ActFlow Scheme Enables Generative Models to Actively Expand Design Space
josephdviviano · x · 2026-08-27
ActFlow is a continued pre-training scheme designed to actively expand the valid design space reachable by flow and diffusion models. Termed 'generable set expansion', it represents a new learning principle for out-of-distribution generative modeling and a step toward evolvable search spaces for scientific discovery.
More from Research
- New Podcast Episode: Coupled Local and Global World Models in Robotics — micoolcho · 2026-08-27
- RayDer enables static-scene NVS from dynamic internet video, scaling like an LLM — CSProfKGD · 2026-08-27
- Hugging Face uses Inkling-Small to generate paper summaries — victormustar · 2026-08-27
- Anders Sandberg: AI can automate data gathering, map cross-country links — anderssandberg · 2026-08-27
- Interactive paper explorer built with Claude for data analysis — anderssandberg · 2026-08-27
- Michael Levin: Forms of Life, Forms of Mind Q&A — drmichaellevin · 2026-08-27