# FlowPlace: Flow Matching for Chip Placement

arXiv: https://arxiv.org/abs/2604.23658 · HTML: https://mlsanity.com/paper/2604.23658/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 10 of its 31 references that are in the map.
- First posted on arXiv 26 Apr 2026.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Improving and generalizing flow-based generative models with minibatch optimal transport](https://mlsanity.com/paper/2302.00482/) (2023)
- [On Joint Learning for Solving Placement and Routing in Chip Design](https://mlsanity.com/paper/2111.00234/) (2021)
- [ChiPFormer: Transferable Chip Placement via Offline Decision Transformer](https://mlsanity.com/paper/2306.14744/) (2023)
- [Gradient-Free Generation for Hard-Constrained Systems](https://mlsanity.com/paper/2412.01786/) (2024)
- [Hier-RTLMP: A Hierarchical Automatic Macro Placer for Large-scale Complex IP Blocks](https://mlsanity.com/paper/2304.11761/) (2023)
- [Chip Placement with Diffusion Models](https://mlsanity.com/paper/2407.12282/) (2024)
- [That Chip Has Sailed: A Critique of Unfounded Skepticism Around AI for Chip Design](https://mlsanity.com/paper/2411.10053/) (2024)

## Built on by (most cited first, 1 of 1)

- [Trinity: One Differentiable Physics for Training, Refining and Scoring Generative Floorplanners](https://mlsanity.com/paper/2610.04957/) (2026)

## Abstract (arXiv)

Chip placement plays an important role in physical design. While generative models like diffusion models offer promising learning-based solutions, current methods have the following limitations: they use random synthetic data for pre-training, require long sampling times, and often result in overlaps due to their dependence on gradient-based solvers during the sampling process. To overcome these issues, we propose FlowPlace, which features mask-guided synthetic data generation, flow-based efficient training with flexible prior injection, and hard constraint sampling for overlap-free layouts. Experiments on OpenROAD and ICCAD 2015 benchmarks show FlowPlace achieves better PPA metrics, 10-50× faster sampling efficiency, and zero overlaps.