New flow-map framework lets generators expand output size on the fly
gottapatchemall · x · 2026-07-29
Expanding Flow Maps lets flow models grow their output size during generation
The paper introduces Expanding Generative Flows (EFlows) and Expanding Flow Maps (EFMs), a framework for few-step flow-based generation that does not require a fixed output canvas upfront.
- Instead of committing to a sequence length or state dimension at initialization, the model can expand the state with new coordinates or tokens as generation proceeds.
- The framework splits generation into two learnable parts: an expand operator that adds new state, and a transport map that denoises and moves the expanded state along the interpolation path.
- The same idea is presented as a unified way to handle variable-length text, graphs, and 3D molecular conformers.
- The authors argue that output size itself can be treated as a learned degree of freedom, rather than a fixed design choice.
Related event: New Flow Map Framework Enables Dynamic Output Expansion During Inference(3 posts)→
More from Research
- NVIDIA opens a model that suggests the next calibration step for quantum processors — AccBalanced · 2026-07-29
- MIT-led preprint uses machine learning to guide Rubisco evolution — chaitjo · 2026-07-29
- OpenAI says coding agents are taking over routine science work — eyishazyer · 2026-07-29
- Qwen3-VL plus DeCoDe lifts accuracy from 27.8% to 89.2% on novel vision tests — HildeKuehne · 2026-07-29
- MazeBench is a 3D open world benchmark that current agents cannot clear — giffmana · 2026-07-29
- ECCV 2026 paper says some multimodal LLMs do worse with one-shot examples — HildeKuehne · 2026-07-29