Valence Labs Courses

Contextual AI Models for Single-cell Protein Biology

Explore PINNACLE, a geometric deep learning approach generating context-aware protein representations for enhanced understanding of protein function and interactions across biological contexts.

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

Identifying Representations for Intervention Extrapolation

Explore identifiable representations for intervention extrapolation, improving generalizability in machine learning. Learn theoretical foundations and practical applications through simulations and Q&A.

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

The Continuous Language of Protein Structure

Explore a novel approach to protein structure generation using continuous autoregressive language models. Learn about innovative techniques for in silico protein design and their potential applications.

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

The Future of Chemistry - Self-Driving Laboratories and AI-Driven Discovery

Explore self-driving laboratories revolutionizing scientific discovery through AI and automation. Learn about cutting-edge applications, key elements, and opportunities in chemistry, materials science, and biotechnology.

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

Weisfeiler-Leman for Euclidean Equivariant Machine Learning

Explore Weisfeiler Leman's application in Euclidean equivariant machine learning, focusing on graph neural networks, point clouds, and the WeLNet architecture for improved N-Body dynamics and molecular conformation generation.

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

A Causal Inference Framework for Combinatorial Interventions

Explore a novel latent factor model for estimating causal effects of combinatorial interventions, addressing challenges in factorial experiments and recommendation systems.

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

Kolmogorov-Arnold Networks - Alternatives to Multi-Layer Perceptrons

Explore Kolmogorov-Arnold Networks as alternatives to MLPs, offering improved accuracy and interpretability in AI. Discover their potential in data fitting, PDE solving, and scientific law discovery.

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

D-Flow: Differentiating through Flows for Controlled Generation

Explore D-Flow framework for controlled generation in AI models, optimizing source points through flow differentiation. Learn applications in inverse problems and conditional generation.

• YouTube
• 1 hour 3 minutes
• On-Demand
• Free Video

EquiReact: An Equivariant Neural Network for Chemical Reactions

Explore EquiReact, an equivariant neural network for predicting chemical reaction properties using 3D structures. Learn its advantages in flexibility, extrapolation, and data efficiency.

• YouTube
• 1 hour 1 minute
• On-Demand
• Free Video

Multimodal Language Models for Mapping the Genotype-Phenotype Relationship

Explore multimodal language models for mapping genotype-phenotype relationships. Learn about integrated genetics frameworks and their applications in analyzing cellular heterogeneity and gene polyfunctionality.

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

Causal Abstractions Using Generalized Functions

Explore generalized functions and their applications in causal models, including nondeterministic structural models and novel types of model reduction, leading to new definitions of causal abstraction.

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

Learning to Group Auxiliary Datasets for Molecule Prediction

Explore MolGroup: a novel approach to optimize auxiliary dataset selection in molecular machine learning, enhancing model performance through intelligent data grouping.

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

Smooth, Exact Rotational Symmetrization for Deep Learning on Point Clouds

Explore rotational symmetrization for deep learning on point clouds, enhancing AI models for chemical and materials modeling with exact compliance to physical constraints.

• YouTube
• 1 hour 15 minutes
• On-Demand
• Free Video

Uncovering and Inducing Interpretable Causal Structure in Deep Learning Models

Explore causal abstraction theory for uncovering and inducing interpretable structures in deep learning models, focusing on faithful explanations and interventions during analysis and training.

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

Local Search GFlowNets - Enhancing Sampling Quality for Drug Discovery

Explore Local Search GFlowNets, a novel algorithm enhancing sampling quality for structured sequence generation in drug discovery and other fields through improved targeting of high-reward regions.

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