Amir Barati Farimani
Amir Barati Farimani has 3 papers in our library, in 2023–2025, most of them on Language models & pretraining, Evaluation & benchmarks, Reasoning; often with Chandan K. Reddy, Kazem Meidani, Parshin Shojaee.
OpenAlex · ORCID · Wikidata · h-index 51 · 269 works · 9,547 citations OpenAlex, 2026-10-14
📄 3 works in our library · 🔗 Cited 63 times in our library · ⭐ Paper Stars ranking: #9050
Affiliations
Fields, topics and concepts
📚 Shelves 9The field of science this work belongs to (OpenAlex fields).Computer Science · 3 worksPhysics and Astronomy · 3 worksComputational Theory and Mathematics · 3 worksStatistical and Nonlinear Physics · 3 worksArtificial Intelligence · 1 workMaterials Chemistry · 1 workMaterials Science · 1 workMathematics · 1 workModeling and Simulation · 1 work
🧭 Topics 3Research subjects and languages the work is about.Language models & pretraining · 3 worksEvaluation & benchmarks · 1 workReasoning · 1 work
Works by year
2020s
Papers
- LLM-SR: Scientific Equation Discovery via Programming with Large Language Models (2024 · 47 citations)
Symbolic regression aims to recover compact, interpretable formulas from observations. The search space is combinatorially huge (the task is NP-hard), and classic tools such as genetic programming over expression trees ignore the domain knowledge that human scientists bring. LLM-SR addresses this by asking a large… - LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models (2025 · 18 citations)
Benchmarks for symbolic regression, such as Feynman, SRBench and SRSD, mostly contain textbook physics laws. - SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training (2023 · 8 citations)
Deep learning models for mathematics usually handle either symbolic expressions or numeric data, and they are typically trained with supervision for one specific task.
Co-authors here
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/amir-barati-farimani/