Related papers: Accurate transition state generation with an objec…

The reaction dynamics of O(3P) + O2(3Sigma_g-) collisions in the O3(1A') electronic ground state is characterized on a high-level MRCI+Q/aug-cc-pVQZ potential energy surface represented as a reproducing kernel. For the atom exchange…

Diffusion generative modeling has become a promising approach for learning robotic manipulation tasks from stochastic human demonstrations. In this paper, we present Diffusion-EDFs, a novel SE(3)-equivariant diffusion-based approach for…

3D molecule generation is crucial for drug discovery and material science, requiring models to process complex multi-modalities, including atom types, chemical bonds, and 3D coordinates. A key challenge is integrating these modalities of…

Transition State Theory overestimates reaction rates in solution because conventional dividing surfaces between reagents and products are crossed many times by the same reactive trajectory. We describe a recipe for constructing a…

Small separation between reactants, not exceeding $10^{-8}-10^{-7}cm$, is the necessary condition for various chemical reactions. It is shown that random advection and stretching by turbulence leads to formation of scalar-enriched sheets of…

Recently, the impressive generative capabilities of diffusion models have been demonstrated, producing images with remarkable fidelity. Particularly, existing methods for the 3D object generation tasks, which is one of the fastest-growing…

Calculating how long a coupled multi-species reactive-diffusive transport process in a heterogeneous medium takes to effectively reach steady state is important in many applications. In this paper, we show how the time required for such…

Due to the lack of large-scale text-3D correspondence data, recent text-to-3D generation works mainly rely on utilizing 2D diffusion models for synthesizing 3D data. Since diffusion-based methods typically require significant optimization…

3D object detection received increasing attention in autonomous driving recently. Objects in 3D scenes are distributed with diverse orientations. Ordinary detectors do not explicitly model the variations of rotation and reflection…

We introduce a novel, training-free system for reconstructing, understanding, and rendering 3D indoor scenes from a sparse set of unposed RGB images. Unlike traditional radiance field approaches that require dense views and per-scene…

We report a series of deep learning models to solve complex forward and inverse design problems in molecular modeling and design. Using both diffusion models inspired by nonequilibrium thermodynamics and attention-based transformer…

In many biological situations, a species arriving from a remote source diffuses in a domain confined between two parallel surfaces until it finds a binding partner. Since such a geometric shape falls in between two- and three-dimensional…

The quantum normal form approach to quantum transition state theory is used to compute the cumulative reaction probability for collinear exchange reactions. It is shown that for heavy atom systems like the nitrogen exchange reaction the…

Breakthroughs in high-accuracy protein structure prediction, such as AlphaFold, have established receptor-based molecule design as a critical driver for rapid early-phase drug discovery. However, most approaches still struggle to balance…

Conical intersections play a pivotal role in excited-state quantum dynamics. Capturing transient molecular structures near conical intersections remains challenging due to the rapid timescales and subtle structural changes involved. We…

Learning a stationary diffusion amounts to estimating the parameters of a stochastic differential equation whose stationary distribution matches a target distribution. We build on the recently introduced kernel deviation from stationarity…

Molecular conformer generation is a fundamental task in computational chemistry. Several machine learning approaches have been developed, but none have outperformed state-of-the-art cheminformatics methods. We propose torsional diffusion, a…

3D object detection is essential for understanding 3D scenes. Contemporary techniques often require extensive annotated training data, yet obtaining point-wise annotations for point clouds is time-consuming and laborious. Recent…

Diffusion models have achieved remarkable generative quality but remain bottlenecked by costly iterative sampling. Recent training-free methods accelerate diffusion process by reusing model outputs. However, these methods ignore denoising…

The quasi-steady state approximation and time-scale separation are commonly applied methods to simplify models of biochemical reaction networks based on ordinary differential equations (ODEs). The concentrations of the "fast" species are…