Valence Labs Courses

Mosaic-SDF for 3D Generative Models

Explore Mosaic-SDF, a novel 3D shape representation for generative models. Learn its design principles, preprocessing, and application in flow matching for efficient 3D generation.

• YouTube
• 1 hour 16 minutes
• On-Demand
• Free Video

Stability-Aware Boltzmann Estimator Training of Neural Network Interatomic Potentials

Explore advanced neural network interatomic potentials for molecular dynamics simulations using Stability-Aware Boltzmann Estimator Training to enhance stability and accuracy across various systems and architectures.

• YouTube
• 1 hour 22 minutes
• On-Demand
• Free Video

Combinatorial Perturbation Prediction Using Causally-Inspired Neural Networks

Explore PDGRAPHER, a novel graph neural network model for phenotype-driven drug discovery. Learn how it predicts perturbagens to reverse disease effects, offering faster and more efficient therapeutic target identification.

• YouTube
• 1 hour 5 minutes
• On-Demand
• Free Video

A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems

Explore geometric graph neural networks for 3D atomic systems, covering fundamental concepts, architectures, datasets, and applications in computational modeling of molecules, proteins, and materials.

• YouTube
• 1 hour 21 minutes
• On-Demand
• Free Video

HyperPCM: Robust Task-Conditioned Modeling of Drug-Target Interactions

Explore HyperPCM, a robust method for predicting drug-target interactions using hypernetworks. Learn about its state-of-the-art performance on benchmarks and excellence in zero-shot inference for unseen protein targets.

• YouTube
• 50 minutes
• On-Demand
• Free Video

Diffusion Models for Sampling Rare Events in Chemistry

Explore advanced diffusion models for generating transition state structures in chemical reactions, accelerating reaction mechanism discovery and network exploration.

• YouTube
• 48 minutes
• On-Demand
• Free Video

MFBind - A Multi-Fidelity Approach for Evaluating Drugs in Generative Modeling

Explore MFBind, a multi-fidelity approach integrating docking and binding free energy simulations for improved drug discovery generative modeling. Learn its advantages over current methods.

• YouTube
• 55 minutes
• On-Demand
• Free Video

Meaningful Causal Aggregation and Paradoxical Confounding

Explore causal aggregation challenges, macro interventions, and micro-realism in statistical analysis. Gain insights into ill-defined causality and its impact on confounding in aggregated variables.

• YouTube
• 56 minutes
• On-Demand
• Free Video

Evaluating Retrosynthesis with Syntheseus and Retro-Fallback

Explore advancements in synthesis planning evaluation through syntheseus and retro-fallback, enhancing molecule discovery with probabilistic uncertainty and new search algorithms.

• YouTube
• 58 minutes
• On-Demand
• Free Video

MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation

Explore MultiDiffusion: a framework for controllable image generation using pre-trained diffusion models. Learn about panorama creation, high-resolution outputs, and versatile user controls without retraining.

• YouTube
• 1 hour 4 minutes
• On-Demand
• Free Video

Additive Decoders for Latent Variables Identification

Explore additive decoders for latent variable identification and out-of-support image generation in representation learning. Gain insights into nonlinear ICA and object-centric representation learning.

• YouTube
• 48 minutes
• On-Demand
• Free Video

Removing Biases from Molecular Representations via Information Maximization

Explore InfoCORE, an innovative approach to remove batch effects in drug screening data, enhancing molecular representations for improved property prediction and molecule-phenotype retrieval.

• YouTube
• 53 minutes
• On-Demand
• Free Video

Equivariant Scalar Fields for Molecular Docking with Fast Fourier Transforms

Explore machine learning-accelerated molecular docking using equivariant scalar fields and fast Fourier transforms for efficient drug discovery and virtual screening.

• YouTube
• 38 minutes
• On-Demand
• Free Video

Generalization in Diffusion Models from Geometry-Adaptive Harmonic Representation

Explore generalization in diffusion models through geometry-adaptive harmonic representation. Analyze denoising DNNs, score functions, and inductive biases to understand high-dimensional density learning and optimal basis adaptation.

• YouTube
• 1 hour 35 minutes
• On-Demand
• Free Video

Manifold Diffusion Fields - Learning Generative Models of Continuous Functions on Riemannian Manifolds

Explore Manifold Diffusion Fields for generating continuous functions on Riemannian manifolds. Learn about spectral geometry, intrinsic coordinate systems, and applications in AI for drug discovery.

• YouTube
• 27 minutes
• On-Demand
• Free Video