Shanda Li
Scholar

Shanda Li

Google Scholar ID: -9NCUG8AAAAJ
Carnegie Mellon University
Machine Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
721
 
H-index
9
 
i10-index
9
 
Publications
15
 
Co-authors
0
 
Contact
Emailshandal@cs.cmu.eduCVOpen ↗GitHubOpen ↗
Publications
15 items
Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation
2026
Cited
0
ReproRepo: Scaling Reproducibility Audits with GitHub Repository Issues
2026
Cited
0
Characterizing initial human-AI proof formalization workflows
2026
Cited
0
Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection
2026
Cited
0
Learn Hard Problems During RL with Reference Guided Fine-tuning
2026
Cited
0
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
2026
Cited
9
Scaling Latent Reasoning via Looped Language Models
2025
Cited
0
Towards Community-Driven Agents for Machine Learning Engineering
2025
Cited
0
Resume
Academic Achievements
  • 2025: 'CodePDE: An Inference Framework for LLM-driven PDE Solver Generation' (arXiv)
  • 2024: 'Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models' (ICLR 2025)
  • 2023: 'Functional Interpolation for Relative Positions Improves Long Context Transformers' (ICLR 2024)
  • 2022: 'Is L² Physics-Informed Loss Always Suitable for Training Physics-Informed Neural Network?' (NeurIPS 2022)
  • July 2024: CMU-MATH team secured 2nd place at the AIMO Prize