Tech Xplore

Discrete spatial diffusion models data while obeying scientific principles

Researchers at Los Alamos National Laboratory have developed a new approach that addresses the limitations of generative AI ...
C&EN

AI screening method to speed up drug discovery

Virtual screen of 10,000 proteins and 500 million compounds takes just a day, delivers 2 million small-molecule hits ...
IEEE

Motion Planning Diffusion: Learning and Adapting Robot Motion Planning With Diffusion Models

Abstract: The performance of optimization-based robot motion planning algorithms is highly dependent on the initial solutions, commonly obtained by running a sampling-based planner to obtain a ...
IEEE

Diffusion With Reinforcement Learning for Pedestrian Trajectory Prediction

Abstract: The trajectories of pedestrian movements involve uncertainty, requiring a predictive probability model capable of modeling the underlying multimodality. To predict the trajectory of ...
GitHub

DSRL for π₀: Diffusion Steering via Reinforcement Learning

This repository provides the official implementation for our paper: Steering Your Diffusion Policy with Latent Space Reinforcement Learning (CoRL 2025). Specifically, it contains a JAX-based ...
CNX Software

ESP32-P4 learning and prototyping kit features 7-inch touchscreen, comes with 16 modules and AI lessons

Elecrow’s “All-in-One Starter Kit for ESP32-P4” is an open-source learning and prototyping platform based on the ESP32-P4 processor, offering AI, multimedia, and embedded features in a single, ...
GitHub

DeepMarket: Limit Order Book (LOB) simulation with Deep Learning.

To perform the simulation with our world agent and historical data, we extend ABIDES, an open-source agent-based interactive Python tool. To foster collaboration and help the research community we ...