612. 08083) consist of the component-wise product of two linear projections, one of which is first passed through a sigmoid function. Code: https://github.com/BlinkDL/RWKV-LM
2023/01/21
1008
/hello-simpleai/ How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection
Open
https://github.com/hello-simpleai/chatgpt-comparison-detection
We call the collected dataset the Human ChatGPT Comparison Corpus (HC3). Code: https://github.com/hello-simpleai/chatgpt-comparison-detection
2023/01/21
239
/sileod/ $\texttt{tasksource}$: Structured Dataset Preprocessing Annotations for Frictionless Extreme Multi-Task Learning and Evaluation
Open
https://github.com/sileod/tasksource
We release a dataset annotation framework and dataset annotations for more than 400 English tasks (https://github. com/sileod/tasksource). Code: https://github.com/sileod/tasksource
2023/01/20
22
/slds-lmu/ Multimodal Deep Learning
Open
https://github.com/slds-lmu/seminar_multimodal_dl
This book is the result of a seminar in which we reviewed multimodal approaches and attempted to create a solid overview of the field, starting with the current state-of-the-art approaches in the two subfields of Deep Learning individually. Code: https://github.com/slds-lmu/seminar_multimodal_dl
2023/01/20
69
/gligen/ GLIGEN: Open-Set Grounded Text-to-Image Generation
Open
https://github.com/gligen/GLIGEN
Large-scale text-to-image diffusion models have made amazing advances. Code: https://github.com/gligen/GLIGEN
2023/01/20
93
/kinyugo/ Msanii: High Fidelity Music Synthesis on a Shoestring Budget
Open
https://github.com/kinyugo/msanii
In this paper, we present Msanii, a novel diffusion-based model for synthesizing long-context, high-fidelity music efficiently. Code: https://github.com/kinyugo/msanii
2023/01/20
64
/timothybrooks/ InstructPix2Pix: Learning to Follow Image Editing Instructions
Open
https://github.com/timothybrooks/instruct-pix2pix
We propose a method for editing images from human instructions: given an input image and a written instruction that tells the model what to do, our model follows these instructions to edit the image. Code: https://github.com/timothybrooks/instruct-pix2pix
2023/01/20
264
/open-mmlab/ RTMDet: An Empirical Study of Designing Real-Time Object Detectors
Open
https://github.com/open-mmlab/mmyolo
In this paper, we aim to design an efficient real-time object detector that exceeds the YOLO series and is easily extensible for many object recognition tasks such as instance segmentation and rotated object detection. Code: https://github.com/open-mmlab/mmyolo
2023/01/18
1058
/agemagician/ Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling
Open
https://github.com/agemagician/Ankh
As opposed to scaling-up protein language models (PLMs), we seek improving performance via protein-specific optimization. Code: https://github.com/agemagician/Ankh
2023/01/18
31
/salesforce/ EDICT: Exact Diffusion Inversion via Coupled Transformations
Open
https://github.com/salesforce/edict
EDICT enables mathematically exact inversion of real and model-generated images by maintaining two coupled noise vectors which are used to invert each other in an alternating fashion. Code: https://github.com/salesforce/edict
2023/01/18
63
/cleanlab/ Utilizing supervised models to infer consensus labels and their quality from data with multiple annotators
Open
https://github.com/cleanlab/cleanlab
Many algorithms also rely solely on annotator statistics, ignoring the features of the examples from which the annotations derive. Code: https://github.com/cleanlab/cleanlab
2023/01/18
4671
/zuruoke/ Free-Form Image Inpainting with Gated Convolution
Open
https://github.com/zuruoke/watermark-removal
We present a generative image inpainting system to complete images with free-form mask and guidance. Code: https://github.com/zuruoke/watermark-removal
2023/01/17
686
/deepmind/ Tracr: Compiled Transformers as a Laboratory for Interpretability
Open
https://github.com/deepmind/tracr
Interpretability research aims to build tools for understanding machine learning (ML) models. Code: https://github.com/deepmind/tracr
2023/01/17
249
/open-mmlab/ SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos
Open
https://github.com/open-mmlab/mmpose
With a simple yet effective motion-aware fully-connected network, SmoothNet improves the temporal smoothness of existing pose estimators significantly and enhances the estimation accuracy of those challenging frames as a side-effect. Code: https://github.com/open-mmlab/mmpose
2023/01/16
2917
/opendr-eu/ VPIT: Real-time Embedded Single Object 3D Tracking Using Voxel Pseudo Images
Open
https://github.com/opendr-eu/opendr
In this paper, we propose a novel voxel-based 3D single object tracking (3D SOT) method called Voxel Pseudo Image Tracking (VPIT). Code: https://github.com/opendr-eu/opendr
2023/01/14
366
/hku-mars/ ImMesh: An Immediate LiDAR Localization and Meshing Framework
Open
https://github.com/hku-mars/immesh
This voxel-wise meshing operation is delicately designed for the purpose of efficiency; it first performs a dimension reduction by projecting 3D points to a 2D local plane contained in the voxel, and then executes the meshing operation with pull, commit and push steps for incremental reconstruction of triangle facets. Code: https://github.com/hku-mars/immesh
2023/01/14
147
/google/ Vectorized and performance-portable Quicksort
Open
https://github.com/google/highway
Recent works showed that implementations of Quicksort using vector CPU instructions can outperform the non-vectorized algorithms in widespread use. Code: https://github.com/google/highway
2023/01/13
2176
/PrieureDeSion/ GNM: A General Navigation Model to Drive Any Robot
Open
https://github.com/PrieureDeSion/drive-any-robot
Learning provides a powerful tool for vision-based navigation, but the capabilities of learning-based policies are constrained by limited training data. Code: https://github.com/PrieureDeSion/drive-any-robot
2023/01/13
115
/felix-petersen/ Deep Differentiable Logic Gate Networks
Open
https://github.com/felix-petersen/difflogic
Recently, research has increasingly focused on developing efficient neural network architectures. Code: https://github.com/felix-petersen/difflogic
2023/01/13
138
/sebastianstarke/ Local motion phases for learning multi-contact character movements
Open
https://github.com/sebastianstarke/AI4Animation
Training a bipedal character to play basketball and interact with objects, or a quadruped character to move in various locomotion modes, are difficult tasks due to the fast and complex contacts happening during the motion. Code: https://github.com/sebastianstarke/AI4Animation
2023/01/11
5813
/mindflow-institue/ Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Review
Open
https://github.com/mindflow-institue/awesome-transformer
The remarkable performance of the Transformer architecture in natural language processing has recently also triggered broad interest in Computer Vision. Code: https://github.com/mindflow-institue/awesome-transformer
2023/01/11
32
/keyu-tian/ Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling
Open
https://github.com/keyu-tian/spark
This is the first use of sparse convolution for 2D masked modeling. Code: https://github.com/keyu-tian/spark
2023/01/11
48
/XT-1997/ DeepMatcher: A Deep Transformer-based Network for Robust and Accurate Local Feature Matching
Open
https://github.com/XT-1997/DeepMatcher
In this work, we propose DeepMatcher, a deep Transformer-based network built upon our investigation of local feature matching in detector-free methods. Code: https://github.com/XT-1997/DeepMatcher
2023/01/11
24
/tzvilederer/ Silent Killer: Optimizing Backdoor Trigger Yields a Stealthy and Powerful Data Poisoning Attack
Open
https://github.com/tzvilederer/silent-killer
In contrast to previous attacks, both the poison and the trigger in our method are stealthy. Code: https://github.com/tzvilederer/silent-killer
2023/01/10
10
/chuhaojin/ Text2Poster: Laying out Stylized Texts on Retrieved Images
Open
https://github.com/chuhaojin/text2poster-icassp-22
Poster generation is a significant task for a wide range of applications, which is often time-consuming and requires lots of manual editing and artistic experience. Code: https://github.com/chuhaojin/text2poster-icassp-22
2023/01/10
19
/blueGorae/ DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domains
Open
https://github.com/blueGorae/DynaGAN
In this paper, we propose DynaGAN, a novel few-shot domain-adaptation method for multiple target domains. Code: https://github.com/blueGorae/DynaGAN
2023/01/10
19
/fwilliams/ Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances
Open
https://github.com/fwilliams/point-cloud-utils
Optimal transportation distances are a fundamental family of parameterized distances for histograms. Code: https://github.com/fwilliams/point-cloud-utils
2023/01/09
699
/anthropics/ Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
Open
https://github.com/anthropics/hh-rlhf
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. Code: https://github.com/anthropics/hh-rlhf
2023/01/09
205
/microsoft/ MPNet: Masked and Permuted Pre-training for Language Understanding
Open
https://github.com/microsoft/MASS
Since BERT neglects dependency among predicted tokens, XLNet introduces permuted language modeling (PLM) for pre-training to address this problem. Code: https://github.com/microsoft/MASS
2023/01/09
1201
Load more
TOP