Gallery

The banner shows a manipulator learning how to slide a puck to reach the target (red point) using Reinforcement Learning

DNA dance and fluctuation in graphene nanopore

Proline polypeptide translocation in MoS2 nanopore

Ligand-directed conformational changes in Mu-Opioid receptor

Using Deep Learning to generate turbulent wake behind a cylinder

Generative machine learning models can accurately predict the thermal diffusion

Structure and dynamics of water molecules in CNT confinement

Detection of allosteric binding sites of GPCRs with machine learning

Robot we created in MAIL that learns to Crawl using RL

Fluid Simulation with Graph Neural Networks

New research, explained in motion

Six conceptual animations introduce image-to-toolpath generation, scientific equation discovery, scalable transformer modeling, robotic clay shaping, adsorption configuration search, and metal–organic framework generation. These illustrations explain the ideas; they are not model outputs or experimental results.

Conceptual Image2Gcode animation: target image, generated toolpath, and layer-by-layer manufacturing. Illustration, not a model output.

Conceptual LLM-SR animation: propose equation programs, fit parameters, evaluate, and refine. Uses synthetic illustrative data.

Conceptual FactFormer animation showing a spatial field, axis-wise interactions, and combined information. Illustration, not simulation or model output.

Conceptual LLM-Craft animation: shape goal, language-guided action planning, and iterative clay deformation. Not experimental footage. Source: https://arxiv.org/abs/2406.08648

Conceptual Adsorb-Agent animation: propose adsorption configurations, evaluate candidates, and refine search using feedback. Schematic, without numerical research results. Source: https://arxiv.org/abs/2410.16658

Conceptual MOFGPT animation: learn MOFid representations, generate material candidates, and guide generation using validity, novelty, and target properties. Abstract lattice, not a generated crystal. Source: https://arxiv.org/abs/2506.00198

Google Sites

Report abuse