Papers by Shangyin Tan

3 papers
S*: Test Time Scaling for Code Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: S* is the first hybrid test-time scaling framework that significantly improves the coverage and selection accuracy of generated code.
Approach: They propose a hybrid test-time scaling framework that augments parallel scaling with sequential scaling to further increase the performance.
Outcome: The proposed framework outperforms existing scaling approaches in large-scale modeling and reasoning models.
SlimFit: Memory-Efficient Fine-Tuning of Transformer-based Models Using Training Dynamics (2024.naacl-long)

Copied to clipboard

Challenge: SlimFit reduces the memory requirements of transformer-based models by analyzing their training dynamics and freezing less-contributory layers during fine-tuning.
Approach: They propose a tool that analyzes transformer-based models and freezes less-contributory layers during fine-tuning to reduce the overall on-device memory usage.
Outcome: SlimFit reduces the memory requirements of transformer-based models by analyzing their training dynamics and freezing less-contributory layers during fine-tuning.
LangProBe: a Language Program Benchmark (2025.findings-emnlp)

Copied to clipboard

Challenge: Composing language models into multi-step language programs is a mainstream paradigm for building AI systems, but tradeoffs in this space have only scarcely been studied before.
Approach: They propose a benchmarking tool to evaluate the architectures and optimization strategies for language programs . they find that optimized language programs offer strong cost-quality Pareto improvement .
Outcome: The proposed framework evaluates the impact of program architectures and optimizers on quality and cost.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations