FlowPlace: Flow Matching for Chip Placement

• URL: http://arxiv.org/abs/2604.23658v1
• Date: Sun, 26 Apr 2026 11:25:17 GMT
• Title: FlowPlace: Flow Matching for Chip Placement
• Abstract summary: FlowPlace aims to overcome the limitations of current generative models for chip placement.<n>It features mask-guided synthetic data generation, flow-based efficient training with flexible prior injection, and hard constraint sampling for overlap-free layouts.<n>Experiments on OpenROAD and ICCAD 2015 benchmarks show FlowPlace achieves better PPA metrics, 10-50$times$ faster sampling efficiency, and zero overlaps.
• Score: 37.01468620035496
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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$\times$ faster sampling efficiency, and zero overlaps.

Related papers

• ConFlow: Constraints-Guided Learning with Flow Matching for Motion Generation [2.0175723444555307]
  In robot motion generation we often have additional constraints that might not be present in the collected data.<n>We propose ConFlow, a constraint-guided flow matching framework that incorporates constraint information directly into the training objective.<n>Experiments on a two-robot navigation task demonstrate that ConFlow achieves lower collision rates and higher trajectory quality.
  arXiv  Detail & Related papers  (2026-07-15T23:27:04Z)
• FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction [43.791981476558384]
  Data preparation pipelines improve data quality in machine learning by transforming raw tables into learning-ready data.<n>Existing state-of-the-art (SOTA) Multi-DQN methods face three key limitations.<n>We propose FlowPipe, a unified framework that formulates pipeline synthesis as conditional probabilistic flow generation over a directed acyclic graph.
  arXiv  Detail & Related papers  (2026-06-23T15:10:00Z)
• Few-Step Diffusion Sampling Through Instance-Aware Discretizations [16.93105640007355]
  Diffusion and flow matching models generate high-fidelity data by simulating paths defined by Ordinary or Differential Equations (ODEs/SDEs)<n>We propose an instance-aware discretization framework, which learns to adapt timestep allocations based on input-dependent priors.<n>Our method consistently improves generation quality with marginal tuning cost compared to training and negligible inference overhead.
  arXiv  Detail & Related papers  (2026-03-18T12:49:38Z)
• Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling [69.7108839028336]
  Conditional Flow Matching (CFM) is a simulation-free method for training continuous normalizing flows.<n>We introduce LOOM-CFM, a novel method to extend the scope of minibatch optimal transport (OT) by preserving and optimizing these assignments across minibatches over training time.<n>Our approach demonstrates consistent improvements in the sampling speed-quality trade-off across multiple datasets.
  arXiv  Detail & Related papers  (2026-03-16T13:42:28Z)
• Riemannian MeanFlow for One-Step Generation on Manifolds [54.09734511705173]
  Flow Matching enables simulation-free training of generative models.<n>MeanFlow can be extended to manifold-valued generation where velocities lie in location-dependent tangent spaces.<n>Experiments on spheres, tori, and SO(3) demonstrate competitive one-step sampling with improved quality-efficiency trade-offs and substantially reduced sampling cost.
  arXiv  Detail & Related papers  (2026-03-11T12:41:46Z)
• Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timesteps [4.397130429878499]
  Diffusion-based generative models have achieved remarkable performance across various domains, yet their practical deployment is often limited by high sampling costs.<n>We propose SDM, a principled framework that aligns the numerical solver with the intrinsic properties of the diffusion trajectory.<n>By analyzing the ODE dynamics, we show that efficient low-order solvers suffice in early high-noise stages while higher-order solvers can be progressively deployed to handle the increasing non-linearity of later stages.
  arXiv  Detail & Related papers  (2026-02-13T05:02:07Z)
• FlowTS: Time Series Generation via Rectified Flow [67.41208519939626]
  FlowTS is an ODE-based model that leverages rectified flow with straight-line transport in probability space.<n>For unconditional setting, FlowTS achieves state-of-the-art performance, with context FID scores of 0.019 and 0.011 on Stock and ETTh datasets.<n>For conditional setting, we have achieved superior performance in solar forecasting.
  arXiv  Detail & Related papers  (2024-11-12T03:03:23Z)
• Guided Flows for Generative Modeling and Decision Making [55.42634941614435]
  We show that Guided Flows significantly improves the sample quality in conditional image generation and zero-shot text synthesis-to-speech. Notably, we are first to apply flow models for plan generation in the offline reinforcement learning setting ax speedup in compared to diffusion models.
  arXiv  Detail & Related papers  (2023-11-22T15:07:59Z)
• Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization [87.21285093582446]
  Diffusion Generative Flow Samplers (DGFS) is a sampling-based framework where the learning process can be tractably broken down into short partial trajectory segments. Our method takes inspiration from the theory developed for generative flow networks (GFlowNets)
  arXiv  Detail & Related papers  (2023-10-04T09:39:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.