Research map / Large language models / AI and society
OSIRIS: Bridging Analog Circuit Design and Machine Learning with Scalable Dataset Generation
Giuseppe Chiari, Michele Piccoli, Davide Zoni
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 RL-driven exploration instead of random exploration | OSIRIS Variants Generation · Miller amplifier | pscore (V): 0.0012 -> 0.00069 | Improved |
| use RL-driven exploration instead of random exploration | OSIRIS Variants Generation · Ahuja amplifier | pscore (V): 0.120 -> 0.120 | No clear effect |
| use RL-driven exploration instead of random exploration | OSIRIS Variants Generation · Feed Forward amplifier | pscore (V): 0.037 -> 0.024 | Improved |
| use RL-driven exploration instead of random exploration | OSIRIS Variants Generation · 5-Transistors OTA | pscore (V): 0.050 -> 0.047 | Improved |
| use RL-driven exploration instead of random exploration | OSIRIS Variants Generation · LPF | pscore (V): 0.102 -> 0.064 | Improved |
| use RL-driven exploration instead of random exploration | OSIRIS Variants Generation · 5-Transistors OTA | layout area (um^2): 266.3 -> 444.5 | Hurt |
| use RL-driven exploration instead of random exploration | OSIRIS Variants Generation · Ahuja amplifier | layout area (um^2): 1\,805 -> 1\,797 | Improved |
| use RL-driven exploration instead of random exploration | OSIRIS Variants Generation · LPF | layout area (um^2): 7\,916 -> 6\,635 | Improved |
| use RL-driven exploration instead of random exploration | OSIRIS Variants Generation · Miller amplifier | acquisition time (hh:mm:ss): 195:00:00 -> 96:00:00 | Improved |
| use OSIRIS random exploration instead of single-pass MAGICAL | layout generation · Miller amplifier | pscore (V): 0.2739 -> 0.0012 | Improved |
| fine-tune Qwen3-14B on OSIRIS capacitor layouts | Qwen3-14B · Capacitor layout generation | valid layouts: vanilla fails to produce valid layouts -> 100% valid outputs | 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.
- MAGICAL — Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptation (NeurIPS 2025) · better on 7 of 8 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
- FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design (NeurIPS 2025 · similarity 0.92)
- AnalogGenie: A Generative Engine for Automatic Discovery of Analog Circuit Topologies (ICLR 2025 · similarity 0.90)
- AUTOCIRCUIT-RL: Reinforcement Learning-Driven LLM for Automated Circuit Topology Generation (ICML 2025 · similarity 0.89)
- AnalogCoder: Analog Circuit Design via Training-Free Code Generation (AAAI 2025 · similarity 0.88)
- LaMAGIC: Language-Model-based Topology Generation for Analog Integrated Circuits (ICML 2024 · similarity 0.88)
- LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation (ICML 2025 · similarity 0.87)
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.
