<aside> 💡 Format was shamelessly copied from Kurin ViTaly.

</aside>

In one of those sleepless nights, I noticed that I am reading too many papers and I realized I had to organize all these knowledge into one place. Here is the result

Machine Learning Basics

Decoupled Weight Decay Regularization

Random

Computer Vision

Complex-Valued Autoencoders for Object Discovery

Image orientation estimation with Convolutional Networks

3D Shape Perception Integrates Intuitive Physics and Analysis-by-Synthesis

The Veiled Virgin illustrates visual segmentation of shape by cause

Model-based RL

Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation

Tactile Sensing

https://s3-us-west-2.amazonaws.com/secure.notion-static.com/970f92a8-b419-4d8e-9a3c-a021770997b3/Untitled.png

Sensing shear forces during food manipulation

Maintaining Grasps within Slipping Bound by Monitoring Incipient Slip

Shape-independent Hardness Estimation Using Deep Learning and a Gelsight Tactile Sensor

VisuoTactile 6D Pose Estimation of In-Hand Object using Vision and Tactile Sensor Data

Taxim: An example-based Simulation Model for GelSight Tactile Sensors

Tactile-RL for Insertion: Generalization to Objects of Unknown Geometry

Reinforcement Learning

NLP/Multimodal

PaLM-E: An Embodied Multimodal Language Model