How to Make Smart Architecture Decisions when Building Generative AI Apps
Explore architectural decisions for building reliable, performant generative AI apps. Learn to make smart choices, enhance safety and accuracy, and apply best practices through real-life use cases.
Flux.1 Image-to-Image and LLM Prompt Enhancement in ComfyUI
Explore image-to-image composition control and AI-assisted prompt enhancement in ComfyUI, featuring Flux.1 workflows and LLM integration for improved image generation.
Fine-tuning Flow and Diffusion Generative Models
Explore reward fine-tuning for dynamical generative models through stochastic optimal control, featuring a novel Adjoint Matching algorithm for improved consistency and realism.
Discrete Flow Matching for High-Dimensional Discrete Data Generation
Explore Discrete Flow Matching for generating high-dimensional discrete data. Learn about probability paths, sampling techniques, and improved generative perplexity in AI applications.
Lab 3 - De Novo Generation Explanation
Explore de novo molecule generation techniques with experts Emmanuel Bengio and Julien Roy in this recorded session from the 2024 Machine Learning for Drug Discovery Summer School.
Generative Models of Molecular Structures - Day 3
Explore generative models for molecular structures, focusing on applications in drug discovery and computational chemistry.
Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
Explore Diffusion Forcing, a novel training paradigm combining next-token prediction and full-sequence diffusion for enhanced sequence generation and decision-making in AI applications.
Metric Flow Matching for Smooth Interpolations on the Data Manifold
Explore Metric Flow Matching for smooth interpolations on data manifolds. Learn about conditional paths, Riemannian metrics, and geodesic interpolants. Discover applications in LiDAR navigation and cellular dynamics modeling.
Injecting Reliability into Generative AI
Explore Wolfram's vision for enhancing LLM reliability through computational intelligence. Learn to inject facts, utilize private data, and combine LLM capabilities with Wolfram Language to solve complex problems.
AI and the Future of Scientific Publishing
Explore AI's impact on scientific publishing with experts discussing new tools, methods, and workflows for arXiv, bioRxiv, medRxiv, and ScienceCast.
Which Language Should I Speak with My Computer? - Computational Conversations Episode 6
Explore the future of human-computer interaction and programming languages in the era of generative AI with Conrad Wolfram and Jon McLoone.
GFlowNet Foundations and Applications in Biological Sequence Design
Explore GFlowNet foundations and applications in biological sequence design. Learn about flow conservation, transition probabilities, and practical implementations for molecule generation and peptide design.
Towards Good Validation Metrics for Generative Models in Offline Model-Based Optimization
Explore principled evaluation frameworks for generative models in offline model-based optimization. Learn about validation metrics, dataset challenges, and strategies for measuring extrapolation capabilities.
DiGress: Discrete Denoising Diffusion for Graph Generation
Explore DiGress, a discrete denoising diffusion model for graph generation with categorical attributes. Learn about its innovative approach, challenges, and state-of-the-art performance in molecular and non-molecular datasets.
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.
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.
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.
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.
Responsible AI and Ethics in AI Engineering
Explore ethical AI engineering practices and their societal impact. Learn to adapt to the changing landscape and consider human factors when building AI-powered systems and products.
Reflected Diffusion Models: Principled Data Constraints in Generative Modeling
Explore reflected diffusion models for improved image generation. Learn about reversing stochastic differential equations, addressing numerical errors, and incorporating data constraints in principled ways.
GenPhys: From Physical Processes to Generative Models
Explore how physical processes inspire new generative models, including diffusion and Poisson flow. Learn to translate PDEs into AI algorithms and expand the design space of generative approaches.