Research map / Reinforcement learning / Offline RL
ChiPFormer: Transferable Chip Placement via Offline Decision Transformer
Yao Lai, Jinxin Liu, Zhentao Tang, Bin Wang, Jianye HAO, Ping Luo
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use ChiPFormer(workflow) instead of the strongest reported baseline | mixed-size placement · public benchmarks in the reported tables | HPWL | Improved |
| Pretrain on more offline circuits (ablation) | ChiPFormer · adaptec1; unseen-circuit transfer | HPWL | Improved |
| Add a circuit token encoding circuit topology (ablation) | ChiPFormer · 12 ISPD05 and ICCAD04 circuits; zero-shot transfer | placement performance | Improved |
| Replace the priority-based replay buffer with FIFO storage (ablation) | ChiPFormer finetuning · unseen chip placement | placement quality and variance | Hurt |
| Remove the entropy loss (ablation) | ChiPFormer finetuning · unseen chip placement | placement quality | Hurt |
| Use 300 ChiPFormer rollouts rather than 3k baseline rollouts | unseen macro placement · 12 unseen circuits | HPWL: better performance in 10 out of 12 tasks | Mixed |
| Increase ChiPFormer rollout count from 300 to 2k | unseen macro placement · 12 unseen circuits | HPWL: minimal wirelength in 10 out of 12 circuits | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MaskPlace — MaskPlace: Fast Chip Placement via Reinforced Visual Representation Learning (NeurIPS 2022) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer (NeurIPS 2024 · similarity 0.90)
- Chip Placement with Diffusion Models (ICML 2025 · similarity 0.89)
- Reinforcement Learning within Tree Search for Fast Macro Placement (ICML 2024 · similarity 0.87)
- Benchmarking End-To-End Performance of AI-Based Chip Placement Algorithms (NeurIPS 2025 · similarity 0.87)
- See it to Place it: Evolving Macro Placements with Vision Language Models (NeurIPS 2026 · similarity 0.87)
- Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization (ICLR 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
