Valence Labs Courses

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
• Self-Paced
• Free Video

Linear Structure of High-Level Concepts in Text-Controlled Generative Models

Explore the linear structure of high-level concepts in text-controlled generative models, focusing on embedding, representation, and semantic encoding for precise model control.

• YouTube
• 1 hour 8 minutes
• Self-Paced
• Free Video

AlphaFold Meets Flow Matching for Generating Protein Ensembles

Explore flow-based generative modeling for protein conformational landscapes using AlphaFold and ESMFold, offering precise and diverse structural predictions with potential to accelerate molecular dynamics simulations.

• YouTube
• 57 minutes
• Self-Paced
• Free Video

Multiflow: Protein Structure and Sequence Co-generation

Explore protein structure and sequence co-generation using Discrete Flow Models and Multiflow, a novel approach combining discrete and continuous data for improved AI-driven drug discovery.

• YouTube
• 55 minutes
• Self-Paced
• Free Video

BISCUIT: Causal Representation Learning from Binary Interactions

Explore causal representation learning in AI using BISCUIT method. Learn to identify causal variables from binary interactions for applications in robotics and embodied AI.

• YouTube
• 1 hour 4 minutes
• Self-Paced
• Free Video

De Novo Design of High-Affinity Binders for Bioactive Helical Peptides

Explore advanced techniques for designing high-affinity binders to helical peptides, including parametric generation and deep learning methods. Learn applications in disease detection and biosensor development.

• YouTube
• 37 minutes
• Self-Paced
• Free Video

Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion

Explore advanced diffusion models with Consistency Trajectory Models, improving sample quality and efficiency in AI-driven image generation. Learn novel sampling techniques and state-of-the-art results.

• YouTube
• 51 minutes
• Self-Paced
• Free Video

Integrating Single-Cell Data with Substantial Batch Effects - Improving cVAE Regularization

Explore advanced techniques for integrating single-cell data with substantial batch effects, focusing on cVAE regularization constraints to improve batch correction while preserving biological information.

• YouTube
• 51 minutes
• Self-Paced
• Free Video

Protein Discovery with Discrete Walk-Jump Sampling

Explore discrete generative modeling for protein discovery using Walk-Jump Sampling. Learn to train energy functions, sample with Langevin MCMC, and optimize for distributional conformity in antibody design.

• YouTube
• 55 minutes
• Self-Paced
• Free Video

Predictive Chemistry Augmented with Text Retrieval

Explore TextReact: a novel method enhancing predictive chemistry models with text retrieval from literature, improving reaction condition recommendations and retrosynthesis predictions.

• YouTube
• 57 minutes
• Self-Paced
• Free Video

Weakly Supervised Causal Representation Learning

Explore weakly supervised causal representation learning, its theoretical foundations, and practical applications in disentangling causal variables from unstructured data like images for improved causal reasoning.

• YouTube
• 1 hour 2 minutes
• Self-Paced
• Free Video

MOFDiff: Coarse-grained Diffusion for Metal-Organic Framework Design

Explore coarse-grained diffusion for metal-organic framework design. Learn about MOFDiff's innovative approach to generating diverse MOF structures for applications like carbon capture.

• YouTube
• 1 hour 14 minutes
• Self-Paced
• Free Video

Structured State-Space Sequence Models for De Novo Drug Design

Explore the potential of Structured State-Space Sequence (S4) models in advancing chemical language modeling for de novo drug design, including bioactive compound identification and natural product design.

• YouTube
• 57 minutes
• Self-Paced
• Free Video

Conditional Graph Information Bottleneck for Molecular Relational Learning

Explore a novel framework for molecular relational learning using graph neural networks to detect core subgraphs and predict interactions between molecular pairs.

• YouTube
• 44 minutes
• Self-Paced
• Free Video

Identifiable Deep Generative Models via Sparse Decoding

Explore sparse VAE for unsupervised learning, uncovering identifiable latent factors in high-dimensional data. Discover theoretical guarantees and practical applications in various domains.

• YouTube
• 1 hour 3 minutes
• Self-Paced
• Free Video