On Medium, anyone can share insightful perspectives, useful knowledge, and life wisdom with the world.

The transformer architecture has changed the field of Artificial Intelligence forever in a sweeping fashion by bringing forth a new…

Embodied artificial intelligence is currently an active research frontier, foundation models like ChatGPT have demonstrated incredible…

Improving end-to-end learning with salient information

Can learning unify the tactile experience across different sensing modalities?

Unsupervised Learning Approach for Identifying Sports Legends in Images.

Robotics has come so far, and there are many examples of people achieving incredible tasks with them — whether it’s self-driving cars…

Scaling the size of the OCTOPI tactile VLM down to a more digestible size

An exploration of using multiple time series instead of one to improve financial time series forecasting.

In this article I’ll be going through training a robot policy step-by-step with the DROID policy learning repository with RLDS format data…

3D UNET Backbone With Adjusted Conditioning for Diffusion Networks on 3D Object Representation Generation

Explaining diffusion policy, a powerful imitation learning method and the building block for robotics foundation models

Can learning unify the tactile experience across different sensing modalities?

The transformer architecture has changed the field of Artificial Intelligence forever in a sweeping fashion by bringing forth a new…

YouTube video by Unitree Robotics

Improving end-to-end learning with salient information

Can learning unify the tactile experience across different sensing modalities?

Modeling Problem Statements with LLMs

A Framework for Attention-based Permutation-Invariant Neural Networks

Ongoing pre-publication research on humanoids and related technologies including paper reviews and tutorials.

Embodied artificial intelligence is currently an active research frontier, foundation models like ChatGPT have demonstrated incredible…

Embodied artificial intelligence is currently an active research frontier, foundation models like ChatGPT have demonstrated incredible…

How to leverage large language models for robotic grasping and code generation

Text-Conditioned Image Generation on FashionMNIST using CLIP Latents

Embodied artificial intelligence is currently an active research frontier, foundation models like ChatGPT have demonstrated incredible…

Over the past three months, I have attended A3 - Association for Advancing Automation 𝐇𝐮𝐦𝐚𝐧𝐨𝐢𝐝 𝐑𝐨𝐛𝐨𝐭 𝐅𝐨𝐫𝐮𝐦 in Memphis, IEEE RAS HUMANOIDS… | 28 comments on LinkedIn

In this ablation study, the “Building CLIP from Scratch” by Matt Nguyen was leveraged. The reference source can be found here…

ChatGPT is never shy at pretending to perform deep thought, but — like our brain — might need better tools to reason accurately

Diffusion Models for 3D Occupancy Synthesis from Partial Observation

Autonomous driving, Geo-localization, Robotic surgery, and Robotic pose estimation

Nikolaus Correll Computer science professor Nikolaus Correll and his lab at CU Boulder have been awarded $1.8 million by the U.S. Department of Energy Advanced

How to train locally and merge the resulting weights, not the raw data itself, to learn using a team of robots

Enabling robots to understand and reason through touch!

Using vision language models to resolve multi-step manipulation tasks

The scientific publication system is kind of broken. On the one end of the spectrum are “high-impact publications” that charge thousands…

How to leverage large language models for robotic grasping and code generation