DuaneNielsen / papers

Repository from Github https://github.comDuaneNielsen/papersRepository from Github https://github.comDuaneNielsen/papers

papers

Benchmarks / Datasets

Monocular Depth Estimation - Unsupervised

DrivingStereo: A Large-Scale Dataset for Stereo Matching in Autonomous Driving Scenarios

A Dataset and Explorer for 3D Signed Distance Functions

Differential equations

Fourier Neural Operator for Parametric Partial Differential Equations

Neural Ordinary Differential Equations

Latent ODEs for Irregularly-Sampled Time Series

Lie Algebra

Lie Groups for 2D and 3D Transformations

Stereo Matching

USegScene: Unsupervised Learning of Depth, Optical Flow and Ego-Motion with Semantic Guidance and Coupled Networks

Sparsely Annotated Object Detection: A Region-based Semi-supervised Approach

MobileStereoNet

GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Feature

Stereo Matching Basics

RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching

Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices

HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching

Deep Learning Stereo Vision at the edge

3D scene completion

Differentiable Signed Distance Function Rendering

NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video

Atlas: End-to-End 3D Scene Reconstruction from Posed Images

3D Semantic Scene Completion: a Survey

SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans

Truncated Signed Distance Fields applied to robotics

DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes

A Volumetric Method for Building Complex Models from Range Images

KinectFusion: Real-Time Dense Surface Mapping and Tracking

Signed Distance Fields: A Natural Representation for Both Mapping and Planning

TSDF Paper

Spatial Imagination With Semantic Cognition for Mobile Robots

Image extrapolation

Controllable and Progressive Image Extrapolation

Spatial description, Merelogy, Activity recognition

Spatial Intelligence

Tracking

BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models

Multi-Object Tracking with Hallucinated and Unlabeled Videos

TAP-Vid: A Benchmark for Tracking Any Point in a Video

Reinforcement Learning / AI

The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for RL

DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames

Transformers are Sample Efficient World Models

A Generalist Agent

The 37 Implementation Details of Proximal Policy Optimization

Mastering Atari Games with Limited Data

QUANTIFYING DIFFERENCES IN REWARD FUNCTIONS

Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning

Dream to Control: Learning Behaviors by Latent Imagination

Mastering Atari with Discrete World Models

Learning Invariant Representations for Reinforcement Learning without Reconstruction

Discrete Latent Space World Models for Reinforcement Learning World model based on vector quantized variational autoencoder (VQ-VAE)

Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor

SOFT ACTOR-CRITIC FOR DISCRETE ACTION SETTINGS

Proximal Policy Optimization Algorithms

World Models

High-Dimensional Continuous Control Using Generalized Advantage Estimation (Advantage)

Asynchronous Methods for Deep Reinforcement Learning

Trust Region Policy Optimization

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm (Alpha Go/Zero)

Deep Reinforcement Learning for Imperfect-Information Games

Baby A3C

Playing Atari with Deep Reinforcement Learning (Replay buffer)

Meta-SAC: Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient

Meta-Gradient Reinforcement Learning

REALM: Retrieval-Augmented Language Model Pre-Training

Continual learning

Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning

NLP

Recursively Summarizing Books with Human Feedback

Code as Policies: Language Model Programs for Embodied Control

Offline RL

IS CONDITIONAL GENERATIVE MODELING ALL YOU NEED FOR DECISION-MAKING?

Awesome Offline RL

SAMPLE-EFFICIENT REINFORCEMENT LEARNING BY BREAKING THE REPLAY RATIO BARRIER

Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations

Is Conditional Generative Modeling all you need for Decision-Making?

Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters

Know Your Boundaries: The Necessity of Explicit Behavioral Cloning in Offline RL

A Pragmatic Look at Deep Imitation Learning

Implicit Behavioral Cloning

A DATASET PERSPECTIVE ON OFFLINE REINFORCEMENT LEARNING

General Policy Evaluation and Improvement by Learning to Identify Few But Crucial States

Contrastive Learning as Goal-Conditioned Reinforcement Learning

Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems

Behavior Transformers: Cloning k modes with one stone

A Minimalist Approach to Offline Reinforcement Learning

Conservative Q-Learning for Offline Reinforcement Learning

Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning

Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning

Online and Offline Reinforcement Learning by Planning with a Learned Model

Regularized Behavior Value Estimation

Accelerating Online Reinforcement Learning with Offline Datasets

Off-Policy Evaluation via Off-Policy Classification

Learning One Representation to Optimize All Rewards

Exploration

Generalized State-Dependent Exploration for Deep Reinforcement Learning in Robotics

Is Out-of-Distribution Detection Learnable?

Differentiable physics

BRAX

Physics Based Deep Learning

Learning to Control PDEs with Differentiable Physics

DiffTaichi: Differentiable Programming for Physical Simulation

End-to-End Differentiable Physics for Learning and Control

ADD: Analytically Differentiable Dynamics for Multi-Body Systems with Frictional Contact

LEARNING MESH-BASED SIMULATION WITH GRAPH NETWORKS

Learning mesh-based simulation with graph networks

Robotics

Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulation

DEP-RL:EMBODIEDEXPLORATIONFOR REINFORCEMENTLEARNINGIN OVERACTUATEDANDMUSCULOSKELETALSYSTEMS

An Active Learning Based Robot Kinematic Calibration Framework Using Gaussian Processes

Enhanced method for reinforcement learning based dynamic obstacle avoidance by assessment of collision risk

Reinforcement Learning with Evolutionary Trajectory Generator: A General Approach for Quadrupedal Locomotion

RMA: Rapid Motor Adaptation for Legged Robots

Transporter Networks: Rearranging the Visual World for Robotic Manipulation

A micro Lie theory for state estimation in robotics

Reinforcement Learning with Videos: Combining Offline Observations with Interaction

Contingencies from Observations: Tractable ContingencyPlanning with Learned Behavior Models

DeepGait: Planning and Control of Quadrupedal Gaits using Deep Reinforcement Learning

Closing the Sim-To-Real Gap with Evolutionary Meta-Learning

Deep occupancy maps: a continuous mapping technique for dynamic environments

Multi-Object Search using Object-Oriented POMDPs

Multi-Resolution POMDP Planning for Multi-Object Search in 3D

Robot localization

Practical and Optimal LSH for Angular Distance

DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras

RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

CeMNet: Self-supervised learning for accurate continuous ego-motion estimation

HIGH SPEED NONHOLONOMIC MOBILE ROBOT ONLINE TRAJECTORY OPTIMATIZATION

RANSAC Matching: Simultaneous Registration and Segmentation

Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography

Robot arms

Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation Paper Explained

Form2Fit: Learning Shape Priors for Generalizable Assembly

TossingBot: Learning to Throw Arbitrary Objects with Residual Physics

Solving Rubik's Cube with a Robot Hand

Learning Dexterous In-Hand Manipulation

NLP

Beyond English-Centric Multilingual Machine Translation

Deep learning

Parallel Context Windows Improve In-Context Learning of Large Language Models

Scaling Transformer to 1M tokens and beyond with RMT

Encoding Recurrence into Transformers

Gradient Estimation with Discrete Stein Operators

What Makes Convolutional Models Great on Long Sequence Modeling?

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

CFPNet-Medicine <-- fast U-net

Patches Are All You Need?

DeepNet: Scaling Transformers to 1,000 Layers

ResNet Strikes Back

Autoregressive Diffusion Models

A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning

Geometric Deep Learning Grids, Groups, Graphs,Geodesics, and Gauges

DATASET CONDENSATION WITH GRADIENT MATCHING

Learning to Learn Single Domain Generalization

DEUP: Direct Epistemic Uncertainty Prediction

Solving Mixed Integer Programs Using Neural Networks

High Quality Monocular Depth Estimation via Transfer Learning

Attention Is All You Need

RETHINKING ATTENTION WITH PERFORMERS

NEURAL OBLIVIOUS DECISION ENSEMBLES FOR DEEP LEARNING ON TABULAR DATA

One-shot conditional audio filtering of arbitrary sounds

Mesh R-CNN

Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning

Fully Convolutional Instance-aware Semantic Segmentation

Mask R-CNN

Faster R-CNN

Feature Pyramid Networks for Object Detection

Transformers in vision: A survey

LAMBDANETWORKS: MODELING LONG-RANGE INTERACTIONS WITHOUT ATTENTION code

In Defense of Grid Features for Visual Question Answering

Adversarially Robust Generalization Requires More Data

Improving Adversarial Robustness via Unlabeled Out-of-Domain Data

Large-Batch Training for LSTM and Beyond

RandAugment: Practical automated data augmentation with a reduced search space

Transfuser

https://arxiv.org/abs/2010.11929

Unsupervised Deep learning

A Cookbook of Self-Supervised Learning

Adversarial Masking for Self-Supervised Learning

BT-Unet: A self-supervised learning framework for biomedical image segmentation using Barlow Twins with U-Net models

MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction

Motion Representations for Articulated Animation

DINO: Emerging Properties in Self-Supervised Vision Transformers

Theory and Experiments on Vector Quantized Autoencoders

Learning deep representations by mutual information estimation and maximization

Unsupervised Learning of Object Keypoints for Perception and Control

Unsupervised Learning of Object Landmarks through Conditional Image Generation

Implicit 3D Orientation Learning for 6D Object Detection from RGB Images

Efficient Training for Positive Unlabeled Learning

Barlow Twins: Self-Supervised Learning via Redundancy Reduction

Scaling and Benchmarking Self-Supervised Visual Representation Learning

Invariant Information Clustering for Unsupervised Image Classification and Segmentation

Neural architecture search

A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions

DARTS: DIFFERENTIABLE ARCHITECTURE SEARCH

Meta Learning

OOD-MAML: Meta-Learning for Few-Shot Out-of-Distribution Detection and Classification

Implicit Layers

Deep Implicit Layers

Articles/Blogs

Learning to drive smoothly using RL

About